Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +207 -0
- added_tokens.json +28 -0
- all_results.json +8 -0
- chat_template.jinja +120 -0
- config.json +68 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00014.safetensors +3 -0
- model-00002-of-00014.safetensors +3 -0
- model-00003-of-00014.safetensors +3 -0
- model-00004-of-00014.safetensors +3 -0
- model-00005-of-00014.safetensors +3 -0
- model-00006-of-00014.safetensors +3 -0
- model-00007-of-00014.safetensors +3 -0
- model-00008-of-00014.safetensors +3 -0
- model-00009-of-00014.safetensors +3 -0
- model-00010-of-00014.safetensors +3 -0
- model-00011-of-00014.safetensors +3 -0
- model-00012-of-00014.safetensors +3 -0
- model-00013-of-00014.safetensors +3 -0
- model-00014-of-00014.safetensors +3 -0
- model.safetensors.index.json +1066 -0
- preprocessor_config.json +39 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +241 -0
- train_results.json +8 -0
- trainer_log.jsonl +135 -0
- trainer_state.json +981 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
- video_preprocessor_config.json +41 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-VL-32B-Instruct
|
| 3 |
+
language: en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
model_name: MussEsSein/STEP-sft-Qwen3-VL-32B-Instruct
|
| 6 |
+
batch_size: 128
|
| 7 |
+
learning_rate: 1e-4
|
| 8 |
+
epochs: 2.0
|
| 9 |
+
dataset: mix_data_v2_crop_560
|
| 10 |
+
crop_size: 560
|
| 11 |
+
method: full SFT + Ahead projector
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Model Card for Model ID
|
| 15 |
+
|
| 16 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
## Model Details
|
| 21 |
+
|
| 22 |
+
### Model Description
|
| 23 |
+
|
| 24 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
- **Developed by:** [More Information Needed]
|
| 29 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 30 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 31 |
+
- **Model type:** [More Information Needed]
|
| 32 |
+
- **Language(s) (NLP):** en
|
| 33 |
+
- **License:** apache-2.0
|
| 34 |
+
- **Finetuned from model [optional]:** Qwen/Qwen3-VL-32B-Instruct
|
| 35 |
+
|
| 36 |
+
### Model Sources [optional]
|
| 37 |
+
|
| 38 |
+
<!-- Provide the basic links for the model. -->
|
| 39 |
+
|
| 40 |
+
- **Repository:** [More Information Needed]
|
| 41 |
+
- **Paper [optional]:** [More Information Needed]
|
| 42 |
+
- **Demo [optional]:** [More Information Needed]
|
| 43 |
+
|
| 44 |
+
## Uses
|
| 45 |
+
|
| 46 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 47 |
+
|
| 48 |
+
### Direct Use
|
| 49 |
+
|
| 50 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 51 |
+
|
| 52 |
+
[More Information Needed]
|
| 53 |
+
|
| 54 |
+
### Downstream Use [optional]
|
| 55 |
+
|
| 56 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 57 |
+
|
| 58 |
+
[More Information Needed]
|
| 59 |
+
|
| 60 |
+
### Out-of-Scope Use
|
| 61 |
+
|
| 62 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 63 |
+
|
| 64 |
+
[More Information Needed]
|
| 65 |
+
|
| 66 |
+
## Bias, Risks, and Limitations
|
| 67 |
+
|
| 68 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 69 |
+
|
| 70 |
+
[More Information Needed]
|
| 71 |
+
|
| 72 |
+
### Recommendations
|
| 73 |
+
|
| 74 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 75 |
+
|
| 76 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 77 |
+
|
| 78 |
+
## How to Get Started with the Model
|
| 79 |
+
|
| 80 |
+
Use the code below to get started with the model.
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
## Training Details
|
| 85 |
+
|
| 86 |
+
### Training Data
|
| 87 |
+
|
| 88 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
### Training Procedure
|
| 93 |
+
|
| 94 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 95 |
+
|
| 96 |
+
#### Preprocessing [optional]
|
| 97 |
+
|
| 98 |
+
[More Information Needed]
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
#### Training Hyperparameters
|
| 102 |
+
|
| 103 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 104 |
+
|
| 105 |
+
#### Speeds, Sizes, Times [optional]
|
| 106 |
+
|
| 107 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 108 |
+
|
| 109 |
+
[More Information Needed]
|
| 110 |
+
|
| 111 |
+
## Evaluation
|
| 112 |
+
|
| 113 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 114 |
+
|
| 115 |
+
### Testing Data, Factors & Metrics
|
| 116 |
+
|
| 117 |
+
#### Testing Data
|
| 118 |
+
|
| 119 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 120 |
+
|
| 121 |
+
[More Information Needed]
|
| 122 |
+
|
| 123 |
+
#### Factors
|
| 124 |
+
|
| 125 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 126 |
+
|
| 127 |
+
[More Information Needed]
|
| 128 |
+
|
| 129 |
+
#### Metrics
|
| 130 |
+
|
| 131 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
### Results
|
| 136 |
+
|
| 137 |
+
[More Information Needed]
|
| 138 |
+
|
| 139 |
+
#### Summary
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
|
| 143 |
+
## Model Examination [optional]
|
| 144 |
+
|
| 145 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 146 |
+
|
| 147 |
+
[More Information Needed]
|
| 148 |
+
|
| 149 |
+
## Environmental Impact
|
| 150 |
+
|
| 151 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 152 |
+
|
| 153 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 154 |
+
|
| 155 |
+
- **Hardware Type:** [More Information Needed]
|
| 156 |
+
- **Hours used:** [More Information Needed]
|
| 157 |
+
- **Cloud Provider:** [More Information Needed]
|
| 158 |
+
- **Compute Region:** [More Information Needed]
|
| 159 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 160 |
+
|
| 161 |
+
## Technical Specifications [optional]
|
| 162 |
+
|
| 163 |
+
### Model Architecture and Objective
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
### Compute Infrastructure
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Hardware
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
#### Software
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
## Citation [optional]
|
| 180 |
+
|
| 181 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 182 |
+
|
| 183 |
+
**BibTeX:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
**APA:**
|
| 188 |
+
|
| 189 |
+
[More Information Needed]
|
| 190 |
+
|
| 191 |
+
## Glossary [optional]
|
| 192 |
+
|
| 193 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## More Information [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Authors [optional]
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
|
| 205 |
+
## Model Card Contact
|
| 206 |
+
|
| 207 |
+
[More Information Needed]
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1877022766792704.0,
|
| 4 |
+
"train_loss": 0.2793045342631301,
|
| 5 |
+
"train_runtime": 58447.463,
|
| 6 |
+
"train_samples_per_second": 5.908,
|
| 7 |
+
"train_steps_per_second": 0.046
|
| 8 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"hidden_size": 5120,
|
| 8 |
+
"image_token_id": 151655,
|
| 9 |
+
"model_type": "qwen3_vl",
|
| 10 |
+
"pad_token_id": 151643,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"bos_token_id": 151643,
|
| 15 |
+
"dtype": "float32",
|
| 16 |
+
"eos_token_id": 151645,
|
| 17 |
+
"head_dim": 128,
|
| 18 |
+
"hidden_act": "silu",
|
| 19 |
+
"hidden_size": 5120,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 25600,
|
| 22 |
+
"max_position_embeddings": 262144,
|
| 23 |
+
"model_type": "qwen3_vl_text",
|
| 24 |
+
"num_attention_heads": 64,
|
| 25 |
+
"num_hidden_layers": 64,
|
| 26 |
+
"num_key_value_heads": 8,
|
| 27 |
+
"rms_norm_eps": 1e-06,
|
| 28 |
+
"rope_scaling": {
|
| 29 |
+
"mrope_interleaved": true,
|
| 30 |
+
"mrope_section": [
|
| 31 |
+
24,
|
| 32 |
+
20,
|
| 33 |
+
20
|
| 34 |
+
],
|
| 35 |
+
"rope_type": "default"
|
| 36 |
+
},
|
| 37 |
+
"rope_theta": 5000000,
|
| 38 |
+
"use_cache": false,
|
| 39 |
+
"vocab_size": 151936
|
| 40 |
+
},
|
| 41 |
+
"tie_word_embeddings": false,
|
| 42 |
+
"transformers_version": "4.57.1",
|
| 43 |
+
"use_cache": false,
|
| 44 |
+
"video_token_id": 151656,
|
| 45 |
+
"vision_config": {
|
| 46 |
+
"deepstack_visual_indexes": [
|
| 47 |
+
8,
|
| 48 |
+
16,
|
| 49 |
+
24
|
| 50 |
+
],
|
| 51 |
+
"depth": 27,
|
| 52 |
+
"dtype": "float32",
|
| 53 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 54 |
+
"hidden_size": 1152,
|
| 55 |
+
"in_channels": 3,
|
| 56 |
+
"initializer_range": 0.02,
|
| 57 |
+
"intermediate_size": 4304,
|
| 58 |
+
"model_type": "qwen3_vl",
|
| 59 |
+
"num_heads": 16,
|
| 60 |
+
"num_position_embeddings": 2304,
|
| 61 |
+
"out_hidden_size": 5120,
|
| 62 |
+
"patch_size": 16,
|
| 63 |
+
"spatial_merge_size": 2,
|
| 64 |
+
"temporal_patch_size": 2
|
| 65 |
+
},
|
| 66 |
+
"vision_end_token_id": 151653,
|
| 67 |
+
"vision_start_token_id": 151652
|
| 68 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.1"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67566d10664a9afbdbde70e39308bdbcb17271d79708b7f7f35279d9186ddc90
|
| 3 |
+
size 4885539608
|
model-00002-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:464a7ff9d522ab7d68e48f1faa4450256ac59a85624a070237a2ea1d2514a05e
|
| 3 |
+
size 4875990520
|
model-00003-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cccf354f1fc48ad615cd12de229a75c97875afc013a042c1b78e3b30dddf48c2
|
| 3 |
+
size 4875990536
|
model-00004-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0f7128efe28614ec015283734ddd9d3d92e0ca7ec8f51283d34727cb28208dd
|
| 3 |
+
size 4875990576
|
model-00005-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a70da91c717cfeee75f7f04ae387e06b60d30cfe20cf7121923107bd0a4a4f28
|
| 3 |
+
size 4875990576
|
model-00006-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f893c08b95e0178de4321bed7092f4d5a4a585e7e53262edbf47f26e392306f0
|
| 3 |
+
size 4875990576
|
model-00007-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49992530248c91c3686f1ecf693ac707ff368fe3f7cee05c3f6556e86094560c
|
| 3 |
+
size 4875990576
|
model-00008-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:652687596da4dfe65bed66fb24ed0dd72feb67cbd76b5b537b25e8b259053e5d
|
| 3 |
+
size 4875990576
|
model-00009-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:486897292e655ba4f834d9a85875be72ae70cbcb0d3a1af8875f943c80222053
|
| 3 |
+
size 4875990576
|
model-00010-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a100d3a942a0d37a97cfc369922651c2ab3b040edff6c59eab7b6afda1641be
|
| 3 |
+
size 4875990576
|
model-00011-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12c2b392d3c3144d523a4a62860002471957eed625c6eb6d9a1ec71c8a52bc33
|
| 3 |
+
size 4875990576
|
model-00012-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a73f785a0b9ddaf304d88cc8e718d57a7380e0d2efa3bf5afd453615a49e05dc
|
| 3 |
+
size 4875990576
|
model-00013-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7673567a2aa9c31be7cc5ab26f6dd809f5891272de6b4559749abaf7e351fca5
|
| 3 |
+
size 4875990576
|
model-00014-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4db62bdb4f43afa4c187316c1cc4eedea77e0ae13feae86644c7d950f3114f3
|
| 3 |
+
size 3317486360
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1066 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 1143024,
|
| 4 |
+
"total_size": 66714780128
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00014-of-00014.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00014.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 12 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 13 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 19 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 20 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 23 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 24 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 30 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 31 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 34 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 35 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 41 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 42 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 45 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 46 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 52 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 53 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 55 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 56 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 57 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 63 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 64 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 66 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 67 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 68 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 74 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 75 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 77 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 78 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 79 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 85 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 86 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 88 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 89 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 90 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 95 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 96 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 97 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 99 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 100 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 101 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 106 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 107 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 108 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 110 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 111 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 112 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 117 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 118 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 119 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 121 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 122 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 123 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 128 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 129 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 130 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 133 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 134 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 139 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 140 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 141 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 143 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 144 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 145 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
| 150 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 151 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 152 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 155 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 156 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 162 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 163 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 166 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 167 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 173 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 174 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 176 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 177 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 178 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 184 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 185 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 187 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 188 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 189 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 194 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 195 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 196 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 198 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 199 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 200 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 205 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 206 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 207 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 209 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 210 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 211 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 216 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 217 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 218 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 220 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 221 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 222 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 227 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 228 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 229 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 231 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 232 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 233 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 238 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 239 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 240 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 242 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 243 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 244 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 249 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 250 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 251 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 253 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 254 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 255 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 260 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 261 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 262 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 264 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 265 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 266 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 271 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 272 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 273 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 275 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 276 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 277 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 282 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 283 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 284 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 286 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 287 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 288 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 293 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 294 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 295 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 298 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 299 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 304 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 305 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 306 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 309 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 310 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 316 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 317 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 320 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 321 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 327 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 328 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 330 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 331 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 332 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 338 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 339 |
+
"model.language_model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 340 |
+
"model.language_model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 341 |
+
"model.language_model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 342 |
+
"model.language_model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 343 |
+
"model.language_model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 344 |
+
"model.language_model.layers.36.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 345 |
+
"model.language_model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 346 |
+
"model.language_model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 347 |
+
"model.language_model.layers.36.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 348 |
+
"model.language_model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 349 |
+
"model.language_model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 350 |
+
"model.language_model.layers.37.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 351 |
+
"model.language_model.layers.37.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 352 |
+
"model.language_model.layers.37.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 353 |
+
"model.language_model.layers.37.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 354 |
+
"model.language_model.layers.37.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 355 |
+
"model.language_model.layers.37.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 356 |
+
"model.language_model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 357 |
+
"model.language_model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 358 |
+
"model.language_model.layers.37.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 359 |
+
"model.language_model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 360 |
+
"model.language_model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 361 |
+
"model.language_model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 362 |
+
"model.language_model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 363 |
+
"model.language_model.layers.38.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 364 |
+
"model.language_model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 365 |
+
"model.language_model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 366 |
+
"model.language_model.layers.38.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 367 |
+
"model.language_model.layers.38.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 368 |
+
"model.language_model.layers.38.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 369 |
+
"model.language_model.layers.38.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 370 |
+
"model.language_model.layers.38.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 371 |
+
"model.language_model.layers.38.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 372 |
+
"model.language_model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 373 |
+
"model.language_model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 374 |
+
"model.language_model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 375 |
+
"model.language_model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 376 |
+
"model.language_model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 377 |
+
"model.language_model.layers.39.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 378 |
+
"model.language_model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 379 |
+
"model.language_model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 380 |
+
"model.language_model.layers.39.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 381 |
+
"model.language_model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 382 |
+
"model.language_model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 383 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 384 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 385 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 386 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 387 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 388 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 389 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 390 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 391 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 392 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 393 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 394 |
+
"model.language_model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 395 |
+
"model.language_model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 396 |
+
"model.language_model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 397 |
+
"model.language_model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 398 |
+
"model.language_model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 399 |
+
"model.language_model.layers.40.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 400 |
+
"model.language_model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 401 |
+
"model.language_model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 402 |
+
"model.language_model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 403 |
+
"model.language_model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 404 |
+
"model.language_model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 405 |
+
"model.language_model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 406 |
+
"model.language_model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 407 |
+
"model.language_model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 408 |
+
"model.language_model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 409 |
+
"model.language_model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 410 |
+
"model.language_model.layers.41.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 411 |
+
"model.language_model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 412 |
+
"model.language_model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 413 |
+
"model.language_model.layers.41.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 414 |
+
"model.language_model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 415 |
+
"model.language_model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 416 |
+
"model.language_model.layers.42.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 417 |
+
"model.language_model.layers.42.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 418 |
+
"model.language_model.layers.42.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 419 |
+
"model.language_model.layers.42.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 420 |
+
"model.language_model.layers.42.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 421 |
+
"model.language_model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 422 |
+
"model.language_model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 423 |
+
"model.language_model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 424 |
+
"model.language_model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 425 |
+
"model.language_model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 426 |
+
"model.language_model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 427 |
+
"model.language_model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 428 |
+
"model.language_model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 429 |
+
"model.language_model.layers.43.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 430 |
+
"model.language_model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 431 |
+
"model.language_model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 432 |
+
"model.language_model.layers.43.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 433 |
+
"model.language_model.layers.43.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 434 |
+
"model.language_model.layers.43.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 435 |
+
"model.language_model.layers.43.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 436 |
+
"model.language_model.layers.43.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 437 |
+
"model.language_model.layers.43.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 438 |
+
"model.language_model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 439 |
+
"model.language_model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 440 |
+
"model.language_model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 441 |
+
"model.language_model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 442 |
+
"model.language_model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 443 |
+
"model.language_model.layers.44.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 444 |
+
"model.language_model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 445 |
+
"model.language_model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 446 |
+
"model.language_model.layers.44.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 447 |
+
"model.language_model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 448 |
+
"model.language_model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 449 |
+
"model.language_model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 450 |
+
"model.language_model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 451 |
+
"model.language_model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 452 |
+
"model.language_model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 453 |
+
"model.language_model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 454 |
+
"model.language_model.layers.45.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 455 |
+
"model.language_model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 456 |
+
"model.language_model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 457 |
+
"model.language_model.layers.45.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 458 |
+
"model.language_model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 459 |
+
"model.language_model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 460 |
+
"model.language_model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 461 |
+
"model.language_model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 462 |
+
"model.language_model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 463 |
+
"model.language_model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 464 |
+
"model.language_model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 465 |
+
"model.language_model.layers.46.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 466 |
+
"model.language_model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 467 |
+
"model.language_model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 468 |
+
"model.language_model.layers.46.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 469 |
+
"model.language_model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 470 |
+
"model.language_model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 471 |
+
"model.language_model.layers.47.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 472 |
+
"model.language_model.layers.47.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 473 |
+
"model.language_model.layers.47.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 474 |
+
"model.language_model.layers.47.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 475 |
+
"model.language_model.layers.47.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 476 |
+
"model.language_model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 477 |
+
"model.language_model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 478 |
+
"model.language_model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 479 |
+
"model.language_model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 480 |
+
"model.language_model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 481 |
+
"model.language_model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 482 |
+
"model.language_model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 483 |
+
"model.language_model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 484 |
+
"model.language_model.layers.48.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 485 |
+
"model.language_model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 486 |
+
"model.language_model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 487 |
+
"model.language_model.layers.48.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 488 |
+
"model.language_model.layers.48.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 489 |
+
"model.language_model.layers.48.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 490 |
+
"model.language_model.layers.48.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 491 |
+
"model.language_model.layers.48.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 492 |
+
"model.language_model.layers.48.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 493 |
+
"model.language_model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 494 |
+
"model.language_model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 495 |
+
"model.language_model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 496 |
+
"model.language_model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 497 |
+
"model.language_model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 498 |
+
"model.language_model.layers.49.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 499 |
+
"model.language_model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 500 |
+
"model.language_model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 501 |
+
"model.language_model.layers.49.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 502 |
+
"model.language_model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 503 |
+
"model.language_model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 504 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 505 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 506 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 507 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 508 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 509 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 510 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 511 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 512 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 513 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 514 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 515 |
+
"model.language_model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 516 |
+
"model.language_model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 517 |
+
"model.language_model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 518 |
+
"model.language_model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 519 |
+
"model.language_model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 520 |
+
"model.language_model.layers.50.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 521 |
+
"model.language_model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 522 |
+
"model.language_model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 523 |
+
"model.language_model.layers.50.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 524 |
+
"model.language_model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 525 |
+
"model.language_model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 526 |
+
"model.language_model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 527 |
+
"model.language_model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 528 |
+
"model.language_model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 529 |
+
"model.language_model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 530 |
+
"model.language_model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 531 |
+
"model.language_model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 532 |
+
"model.language_model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 533 |
+
"model.language_model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 534 |
+
"model.language_model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 535 |
+
"model.language_model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 536 |
+
"model.language_model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 537 |
+
"model.language_model.layers.52.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 538 |
+
"model.language_model.layers.52.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 539 |
+
"model.language_model.layers.52.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 540 |
+
"model.language_model.layers.52.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 541 |
+
"model.language_model.layers.52.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 542 |
+
"model.language_model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 543 |
+
"model.language_model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 544 |
+
"model.language_model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 545 |
+
"model.language_model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 546 |
+
"model.language_model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 547 |
+
"model.language_model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 548 |
+
"model.language_model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 549 |
+
"model.language_model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 550 |
+
"model.language_model.layers.53.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 551 |
+
"model.language_model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 552 |
+
"model.language_model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 553 |
+
"model.language_model.layers.53.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 554 |
+
"model.language_model.layers.53.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 555 |
+
"model.language_model.layers.53.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 556 |
+
"model.language_model.layers.53.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 557 |
+
"model.language_model.layers.53.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 558 |
+
"model.language_model.layers.53.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 559 |
+
"model.language_model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 560 |
+
"model.language_model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 561 |
+
"model.language_model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 562 |
+
"model.language_model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 563 |
+
"model.language_model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 564 |
+
"model.language_model.layers.54.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 565 |
+
"model.language_model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 566 |
+
"model.language_model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 567 |
+
"model.language_model.layers.54.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 568 |
+
"model.language_model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 569 |
+
"model.language_model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 570 |
+
"model.language_model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 571 |
+
"model.language_model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 572 |
+
"model.language_model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 573 |
+
"model.language_model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 574 |
+
"model.language_model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 575 |
+
"model.language_model.layers.55.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 576 |
+
"model.language_model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 577 |
+
"model.language_model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 578 |
+
"model.language_model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 579 |
+
"model.language_model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 580 |
+
"model.language_model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 581 |
+
"model.language_model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 582 |
+
"model.language_model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 583 |
+
"model.language_model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 584 |
+
"model.language_model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 585 |
+
"model.language_model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 586 |
+
"model.language_model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 587 |
+
"model.language_model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 588 |
+
"model.language_model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 589 |
+
"model.language_model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 590 |
+
"model.language_model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 591 |
+
"model.language_model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 592 |
+
"model.language_model.layers.57.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 593 |
+
"model.language_model.layers.57.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 594 |
+
"model.language_model.layers.57.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 595 |
+
"model.language_model.layers.57.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 596 |
+
"model.language_model.layers.57.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 597 |
+
"model.language_model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 598 |
+
"model.language_model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 599 |
+
"model.language_model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 600 |
+
"model.language_model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 601 |
+
"model.language_model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 602 |
+
"model.language_model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 603 |
+
"model.language_model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 604 |
+
"model.language_model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 605 |
+
"model.language_model.layers.58.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 606 |
+
"model.language_model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 607 |
+
"model.language_model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 608 |
+
"model.language_model.layers.58.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 609 |
+
"model.language_model.layers.58.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 610 |
+
"model.language_model.layers.58.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 611 |
+
"model.language_model.layers.58.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 612 |
+
"model.language_model.layers.58.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 613 |
+
"model.language_model.layers.58.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 614 |
+
"model.language_model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 615 |
+
"model.language_model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 616 |
+
"model.language_model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 617 |
+
"model.language_model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 618 |
+
"model.language_model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 619 |
+
"model.language_model.layers.59.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 620 |
+
"model.language_model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 621 |
+
"model.language_model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 622 |
+
"model.language_model.layers.59.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 623 |
+
"model.language_model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 624 |
+
"model.language_model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 625 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 626 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 627 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 628 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 629 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 630 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 631 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 632 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 633 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 634 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 635 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 636 |
+
"model.language_model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 637 |
+
"model.language_model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 638 |
+
"model.language_model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 639 |
+
"model.language_model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 640 |
+
"model.language_model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 641 |
+
"model.language_model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 642 |
+
"model.language_model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 643 |
+
"model.language_model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 644 |
+
"model.language_model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 645 |
+
"model.language_model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 646 |
+
"model.language_model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 647 |
+
"model.language_model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 648 |
+
"model.language_model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 649 |
+
"model.language_model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 650 |
+
"model.language_model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 651 |
+
"model.language_model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 652 |
+
"model.language_model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 653 |
+
"model.language_model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 654 |
+
"model.language_model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 655 |
+
"model.language_model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 656 |
+
"model.language_model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 657 |
+
"model.language_model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 658 |
+
"model.language_model.layers.62.input_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 659 |
+
"model.language_model.layers.62.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
| 660 |
+
"model.language_model.layers.62.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
|
| 661 |
+
"model.language_model.layers.62.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
| 662 |
+
"model.language_model.layers.62.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 663 |
+
"model.language_model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 664 |
+
"model.language_model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 665 |
+
"model.language_model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 666 |
+
"model.language_model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 667 |
+
"model.language_model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 668 |
+
"model.language_model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 669 |
+
"model.language_model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 670 |
+
"model.language_model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
| 671 |
+
"model.language_model.layers.63.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
|
| 672 |
+
"model.language_model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
| 673 |
+
"model.language_model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 674 |
+
"model.language_model.layers.63.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
|
| 675 |
+
"model.language_model.layers.63.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
|
| 676 |
+
"model.language_model.layers.63.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
|
| 677 |
+
"model.language_model.layers.63.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
|
| 678 |
+
"model.language_model.layers.63.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
|
| 679 |
+
"model.language_model.layers.63.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
|
| 680 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 681 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 682 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 683 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 684 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 685 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 686 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 687 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 688 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 689 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 690 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 691 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 692 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 693 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 694 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 695 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 696 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 697 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 698 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 699 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 700 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 701 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 702 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 703 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 704 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 705 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 706 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 707 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 708 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 709 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 710 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 711 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 712 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 713 |
+
"model.language_model.norm.weight": "model-00014-of-00014.safetensors",
|
| 714 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 715 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 716 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 717 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 718 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 719 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 720 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 721 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 722 |
+
"model.visual.blocks.0.norm1.bias": "model-00001-of-00014.safetensors",
|
| 723 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00014.safetensors",
|
| 724 |
+
"model.visual.blocks.0.norm2.bias": "model-00001-of-00014.safetensors",
|
| 725 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00014.safetensors",
|
| 726 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 727 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 728 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 729 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 730 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 731 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 732 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 733 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 734 |
+
"model.visual.blocks.1.norm1.bias": "model-00001-of-00014.safetensors",
|
| 735 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00014.safetensors",
|
| 736 |
+
"model.visual.blocks.1.norm2.bias": "model-00001-of-00014.safetensors",
|
| 737 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00014.safetensors",
|
| 738 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 739 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 740 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 741 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 742 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 743 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 744 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 745 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 746 |
+
"model.visual.blocks.10.norm1.bias": "model-00001-of-00014.safetensors",
|
| 747 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00014.safetensors",
|
| 748 |
+
"model.visual.blocks.10.norm2.bias": "model-00001-of-00014.safetensors",
|
| 749 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00014.safetensors",
|
| 750 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 751 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 752 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 753 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 754 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 755 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 756 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 757 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 758 |
+
"model.visual.blocks.11.norm1.bias": "model-00001-of-00014.safetensors",
|
| 759 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00014.safetensors",
|
| 760 |
+
"model.visual.blocks.11.norm2.bias": "model-00001-of-00014.safetensors",
|
| 761 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00014.safetensors",
|
| 762 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 763 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 764 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 765 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 766 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 767 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 768 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 769 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 770 |
+
"model.visual.blocks.12.norm1.bias": "model-00001-of-00014.safetensors",
|
| 771 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00014.safetensors",
|
| 772 |
+
"model.visual.blocks.12.norm2.bias": "model-00001-of-00014.safetensors",
|
| 773 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00014.safetensors",
|
| 774 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 775 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 776 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 777 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 778 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 779 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 780 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 781 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 782 |
+
"model.visual.blocks.13.norm1.bias": "model-00001-of-00014.safetensors",
|
| 783 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00014.safetensors",
|
| 784 |
+
"model.visual.blocks.13.norm2.bias": "model-00001-of-00014.safetensors",
|
| 785 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00014.safetensors",
|
| 786 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 787 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 788 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 789 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 790 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 791 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 792 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 793 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 794 |
+
"model.visual.blocks.14.norm1.bias": "model-00001-of-00014.safetensors",
|
| 795 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00014.safetensors",
|
| 796 |
+
"model.visual.blocks.14.norm2.bias": "model-00001-of-00014.safetensors",
|
| 797 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00014.safetensors",
|
| 798 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 799 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 800 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 801 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 802 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 803 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 804 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 805 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 806 |
+
"model.visual.blocks.15.norm1.bias": "model-00001-of-00014.safetensors",
|
| 807 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00014.safetensors",
|
| 808 |
+
"model.visual.blocks.15.norm2.bias": "model-00001-of-00014.safetensors",
|
| 809 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00014.safetensors",
|
| 810 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 811 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 812 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 813 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 814 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 815 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 816 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 817 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 818 |
+
"model.visual.blocks.16.norm1.bias": "model-00001-of-00014.safetensors",
|
| 819 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00014.safetensors",
|
| 820 |
+
"model.visual.blocks.16.norm2.bias": "model-00001-of-00014.safetensors",
|
| 821 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00014.safetensors",
|
| 822 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 823 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 824 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 825 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 826 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 827 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 828 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 829 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 830 |
+
"model.visual.blocks.17.norm1.bias": "model-00001-of-00014.safetensors",
|
| 831 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00014.safetensors",
|
| 832 |
+
"model.visual.blocks.17.norm2.bias": "model-00001-of-00014.safetensors",
|
| 833 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00014.safetensors",
|
| 834 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 835 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 836 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 837 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 838 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 839 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 840 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 841 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 842 |
+
"model.visual.blocks.18.norm1.bias": "model-00001-of-00014.safetensors",
|
| 843 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00014.safetensors",
|
| 844 |
+
"model.visual.blocks.18.norm2.bias": "model-00001-of-00014.safetensors",
|
| 845 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00014.safetensors",
|
| 846 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 847 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 848 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 849 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 850 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 851 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 852 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 853 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 854 |
+
"model.visual.blocks.19.norm1.bias": "model-00001-of-00014.safetensors",
|
| 855 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00014.safetensors",
|
| 856 |
+
"model.visual.blocks.19.norm2.bias": "model-00001-of-00014.safetensors",
|
| 857 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00014.safetensors",
|
| 858 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 859 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 860 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 861 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 862 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 863 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 864 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 865 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 866 |
+
"model.visual.blocks.2.norm1.bias": "model-00001-of-00014.safetensors",
|
| 867 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00014.safetensors",
|
| 868 |
+
"model.visual.blocks.2.norm2.bias": "model-00001-of-00014.safetensors",
|
| 869 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00014.safetensors",
|
| 870 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 871 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 872 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 873 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 874 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 875 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 876 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 877 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 878 |
+
"model.visual.blocks.20.norm1.bias": "model-00001-of-00014.safetensors",
|
| 879 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00014.safetensors",
|
| 880 |
+
"model.visual.blocks.20.norm2.bias": "model-00001-of-00014.safetensors",
|
| 881 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00014.safetensors",
|
| 882 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 883 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 884 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 885 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 886 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 887 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 888 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 889 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 890 |
+
"model.visual.blocks.21.norm1.bias": "model-00001-of-00014.safetensors",
|
| 891 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00014.safetensors",
|
| 892 |
+
"model.visual.blocks.21.norm2.bias": "model-00001-of-00014.safetensors",
|
| 893 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00014.safetensors",
|
| 894 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 895 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 896 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 897 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 898 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 899 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 900 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 901 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 902 |
+
"model.visual.blocks.22.norm1.bias": "model-00001-of-00014.safetensors",
|
| 903 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00014.safetensors",
|
| 904 |
+
"model.visual.blocks.22.norm2.bias": "model-00001-of-00014.safetensors",
|
| 905 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00014.safetensors",
|
| 906 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 907 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 908 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 909 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 910 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 911 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 912 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 913 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 914 |
+
"model.visual.blocks.23.norm1.bias": "model-00001-of-00014.safetensors",
|
| 915 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00014.safetensors",
|
| 916 |
+
"model.visual.blocks.23.norm2.bias": "model-00001-of-00014.safetensors",
|
| 917 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00014.safetensors",
|
| 918 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 919 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 920 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 921 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 922 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 923 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 924 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 925 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 926 |
+
"model.visual.blocks.24.norm1.bias": "model-00001-of-00014.safetensors",
|
| 927 |
+
"model.visual.blocks.24.norm1.weight": "model-00001-of-00014.safetensors",
|
| 928 |
+
"model.visual.blocks.24.norm2.bias": "model-00001-of-00014.safetensors",
|
| 929 |
+
"model.visual.blocks.24.norm2.weight": "model-00001-of-00014.safetensors",
|
| 930 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 931 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 932 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 933 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 934 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 935 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 936 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 937 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 938 |
+
"model.visual.blocks.25.norm1.bias": "model-00001-of-00014.safetensors",
|
| 939 |
+
"model.visual.blocks.25.norm1.weight": "model-00001-of-00014.safetensors",
|
| 940 |
+
"model.visual.blocks.25.norm2.bias": "model-00001-of-00014.safetensors",
|
| 941 |
+
"model.visual.blocks.25.norm2.weight": "model-00001-of-00014.safetensors",
|
| 942 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 943 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 944 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 945 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 946 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 947 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 948 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 949 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 950 |
+
"model.visual.blocks.26.norm1.bias": "model-00001-of-00014.safetensors",
|
| 951 |
+
"model.visual.blocks.26.norm1.weight": "model-00001-of-00014.safetensors",
|
| 952 |
+
"model.visual.blocks.26.norm2.bias": "model-00001-of-00014.safetensors",
|
| 953 |
+
"model.visual.blocks.26.norm2.weight": "model-00001-of-00014.safetensors",
|
| 954 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 955 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 956 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 957 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 958 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 959 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 960 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 961 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 962 |
+
"model.visual.blocks.3.norm1.bias": "model-00001-of-00014.safetensors",
|
| 963 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00014.safetensors",
|
| 964 |
+
"model.visual.blocks.3.norm2.bias": "model-00001-of-00014.safetensors",
|
| 965 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00014.safetensors",
|
| 966 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 967 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 968 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 969 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 970 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 971 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 972 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 973 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 974 |
+
"model.visual.blocks.4.norm1.bias": "model-00001-of-00014.safetensors",
|
| 975 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00014.safetensors",
|
| 976 |
+
"model.visual.blocks.4.norm2.bias": "model-00001-of-00014.safetensors",
|
| 977 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00014.safetensors",
|
| 978 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 979 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 980 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 981 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 982 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 983 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 984 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 985 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 986 |
+
"model.visual.blocks.5.norm1.bias": "model-00001-of-00014.safetensors",
|
| 987 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00014.safetensors",
|
| 988 |
+
"model.visual.blocks.5.norm2.bias": "model-00001-of-00014.safetensors",
|
| 989 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00014.safetensors",
|
| 990 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 991 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 992 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 993 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 994 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 995 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 996 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 997 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 998 |
+
"model.visual.blocks.6.norm1.bias": "model-00001-of-00014.safetensors",
|
| 999 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00014.safetensors",
|
| 1000 |
+
"model.visual.blocks.6.norm2.bias": "model-00001-of-00014.safetensors",
|
| 1001 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00014.safetensors",
|
| 1002 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 1003 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 1004 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 1005 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 1006 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 1007 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 1008 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 1009 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 1010 |
+
"model.visual.blocks.7.norm1.bias": "model-00001-of-00014.safetensors",
|
| 1011 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00014.safetensors",
|
| 1012 |
+
"model.visual.blocks.7.norm2.bias": "model-00001-of-00014.safetensors",
|
| 1013 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00014.safetensors",
|
| 1014 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 1015 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 1016 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 1017 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 1018 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 1019 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 1020 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 1021 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 1022 |
+
"model.visual.blocks.8.norm1.bias": "model-00001-of-00014.safetensors",
|
| 1023 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00014.safetensors",
|
| 1024 |
+
"model.visual.blocks.8.norm2.bias": "model-00001-of-00014.safetensors",
|
| 1025 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00014.safetensors",
|
| 1026 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00014.safetensors",
|
| 1027 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00014.safetensors",
|
| 1028 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00014.safetensors",
|
| 1029 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00014.safetensors",
|
| 1030 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 1031 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 1032 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 1033 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 1034 |
+
"model.visual.blocks.9.norm1.bias": "model-00001-of-00014.safetensors",
|
| 1035 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00014.safetensors",
|
| 1036 |
+
"model.visual.blocks.9.norm2.bias": "model-00001-of-00014.safetensors",
|
| 1037 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00014.safetensors",
|
| 1038 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 1039 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 1040 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 1041 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 1042 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00014.safetensors",
|
| 1043 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00014.safetensors",
|
| 1044 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 1045 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 1046 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 1047 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 1048 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00014.safetensors",
|
| 1049 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00014.safetensors",
|
| 1050 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 1051 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 1052 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 1053 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 1054 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00014.safetensors",
|
| 1055 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00014.safetensors",
|
| 1056 |
+
"model.visual.merger.linear_fc1.bias": "model-00001-of-00014.safetensors",
|
| 1057 |
+
"model.visual.merger.linear_fc1.weight": "model-00001-of-00014.safetensors",
|
| 1058 |
+
"model.visual.merger.linear_fc2.bias": "model-00001-of-00014.safetensors",
|
| 1059 |
+
"model.visual.merger.linear_fc2.weight": "model-00001-of-00014.safetensors",
|
| 1060 |
+
"model.visual.merger.norm.bias": "model-00001-of-00014.safetensors",
|
| 1061 |
+
"model.visual.merger.norm.weight": "model-00001-of-00014.safetensors",
|
| 1062 |
+
"model.visual.patch_embed.proj.bias": "model-00001-of-00014.safetensors",
|
| 1063 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00014.safetensors",
|
| 1064 |
+
"model.visual.pos_embed.weight": "model-00001-of-00014.safetensors"
|
| 1065 |
+
}
|
| 1066 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_rgb": true,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_pad": null,
|
| 11 |
+
"do_rescale": true,
|
| 12 |
+
"do_resize": true,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 19 |
+
"image_std": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"input_data_format": null,
|
| 25 |
+
"max_pixels": null,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"min_pixels": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_tensors": null,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 16777216,
|
| 36 |
+
"shortest_edge": 65536
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2
|
| 39 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"processor_class": "Qwen3VLProcessor",
|
| 238 |
+
"split_special_tokens": false,
|
| 239 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 240 |
+
"unk_token": null
|
| 241 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1877022766792704.0,
|
| 4 |
+
"train_loss": 0.2793045342631301,
|
| 5 |
+
"train_runtime": 58447.463,
|
| 6 |
+
"train_samples_per_second": 5.908,
|
| 7 |
+
"train_steps_per_second": 0.046
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,135 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 20, "total_steps": 2698, "loss": 3.3934, "lr": 7.037037037037038e-07, "epoch": 0.007414100692755034, "percentage": 0.74, "elapsed_time": "0:07:23", "remaining_time": "16:29:01"}
|
| 2 |
+
{"current_steps": 40, "total_steps": 2698, "loss": 1.2307, "lr": 1.4444444444444445e-06, "epoch": 0.014828201385510068, "percentage": 1.48, "elapsed_time": "0:14:37", "remaining_time": "16:11:28"}
|
| 3 |
+
{"current_steps": 60, "total_steps": 2698, "loss": 0.4061, "lr": 2.1851851851851853e-06, "epoch": 0.0222423020782651, "percentage": 2.22, "elapsed_time": "0:21:52", "remaining_time": "16:01:50"}
|
| 4 |
+
{"current_steps": 80, "total_steps": 2698, "loss": 0.3405, "lr": 2.9259259259259257e-06, "epoch": 0.029656402771020135, "percentage": 2.97, "elapsed_time": "0:29:06", "remaining_time": "15:52:42"}
|
| 5 |
+
{"current_steps": 100, "total_steps": 2698, "loss": 0.3194, "lr": 3.6666666666666666e-06, "epoch": 0.03707050346377517, "percentage": 3.71, "elapsed_time": "0:36:21", "remaining_time": "15:44:24"}
|
| 6 |
+
{"current_steps": 120, "total_steps": 2698, "loss": 0.3032, "lr": 4.407407407407408e-06, "epoch": 0.0444846041565302, "percentage": 4.45, "elapsed_time": "0:43:35", "remaining_time": "15:36:22"}
|
| 7 |
+
{"current_steps": 140, "total_steps": 2698, "loss": 0.309, "lr": 5.148148148148149e-06, "epoch": 0.051898704849285236, "percentage": 5.19, "elapsed_time": "0:50:48", "remaining_time": "15:28:12"}
|
| 8 |
+
{"current_steps": 160, "total_steps": 2698, "loss": 0.2961, "lr": 5.88888888888889e-06, "epoch": 0.05931280554204027, "percentage": 5.93, "elapsed_time": "0:58:00", "remaining_time": "15:20:12"}
|
| 9 |
+
{"current_steps": 180, "total_steps": 2698, "loss": 0.2912, "lr": 6.62962962962963e-06, "epoch": 0.0667269062347953, "percentage": 6.67, "elapsed_time": "1:05:14", "remaining_time": "15:12:42"}
|
| 10 |
+
{"current_steps": 200, "total_steps": 2698, "loss": 0.2912, "lr": 7.370370370370371e-06, "epoch": 0.07414100692755034, "percentage": 7.41, "elapsed_time": "1:12:28", "remaining_time": "15:05:14"}
|
| 11 |
+
{"current_steps": 220, "total_steps": 2698, "loss": 0.3035, "lr": 8.111111111111112e-06, "epoch": 0.08155510762030536, "percentage": 8.15, "elapsed_time": "1:19:42", "remaining_time": "14:57:52"}
|
| 12 |
+
{"current_steps": 240, "total_steps": 2698, "loss": 0.2862, "lr": 8.851851851851853e-06, "epoch": 0.0889692083130604, "percentage": 8.9, "elapsed_time": "1:26:56", "remaining_time": "14:50:29"}
|
| 13 |
+
{"current_steps": 260, "total_steps": 2698, "loss": 0.293, "lr": 9.592592592592593e-06, "epoch": 0.09638330900581543, "percentage": 9.64, "elapsed_time": "1:34:10", "remaining_time": "14:43:05"}
|
| 14 |
+
{"current_steps": 280, "total_steps": 2698, "loss": 0.3, "lr": 9.999660982200767e-06, "epoch": 0.10379740969857047, "percentage": 10.38, "elapsed_time": "1:41:23", "remaining_time": "14:35:37"}
|
| 15 |
+
{"current_steps": 300, "total_steps": 2698, "loss": 0.29, "lr": 9.996480447662715e-06, "epoch": 0.1112115103913255, "percentage": 11.12, "elapsed_time": "1:48:37", "remaining_time": "14:28:14"}
|
| 16 |
+
{"current_steps": 320, "total_steps": 2698, "loss": 0.2937, "lr": 9.989954095012863e-06, "epoch": 0.11862561108408054, "percentage": 11.86, "elapsed_time": "1:55:51", "remaining_time": "14:20:56"}
|
| 17 |
+
{"current_steps": 340, "total_steps": 2698, "loss": 0.2921, "lr": 9.980086294525275e-06, "epoch": 0.12603971177683557, "percentage": 12.6, "elapsed_time": "2:03:05", "remaining_time": "14:13:43"}
|
| 18 |
+
{"current_steps": 360, "total_steps": 2698, "loss": 0.285, "lr": 9.966883654024384e-06, "epoch": 0.1334538124695906, "percentage": 13.34, "elapsed_time": "2:10:20", "remaining_time": "14:06:27"}
|
| 19 |
+
{"current_steps": 380, "total_steps": 2698, "loss": 0.2803, "lr": 9.950355014460171e-06, "epoch": 0.14086791316234565, "percentage": 14.08, "elapsed_time": "2:17:33", "remaining_time": "13:59:07"}
|
| 20 |
+
{"current_steps": 400, "total_steps": 2698, "loss": 0.2774, "lr": 9.93051144398795e-06, "epoch": 0.14828201385510068, "percentage": 14.83, "elapsed_time": "2:24:48", "remaining_time": "13:51:55"}
|
| 21 |
+
{"current_steps": 420, "total_steps": 2698, "loss": 0.2796, "lr": 9.907366230556745e-06, "epoch": 0.1556961145478557, "percentage": 15.57, "elapsed_time": "2:32:02", "remaining_time": "13:44:40"}
|
| 22 |
+
{"current_steps": 440, "total_steps": 2698, "loss": 0.2797, "lr": 9.880934873011216e-06, "epoch": 0.16311021524061073, "percentage": 16.31, "elapsed_time": "2:39:16", "remaining_time": "13:37:24"}
|
| 23 |
+
{"current_steps": 460, "total_steps": 2698, "loss": 0.281, "lr": 9.851235070713086e-06, "epoch": 0.17052431593336578, "percentage": 17.05, "elapsed_time": "2:46:30", "remaining_time": "13:30:07"}
|
| 24 |
+
{"current_steps": 480, "total_steps": 2698, "loss": 0.2795, "lr": 9.818286711689036e-06, "epoch": 0.1779384166261208, "percentage": 17.79, "elapsed_time": "2:53:44", "remaining_time": "13:22:50"}
|
| 25 |
+
{"current_steps": 500, "total_steps": 2698, "loss": 0.2687, "lr": 9.78211185931298e-06, "epoch": 0.18535251731887584, "percentage": 18.53, "elapsed_time": "3:00:58", "remaining_time": "13:15:34"}
|
| 26 |
+
{"current_steps": 520, "total_steps": 2698, "loss": 0.2707, "lr": 9.742734737531662e-06, "epoch": 0.19276661801163086, "percentage": 19.27, "elapsed_time": "3:08:12", "remaining_time": "13:08:20"}
|
| 27 |
+
{"current_steps": 540, "total_steps": 2698, "loss": 0.2657, "lr": 9.700181714643453e-06, "epoch": 0.2001807187043859, "percentage": 20.01, "elapsed_time": "3:15:26", "remaining_time": "13:01:02"}
|
| 28 |
+
{"current_steps": 560, "total_steps": 2698, "loss": 0.2834, "lr": 9.654481285641214e-06, "epoch": 0.20759481939714095, "percentage": 20.76, "elapsed_time": "3:22:41", "remaining_time": "12:53:49"}
|
| 29 |
+
{"current_steps": 580, "total_steps": 2698, "loss": 0.263, "lr": 9.605664053131058e-06, "epoch": 0.21500892008989597, "percentage": 21.5, "elapsed_time": "3:29:54", "remaining_time": "12:46:29"}
|
| 30 |
+
{"current_steps": 600, "total_steps": 2698, "loss": 0.2706, "lr": 9.553762706839763e-06, "epoch": 0.222423020782651, "percentage": 22.24, "elapsed_time": "3:37:08", "remaining_time": "12:39:15"}
|
| 31 |
+
{"current_steps": 620, "total_steps": 2698, "loss": 0.2614, "lr": 9.498812001724594e-06, "epoch": 0.22983712147540603, "percentage": 22.98, "elapsed_time": "3:44:21", "remaining_time": "12:31:56"}
|
| 32 |
+
{"current_steps": 640, "total_steps": 2698, "loss": 0.2621, "lr": 9.440848734700175e-06, "epoch": 0.23725122216816108, "percentage": 23.72, "elapsed_time": "3:51:34", "remaining_time": "12:24:40"}
|
| 33 |
+
{"current_steps": 660, "total_steps": 2698, "loss": 0.2617, "lr": 9.379911719997975e-06, "epoch": 0.2446653228609161, "percentage": 24.46, "elapsed_time": "3:58:50", "remaining_time": "12:17:29"}
|
| 34 |
+
{"current_steps": 680, "total_steps": 2698, "loss": 0.2643, "lr": 9.316041763174946e-06, "epoch": 0.25207942355367113, "percentage": 25.2, "elapsed_time": "4:06:04", "remaining_time": "12:10:14"}
|
| 35 |
+
{"current_steps": 700, "total_steps": 2698, "loss": 0.2624, "lr": 9.249281633788692e-06, "epoch": 0.2594935242464262, "percentage": 25.95, "elapsed_time": "4:13:18", "remaining_time": "12:03:02"}
|
| 36 |
+
{"current_steps": 720, "total_steps": 2698, "loss": 0.2659, "lr": 9.179676036757488e-06, "epoch": 0.2669076249391812, "percentage": 26.69, "elapsed_time": "4:20:32", "remaining_time": "11:55:45"}
|
| 37 |
+
{"current_steps": 740, "total_steps": 2698, "loss": 0.2644, "lr": 9.107271582424284e-06, "epoch": 0.27432172563193624, "percentage": 27.43, "elapsed_time": "4:27:46", "remaining_time": "11:48:30"}
|
| 38 |
+
{"current_steps": 760, "total_steps": 2698, "loss": 0.2512, "lr": 9.032116755344804e-06, "epoch": 0.2817358263246913, "percentage": 28.17, "elapsed_time": "4:34:59", "remaining_time": "11:41:13"}
|
| 39 |
+
{"current_steps": 780, "total_steps": 2698, "loss": 0.2647, "lr": 8.954261881820584e-06, "epoch": 0.2891499270174463, "percentage": 28.91, "elapsed_time": "4:42:13", "remaining_time": "11:33:59"}
|
| 40 |
+
{"current_steps": 800, "total_steps": 2698, "loss": 0.2578, "lr": 8.873759096198724e-06, "epoch": 0.29656402771020135, "percentage": 29.65, "elapsed_time": "4:49:27", "remaining_time": "11:26:43"}
|
| 41 |
+
{"current_steps": 820, "total_steps": 2698, "loss": 0.2556, "lr": 8.790662305960899e-06, "epoch": 0.30397812840295635, "percentage": 30.39, "elapsed_time": "4:56:41", "remaining_time": "11:19:28"}
|
| 42 |
+
{"current_steps": 840, "total_steps": 2698, "loss": 0.2465, "lr": 8.705027155625034e-06, "epoch": 0.3113922290957114, "percentage": 31.13, "elapsed_time": "5:03:54", "remaining_time": "11:12:13"}
|
| 43 |
+
{"current_steps": 860, "total_steps": 2698, "loss": 0.2624, "lr": 8.616910989483773e-06, "epoch": 0.31880632978846646, "percentage": 31.88, "elapsed_time": "5:11:08", "remaining_time": "11:04:59"}
|
| 44 |
+
{"current_steps": 880, "total_steps": 2698, "loss": 0.2511, "lr": 8.526372813204749e-06, "epoch": 0.32622043048122146, "percentage": 32.62, "elapsed_time": "5:18:22", "remaining_time": "10:57:43"}
|
| 45 |
+
{"current_steps": 900, "total_steps": 2698, "loss": 0.2571, "lr": 8.433473254318313e-06, "epoch": 0.3336345311739765, "percentage": 33.36, "elapsed_time": "5:25:37", "remaining_time": "10:50:30"}
|
| 46 |
+
{"current_steps": 920, "total_steps": 2698, "loss": 0.2512, "lr": 8.33827452161923e-06, "epoch": 0.34104863186673157, "percentage": 34.1, "elapsed_time": "5:32:50", "remaining_time": "10:43:15"}
|
| 47 |
+
{"current_steps": 940, "total_steps": 2698, "loss": 0.2549, "lr": 8.240840363509482e-06, "epoch": 0.34846273255948657, "percentage": 34.84, "elapsed_time": "5:40:04", "remaining_time": "10:36:00"}
|
| 48 |
+
{"current_steps": 960, "total_steps": 2698, "loss": 0.2594, "lr": 8.141236025310118e-06, "epoch": 0.3558768332522416, "percentage": 35.58, "elapsed_time": "5:47:18", "remaining_time": "10:28:45"}
|
| 49 |
+
{"current_steps": 980, "total_steps": 2698, "loss": 0.2444, "lr": 8.039528205570695e-06, "epoch": 0.3632909339449966, "percentage": 36.32, "elapsed_time": "5:54:32", "remaining_time": "10:21:31"}
|
| 50 |
+
{"current_steps": 1000, "total_steps": 2698, "loss": 0.2478, "lr": 7.935785011405605e-06, "epoch": 0.3707050346377517, "percentage": 37.06, "elapsed_time": "6:01:45", "remaining_time": "10:14:15"}
|
| 51 |
+
{"current_steps": 1020, "total_steps": 2698, "loss": 0.2523, "lr": 7.83007591288716e-06, "epoch": 0.37811913533050673, "percentage": 37.81, "elapsed_time": "6:10:28", "remaining_time": "10:09:28"}
|
| 52 |
+
{"current_steps": 1040, "total_steps": 2698, "loss": 0.2589, "lr": 7.722471696526007e-06, "epoch": 0.3855332360232617, "percentage": 38.55, "elapsed_time": "6:17:43", "remaining_time": "10:02:10"}
|
| 53 |
+
{"current_steps": 1060, "total_steps": 2698, "loss": 0.2491, "lr": 7.613044417870006e-06, "epoch": 0.3929473367160168, "percentage": 39.29, "elapsed_time": "6:24:56", "remaining_time": "9:54:51"}
|
| 54 |
+
{"current_steps": 1080, "total_steps": 2698, "loss": 0.2462, "lr": 7.501867353253301e-06, "epoch": 0.4003614374087718, "percentage": 40.03, "elapsed_time": "6:32:10", "remaining_time": "9:47:31"}
|
| 55 |
+
{"current_steps": 1100, "total_steps": 2698, "loss": 0.2582, "lr": 7.389014950727938e-06, "epoch": 0.40777553810152684, "percentage": 40.77, "elapsed_time": "6:39:24", "remaining_time": "9:40:14"}
|
| 56 |
+
{"current_steps": 1120, "total_steps": 2698, "loss": 0.2399, "lr": 7.274562780210837e-06, "epoch": 0.4151896387942819, "percentage": 41.51, "elapsed_time": "6:46:38", "remaining_time": "9:32:56"}
|
| 57 |
+
{"current_steps": 1140, "total_steps": 2698, "loss": 0.2419, "lr": 7.158587482879542e-06, "epoch": 0.4226037394870369, "percentage": 42.25, "elapsed_time": "6:53:51", "remaining_time": "9:25:36"}
|
| 58 |
+
{"current_steps": 1160, "total_steps": 2698, "loss": 0.2361, "lr": 7.041166719850585e-06, "epoch": 0.43001784017979194, "percentage": 42.99, "elapsed_time": "7:01:04", "remaining_time": "9:18:17"}
|
| 59 |
+
{"current_steps": 1180, "total_steps": 2698, "loss": 0.2426, "lr": 6.922379120174911e-06, "epoch": 0.437431940872547, "percentage": 43.74, "elapsed_time": "7:08:18", "remaining_time": "9:10:59"}
|
| 60 |
+
{"current_steps": 1200, "total_steps": 2698, "loss": 0.2499, "lr": 6.802304228185097e-06, "epoch": 0.444846041565302, "percentage": 44.48, "elapsed_time": "7:15:31", "remaining_time": "9:03:41"}
|
| 61 |
+
{"current_steps": 1220, "total_steps": 2698, "loss": 0.2431, "lr": 6.6810224502296924e-06, "epoch": 0.45226014225805705, "percentage": 45.22, "elapsed_time": "7:22:45", "remaining_time": "8:56:23"}
|
| 62 |
+
{"current_steps": 1240, "total_steps": 2698, "loss": 0.2475, "lr": 6.55861500083031e-06, "epoch": 0.45967424295081205, "percentage": 45.96, "elapsed_time": "7:29:59", "remaining_time": "8:49:05"}
|
| 63 |
+
{"current_steps": 1260, "total_steps": 2698, "loss": 0.2434, "lr": 6.435163848297549e-06, "epoch": 0.4670883436435671, "percentage": 46.7, "elapsed_time": "7:37:12", "remaining_time": "8:41:47"}
|
| 64 |
+
{"current_steps": 1280, "total_steps": 2698, "loss": 0.2446, "lr": 6.310751659842136e-06, "epoch": 0.47450244433632216, "percentage": 47.44, "elapsed_time": "7:44:25", "remaining_time": "8:34:29"}
|
| 65 |
+
{"current_steps": 1300, "total_steps": 2698, "loss": 0.2402, "lr": 6.185461746218072e-06, "epoch": 0.48191654502907716, "percentage": 48.18, "elapsed_time": "7:51:38", "remaining_time": "8:27:11"}
|
| 66 |
+
{"current_steps": 1320, "total_steps": 2698, "loss": 0.24, "lr": 6.05937800593485e-06, "epoch": 0.4893306457218322, "percentage": 48.93, "elapsed_time": "7:58:52", "remaining_time": "8:19:54"}
|
| 67 |
+
{"current_steps": 1340, "total_steps": 2698, "loss": 0.2493, "lr": 5.932584869076049e-06, "epoch": 0.49674474641458727, "percentage": 49.67, "elapsed_time": "8:06:05", "remaining_time": "8:12:37"}
|
| 68 |
+
{"current_steps": 1360, "total_steps": 2698, "loss": 0.2351, "lr": 5.8051672407620295e-06, "epoch": 0.5041588471073423, "percentage": 50.41, "elapsed_time": "8:13:19", "remaining_time": "8:05:20"}
|
| 69 |
+
{"current_steps": 1380, "total_steps": 2698, "loss": 0.2434, "lr": 5.6772104442944674e-06, "epoch": 0.5115729478000973, "percentage": 51.15, "elapsed_time": "8:20:32", "remaining_time": "7:58:03"}
|
| 70 |
+
{"current_steps": 1400, "total_steps": 2698, "loss": 0.2427, "lr": 5.548800164020905e-06, "epoch": 0.5189870484928524, "percentage": 51.89, "elapsed_time": "8:27:45", "remaining_time": "7:50:45"}
|
| 71 |
+
{"current_steps": 1420, "total_steps": 2698, "loss": 0.2408, "lr": 5.420022387957501e-06, "epoch": 0.5264011491856074, "percentage": 52.63, "elapsed_time": "8:34:58", "remaining_time": "7:43:28"}
|
| 72 |
+
{"current_steps": 1440, "total_steps": 2698, "loss": 0.2353, "lr": 5.290963350208455e-06, "epoch": 0.5338152498783624, "percentage": 53.37, "elapsed_time": "8:42:11", "remaining_time": "7:36:11"}
|
| 73 |
+
{"current_steps": 1460, "total_steps": 2698, "loss": 0.237, "lr": 5.161709473220628e-06, "epoch": 0.5412293505711174, "percentage": 54.11, "elapsed_time": "8:49:25", "remaining_time": "7:28:55"}
|
| 74 |
+
{"current_steps": 1480, "total_steps": 2698, "loss": 0.2418, "lr": 5.032347309912058e-06, "epoch": 0.5486434512638725, "percentage": 54.86, "elapsed_time": "8:56:38", "remaining_time": "7:21:38"}
|
| 75 |
+
{"current_steps": 1500, "total_steps": 2698, "loss": 0.2381, "lr": 4.902963485713087e-06, "epoch": 0.5560575519566275, "percentage": 55.6, "elapsed_time": "9:03:51", "remaining_time": "7:14:21"}
|
| 76 |
+
{"current_steps": 1520, "total_steps": 2698, "loss": 0.2388, "lr": 4.773644640558944e-06, "epoch": 0.5634716526493826, "percentage": 56.34, "elapsed_time": "9:11:04", "remaining_time": "7:07:04"}
|
| 77 |
+
{"current_steps": 1540, "total_steps": 2698, "loss": 0.2388, "lr": 4.644477370872627e-06, "epoch": 0.5708857533421375, "percentage": 57.08, "elapsed_time": "9:18:16", "remaining_time": "6:59:47"}
|
| 78 |
+
{"current_steps": 1560, "total_steps": 2698, "loss": 0.2363, "lr": 4.515548171576886e-06, "epoch": 0.5782998540348926, "percentage": 57.82, "elapsed_time": "9:25:28", "remaining_time": "6:52:30"}
|
| 79 |
+
{"current_steps": 1580, "total_steps": 2698, "loss": 0.236, "lr": 4.386943378174214e-06, "epoch": 0.5857139547276476, "percentage": 58.56, "elapsed_time": "9:32:42", "remaining_time": "6:45:14"}
|
| 80 |
+
{"current_steps": 1600, "total_steps": 2698, "loss": 0.2369, "lr": 4.258749108933571e-06, "epoch": 0.5931280554204027, "percentage": 59.3, "elapsed_time": "9:39:56", "remaining_time": "6:37:58"}
|
| 81 |
+
{"current_steps": 1620, "total_steps": 2698, "loss": 0.2387, "lr": 4.131051207222571e-06, "epoch": 0.6005421561131578, "percentage": 60.04, "elapsed_time": "9:47:09", "remaining_time": "6:30:42"}
|
| 82 |
+
{"current_steps": 1640, "total_steps": 2698, "loss": 0.2479, "lr": 4.003935184023768e-06, "epoch": 0.6079562568059127, "percentage": 60.79, "elapsed_time": "9:54:22", "remaining_time": "6:23:26"}
|
| 83 |
+
{"current_steps": 1660, "total_steps": 2698, "loss": 0.235, "lr": 3.877486160673502e-06, "epoch": 0.6153703574986678, "percentage": 61.53, "elapsed_time": "10:01:34", "remaining_time": "6:16:09"}
|
| 84 |
+
{"current_steps": 1680, "total_steps": 2698, "loss": 0.2346, "lr": 3.7517888118616853e-06, "epoch": 0.6227844581914228, "percentage": 62.27, "elapsed_time": "10:08:46", "remaining_time": "6:08:53"}
|
| 85 |
+
{"current_steps": 1700, "total_steps": 2698, "loss": 0.2457, "lr": 3.626927308930658e-06, "epoch": 0.6301985588841779, "percentage": 63.01, "elapsed_time": "10:15:59", "remaining_time": "6:01:37"}
|
| 86 |
+
{"current_steps": 1720, "total_steps": 2698, "loss": 0.2308, "lr": 3.5029852635111172e-06, "epoch": 0.6376126595769329, "percentage": 63.75, "elapsed_time": "10:23:11", "remaining_time": "5:54:20"}
|
| 87 |
+
{"current_steps": 1740, "total_steps": 2698, "loss": 0.2329, "lr": 3.380045671532839e-06, "epoch": 0.6450267602696879, "percentage": 64.49, "elapsed_time": "10:30:23", "remaining_time": "5:47:04"}
|
| 88 |
+
{"current_steps": 1760, "total_steps": 2698, "loss": 0.2334, "lr": 3.2581908576477127e-06, "epoch": 0.6524408609624429, "percentage": 65.23, "elapsed_time": "10:37:35", "remaining_time": "5:39:48"}
|
| 89 |
+
{"current_steps": 1780, "total_steps": 2698, "loss": 0.2349, "lr": 3.1375024201022563e-06, "epoch": 0.659854961655198, "percentage": 65.97, "elapsed_time": "10:44:45", "remaining_time": "5:32:31"}
|
| 90 |
+
{"current_steps": 1800, "total_steps": 2698, "loss": 0.2297, "lr": 3.0180611760965877e-06, "epoch": 0.667269062347953, "percentage": 66.72, "elapsed_time": "10:51:56", "remaining_time": "5:25:14"}
|
| 91 |
+
{"current_steps": 1820, "total_steps": 2698, "loss": 0.2367, "lr": 2.8999471076663967e-06, "epoch": 0.6746831630407081, "percentage": 67.46, "elapsed_time": "10:59:08", "remaining_time": "5:17:58"}
|
| 92 |
+
{"current_steps": 1840, "total_steps": 2698, "loss": 0.231, "lr": 2.783239308124178e-06, "epoch": 0.6820972637334631, "percentage": 68.2, "elapsed_time": "11:06:19", "remaining_time": "5:10:42"}
|
| 93 |
+
{"current_steps": 1860, "total_steps": 2698, "loss": 0.2285, "lr": 2.6680159290955777e-06, "epoch": 0.6895113644262181, "percentage": 68.94, "elapsed_time": "11:13:30", "remaining_time": "5:03:26"}
|
| 94 |
+
{"current_steps": 1880, "total_steps": 2698, "loss": 0.2365, "lr": 2.5543541281863334e-06, "epoch": 0.6969254651189731, "percentage": 69.68, "elapsed_time": "11:20:38", "remaining_time": "4:56:09"}
|
| 95 |
+
{"current_steps": 1900, "total_steps": 2698, "loss": 0.2293, "lr": 2.4423300173148407e-06, "epoch": 0.7043395658117282, "percentage": 70.42, "elapsed_time": "11:27:46", "remaining_time": "4:48:51"}
|
| 96 |
+
{"current_steps": 1920, "total_steps": 2698, "loss": 0.2317, "lr": 2.332018611744952e-06, "epoch": 0.7117536665044832, "percentage": 71.16, "elapsed_time": "11:34:52", "remaining_time": "4:41:34"}
|
| 97 |
+
{"current_steps": 1940, "total_steps": 2698, "loss": 0.2212, "lr": 2.22349377985313e-06, "epoch": 0.7191677671972383, "percentage": 71.91, "elapsed_time": "11:41:58", "remaining_time": "4:34:16"}
|
| 98 |
+
{"current_steps": 1960, "total_steps": 2698, "loss": 0.2265, "lr": 2.1168281936635964e-06, "epoch": 0.7265818678899932, "percentage": 72.65, "elapsed_time": "11:49:04", "remaining_time": "4:26:59"}
|
| 99 |
+
{"current_steps": 1980, "total_steps": 2698, "loss": 0.2192, "lr": 2.012093280184607e-06, "epoch": 0.7339959685827483, "percentage": 73.39, "elapsed_time": "11:56:09", "remaining_time": "4:19:41"}
|
| 100 |
+
{"current_steps": 2000, "total_steps": 2698, "loss": 0.2311, "lr": 1.909359173578424e-06, "epoch": 0.7414100692755033, "percentage": 74.13, "elapsed_time": "12:03:15", "remaining_time": "4:12:25"}
|
| 101 |
+
{"current_steps": 2020, "total_steps": 2698, "loss": 0.223, "lr": 1.8086946681970274e-06, "epoch": 0.7488241699682584, "percentage": 74.87, "elapsed_time": "12:12:13", "remaining_time": "4:05:46"}
|
| 102 |
+
{"current_steps": 2040, "total_steps": 2698, "loss": 0.2266, "lr": 1.710167172515011e-06, "epoch": 0.7562382706610135, "percentage": 75.61, "elapsed_time": "12:19:19", "remaining_time": "3:58:28"}
|
| 103 |
+
{"current_steps": 2060, "total_steps": 2698, "loss": 0.2262, "lr": 1.6138426639905163e-06, "epoch": 0.7636523713537684, "percentage": 76.35, "elapsed_time": "12:26:25", "remaining_time": "3:51:10"}
|
| 104 |
+
{"current_steps": 2080, "total_steps": 2698, "loss": 0.2256, "lr": 1.5197856448844e-06, "epoch": 0.7710664720465235, "percentage": 77.09, "elapsed_time": "12:33:32", "remaining_time": "3:43:53"}
|
| 105 |
+
{"current_steps": 2100, "total_steps": 2698, "loss": 0.2259, "lr": 1.4280590990672827e-06, "epoch": 0.7784805727392785, "percentage": 77.84, "elapsed_time": "12:40:37", "remaining_time": "3:36:35"}
|
| 106 |
+
{"current_steps": 2120, "total_steps": 2698, "loss": 0.2286, "lr": 1.3387244498433389e-06, "epoch": 0.7858946734320336, "percentage": 78.58, "elapsed_time": "12:47:44", "remaining_time": "3:29:18"}
|
| 107 |
+
{"current_steps": 2140, "total_steps": 2698, "loss": 0.2236, "lr": 1.2518415188191008e-06, "epoch": 0.7933087741247886, "percentage": 79.32, "elapsed_time": "12:54:50", "remaining_time": "3:22:02"}
|
| 108 |
+
{"current_steps": 2160, "total_steps": 2698, "loss": 0.225, "lr": 1.1674684858448164e-06, "epoch": 0.8007228748175436, "percentage": 80.06, "elapsed_time": "13:01:55", "remaining_time": "3:14:45"}
|
| 109 |
+
{"current_steps": 2180, "total_steps": 2698, "loss": 0.2276, "lr": 1.085661850055193e-06, "epoch": 0.8081369755102986, "percentage": 80.8, "elapsed_time": "13:09:02", "remaining_time": "3:07:29"}
|
| 110 |
+
{"current_steps": 2200, "total_steps": 2698, "loss": 0.2188, "lr": 1.006476392035598e-06, "epoch": 0.8155510762030537, "percentage": 81.54, "elapsed_time": "13:16:07", "remaining_time": "3:00:12"}
|
| 111 |
+
{"current_steps": 2220, "total_steps": 2698, "loss": 0.2172, "lr": 9.299651371390589e-07, "epoch": 0.8229651768958087, "percentage": 82.28, "elapsed_time": "13:23:13", "remaining_time": "2:52:56"}
|
| 112 |
+
{"current_steps": 2240, "total_steps": 2698, "loss": 0.2243, "lr": 8.561793199786339e-07, "epoch": 0.8303792775885638, "percentage": 83.02, "elapsed_time": "13:30:20", "remaining_time": "2:45:41"}
|
| 113 |
+
{"current_steps": 2260, "total_steps": 2698, "loss": 0.2271, "lr": 7.8516835011892e-07, "epoch": 0.8377933782813188, "percentage": 83.77, "elapsed_time": "13:37:26", "remaining_time": "2:38:25"}
|
| 114 |
+
{"current_steps": 2280, "total_steps": 2698, "loss": 0.2237, "lr": 7.169797789896876e-07, "epoch": 0.8452074789740738, "percentage": 84.51, "elapsed_time": "13:44:32", "remaining_time": "2:31:09"}
|
| 115 |
+
{"current_steps": 2300, "total_steps": 2698, "loss": 0.2236, "lr": 6.516592680437717e-07, "epoch": 0.8526215796668288, "percentage": 85.25, "elapsed_time": "13:51:38", "remaining_time": "2:23:54"}
|
| 116 |
+
{"current_steps": 2320, "total_steps": 2698, "loss": 0.2216, "lr": 5.892505581805669e-07, "epoch": 0.8600356803595839, "percentage": 85.99, "elapsed_time": "13:58:44", "remaining_time": "2:16:39"}
|
| 117 |
+
{"current_steps": 2340, "total_steps": 2698, "loss": 0.2232, "lr": 5.297954404555944e-07, "epoch": 0.8674497810523389, "percentage": 86.73, "elapsed_time": "14:05:49", "remaining_time": "2:09:24"}
|
| 118 |
+
{"current_steps": 2360, "total_steps": 2698, "loss": 0.2279, "lr": 4.7333372809574616e-07, "epoch": 0.874863881745094, "percentage": 87.47, "elapsed_time": "14:12:55", "remaining_time": "2:02:09"}
|
| 119 |
+
{"current_steps": 2380, "total_steps": 2698, "loss": 0.2232, "lr": 4.199032298389549e-07, "epoch": 0.8822779824378489, "percentage": 88.21, "elapsed_time": "14:20:03", "remaining_time": "1:54:54"}
|
| 120 |
+
{"current_steps": 2400, "total_steps": 2698, "loss": 0.2217, "lr": 3.6953972461614364e-07, "epoch": 0.889692083130604, "percentage": 88.95, "elapsed_time": "14:27:09", "remaining_time": "1:47:40"}
|
| 121 |
+
{"current_steps": 2420, "total_steps": 2698, "loss": 0.2161, "lr": 3.2227693759239785e-07, "epoch": 0.897106183823359, "percentage": 89.7, "elapsed_time": "14:34:15", "remaining_time": "1:40:25"}
|
| 122 |
+
{"current_steps": 2440, "total_steps": 2698, "loss": 0.2228, "lr": 2.781465175834186e-07, "epoch": 0.9045202845161141, "percentage": 90.44, "elapsed_time": "14:41:22", "remaining_time": "1:33:11"}
|
| 123 |
+
{"current_steps": 2460, "total_steps": 2698, "loss": 0.2144, "lr": 2.3717801586236544e-07, "epoch": 0.9119343852088692, "percentage": 91.18, "elapsed_time": "14:48:27", "remaining_time": "1:25:57"}
|
| 124 |
+
{"current_steps": 2480, "total_steps": 2698, "loss": 0.2173, "lr": 1.9939886637129145e-07, "epoch": 0.9193484859016241, "percentage": 91.92, "elapsed_time": "14:55:33", "remaining_time": "1:18:43"}
|
| 125 |
+
{"current_steps": 2500, "total_steps": 2698, "loss": 0.2184, "lr": 1.648343673504166e-07, "epoch": 0.9267625865943792, "percentage": 92.66, "elapsed_time": "15:02:39", "remaining_time": "1:11:29"}
|
| 126 |
+
{"current_steps": 2520, "total_steps": 2698, "loss": 0.2193, "lr": 1.3350766439753914e-07, "epoch": 0.9341766872871342, "percentage": 93.4, "elapsed_time": "15:09:44", "remaining_time": "1:04:15"}
|
| 127 |
+
{"current_steps": 2540, "total_steps": 2698, "loss": 0.2232, "lr": 1.0543973496893401e-07, "epoch": 0.9415907879798893, "percentage": 94.14, "elapsed_time": "15:16:49", "remaining_time": "0:57:01"}
|
| 128 |
+
{"current_steps": 2560, "total_steps": 2698, "loss": 0.22, "lr": 8.064937433211518e-08, "epoch": 0.9490048886726443, "percentage": 94.89, "elapsed_time": "15:23:54", "remaining_time": "0:49:48"}
|
| 129 |
+
{"current_steps": 2580, "total_steps": 2698, "loss": 0.2249, "lr": 5.91531829798675e-08, "epoch": 0.9564189893653993, "percentage": 95.63, "elapsed_time": "15:31:00", "remaining_time": "0:42:34"}
|
| 130 |
+
{"current_steps": 2600, "total_steps": 2698, "loss": 0.2203, "lr": 4.0965555513974297e-08, "epoch": 0.9638330900581543, "percentage": 96.37, "elapsed_time": "15:38:05", "remaining_time": "0:35:21"}
|
| 131 |
+
{"current_steps": 2620, "total_steps": 2698, "loss": 0.2224, "lr": 2.6098671006087873e-08, "epoch": 0.9712471907509094, "percentage": 97.11, "elapsed_time": "15:45:11", "remaining_time": "0:28:08"}
|
| 132 |
+
{"current_steps": 2640, "total_steps": 2698, "loss": 0.2204, "lr": 1.4562484842199354e-08, "epoch": 0.9786612914436644, "percentage": 97.85, "elapsed_time": "15:52:16", "remaining_time": "0:20:55"}
|
| 133 |
+
{"current_steps": 2660, "total_steps": 2698, "loss": 0.222, "lr": 6.3647220561624535e-09, "epoch": 0.9860753921364195, "percentage": 98.59, "elapsed_time": "15:59:22", "remaining_time": "0:13:42"}
|
| 134 |
+
{"current_steps": 2680, "total_steps": 2698, "loss": 0.2176, "lr": 1.5108721567419493e-09, "epoch": 0.9934894928291745, "percentage": 99.33, "elapsed_time": "16:06:27", "remaining_time": "0:06:29"}
|
| 135 |
+
{"current_steps": 2698, "total_steps": 2698, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "16:14:07", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,981 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2698,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007414100692755034,
|
| 14 |
+
"grad_norm": 32.06580537112801,
|
| 15 |
+
"learning_rate": 7.037037037037038e-07,
|
| 16 |
+
"loss": 3.3934,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.014828201385510068,
|
| 21 |
+
"grad_norm": 3.3326163294817954,
|
| 22 |
+
"learning_rate": 1.4444444444444445e-06,
|
| 23 |
+
"loss": 1.2307,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0222423020782651,
|
| 28 |
+
"grad_norm": 4.290780419763869,
|
| 29 |
+
"learning_rate": 2.1851851851851853e-06,
|
| 30 |
+
"loss": 0.4061,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.029656402771020135,
|
| 35 |
+
"grad_norm": 2.6943584691235576,
|
| 36 |
+
"learning_rate": 2.9259259259259257e-06,
|
| 37 |
+
"loss": 0.3405,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03707050346377517,
|
| 42 |
+
"grad_norm": 2.266412502759934,
|
| 43 |
+
"learning_rate": 3.6666666666666666e-06,
|
| 44 |
+
"loss": 0.3194,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0444846041565302,
|
| 49 |
+
"grad_norm": 2.0806674330352632,
|
| 50 |
+
"learning_rate": 4.407407407407408e-06,
|
| 51 |
+
"loss": 0.3032,
|
| 52 |
+
"step": 120
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.051898704849285236,
|
| 56 |
+
"grad_norm": 1.8472539326338435,
|
| 57 |
+
"learning_rate": 5.148148148148149e-06,
|
| 58 |
+
"loss": 0.309,
|
| 59 |
+
"step": 140
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.05931280554204027,
|
| 63 |
+
"grad_norm": 1.7376245233341043,
|
| 64 |
+
"learning_rate": 5.88888888888889e-06,
|
| 65 |
+
"loss": 0.2961,
|
| 66 |
+
"step": 160
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0667269062347953,
|
| 70 |
+
"grad_norm": 1.516283408516978,
|
| 71 |
+
"learning_rate": 6.62962962962963e-06,
|
| 72 |
+
"loss": 0.2912,
|
| 73 |
+
"step": 180
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.07414100692755034,
|
| 77 |
+
"grad_norm": 1.2314417372784106,
|
| 78 |
+
"learning_rate": 7.370370370370371e-06,
|
| 79 |
+
"loss": 0.2912,
|
| 80 |
+
"step": 200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.08155510762030536,
|
| 84 |
+
"grad_norm": 1.4472634085041824,
|
| 85 |
+
"learning_rate": 8.111111111111112e-06,
|
| 86 |
+
"loss": 0.3035,
|
| 87 |
+
"step": 220
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0889692083130604,
|
| 91 |
+
"grad_norm": 1.2659145795134694,
|
| 92 |
+
"learning_rate": 8.851851851851853e-06,
|
| 93 |
+
"loss": 0.2862,
|
| 94 |
+
"step": 240
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.09638330900581543,
|
| 98 |
+
"grad_norm": 1.2890767825393588,
|
| 99 |
+
"learning_rate": 9.592592592592593e-06,
|
| 100 |
+
"loss": 0.293,
|
| 101 |
+
"step": 260
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.10379740969857047,
|
| 105 |
+
"grad_norm": 3.448944854479974,
|
| 106 |
+
"learning_rate": 9.999660982200767e-06,
|
| 107 |
+
"loss": 0.3,
|
| 108 |
+
"step": 280
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.1112115103913255,
|
| 112 |
+
"grad_norm": 1.2378181628212996,
|
| 113 |
+
"learning_rate": 9.996480447662715e-06,
|
| 114 |
+
"loss": 0.29,
|
| 115 |
+
"step": 300
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.11862561108408054,
|
| 119 |
+
"grad_norm": 1.3427597598729493,
|
| 120 |
+
"learning_rate": 9.989954095012863e-06,
|
| 121 |
+
"loss": 0.2937,
|
| 122 |
+
"step": 320
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.12603971177683557,
|
| 126 |
+
"grad_norm": 0.975575976420179,
|
| 127 |
+
"learning_rate": 9.980086294525275e-06,
|
| 128 |
+
"loss": 0.2921,
|
| 129 |
+
"step": 340
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1334538124695906,
|
| 133 |
+
"grad_norm": 0.9658470351220226,
|
| 134 |
+
"learning_rate": 9.966883654024384e-06,
|
| 135 |
+
"loss": 0.285,
|
| 136 |
+
"step": 360
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.14086791316234565,
|
| 140 |
+
"grad_norm": 0.907938463759864,
|
| 141 |
+
"learning_rate": 9.950355014460171e-06,
|
| 142 |
+
"loss": 0.2803,
|
| 143 |
+
"step": 380
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.14828201385510068,
|
| 147 |
+
"grad_norm": 1.0837571176440133,
|
| 148 |
+
"learning_rate": 9.93051144398795e-06,
|
| 149 |
+
"loss": 0.2774,
|
| 150 |
+
"step": 400
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.1556961145478557,
|
| 154 |
+
"grad_norm": 1.0159088629816762,
|
| 155 |
+
"learning_rate": 9.907366230556745e-06,
|
| 156 |
+
"loss": 0.2796,
|
| 157 |
+
"step": 420
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.16311021524061073,
|
| 161 |
+
"grad_norm": 0.8347916457344657,
|
| 162 |
+
"learning_rate": 9.880934873011216e-06,
|
| 163 |
+
"loss": 0.2797,
|
| 164 |
+
"step": 440
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.17052431593336578,
|
| 168 |
+
"grad_norm": 1.1330585238504898,
|
| 169 |
+
"learning_rate": 9.851235070713086e-06,
|
| 170 |
+
"loss": 0.281,
|
| 171 |
+
"step": 460
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.1779384166261208,
|
| 175 |
+
"grad_norm": 0.9622555723755646,
|
| 176 |
+
"learning_rate": 9.818286711689036e-06,
|
| 177 |
+
"loss": 0.2795,
|
| 178 |
+
"step": 480
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.18535251731887584,
|
| 182 |
+
"grad_norm": 0.99111564845969,
|
| 183 |
+
"learning_rate": 9.78211185931298e-06,
|
| 184 |
+
"loss": 0.2687,
|
| 185 |
+
"step": 500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.19276661801163086,
|
| 189 |
+
"grad_norm": 0.9679547178989175,
|
| 190 |
+
"learning_rate": 9.742734737531662e-06,
|
| 191 |
+
"loss": 0.2707,
|
| 192 |
+
"step": 520
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.2001807187043859,
|
| 196 |
+
"grad_norm": 1.4672952066714184,
|
| 197 |
+
"learning_rate": 9.700181714643453e-06,
|
| 198 |
+
"loss": 0.2657,
|
| 199 |
+
"step": 540
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.20759481939714095,
|
| 203 |
+
"grad_norm": 0.9454408078270417,
|
| 204 |
+
"learning_rate": 9.654481285641214e-06,
|
| 205 |
+
"loss": 0.2834,
|
| 206 |
+
"step": 560
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.21500892008989597,
|
| 210 |
+
"grad_norm": 2.185790922947196,
|
| 211 |
+
"learning_rate": 9.605664053131058e-06,
|
| 212 |
+
"loss": 0.263,
|
| 213 |
+
"step": 580
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.222423020782651,
|
| 217 |
+
"grad_norm": 0.8118181314852884,
|
| 218 |
+
"learning_rate": 9.553762706839763e-06,
|
| 219 |
+
"loss": 0.2706,
|
| 220 |
+
"step": 600
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.22983712147540603,
|
| 224 |
+
"grad_norm": 0.9392583618462029,
|
| 225 |
+
"learning_rate": 9.498812001724594e-06,
|
| 226 |
+
"loss": 0.2614,
|
| 227 |
+
"step": 620
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.23725122216816108,
|
| 231 |
+
"grad_norm": 0.6948312735577339,
|
| 232 |
+
"learning_rate": 9.440848734700175e-06,
|
| 233 |
+
"loss": 0.2621,
|
| 234 |
+
"step": 640
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2446653228609161,
|
| 238 |
+
"grad_norm": 0.8256442560540643,
|
| 239 |
+
"learning_rate": 9.379911719997975e-06,
|
| 240 |
+
"loss": 0.2617,
|
| 241 |
+
"step": 660
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.25207942355367113,
|
| 245 |
+
"grad_norm": 0.7805987945354576,
|
| 246 |
+
"learning_rate": 9.316041763174946e-06,
|
| 247 |
+
"loss": 0.2643,
|
| 248 |
+
"step": 680
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.2594935242464262,
|
| 252 |
+
"grad_norm": 0.8124960825173237,
|
| 253 |
+
"learning_rate": 9.249281633788692e-06,
|
| 254 |
+
"loss": 0.2624,
|
| 255 |
+
"step": 700
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.2669076249391812,
|
| 259 |
+
"grad_norm": 0.7823012396587974,
|
| 260 |
+
"learning_rate": 9.179676036757488e-06,
|
| 261 |
+
"loss": 0.2659,
|
| 262 |
+
"step": 720
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.27432172563193624,
|
| 266 |
+
"grad_norm": 0.7555442715531621,
|
| 267 |
+
"learning_rate": 9.107271582424284e-06,
|
| 268 |
+
"loss": 0.2644,
|
| 269 |
+
"step": 740
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.2817358263246913,
|
| 273 |
+
"grad_norm": 1.1171738106079774,
|
| 274 |
+
"learning_rate": 9.032116755344804e-06,
|
| 275 |
+
"loss": 0.2512,
|
| 276 |
+
"step": 760
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.2891499270174463,
|
| 280 |
+
"grad_norm": 0.7798366005214705,
|
| 281 |
+
"learning_rate": 8.954261881820584e-06,
|
| 282 |
+
"loss": 0.2647,
|
| 283 |
+
"step": 780
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.29656402771020135,
|
| 287 |
+
"grad_norm": 0.8245286080721071,
|
| 288 |
+
"learning_rate": 8.873759096198724e-06,
|
| 289 |
+
"loss": 0.2578,
|
| 290 |
+
"step": 800
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.30397812840295635,
|
| 294 |
+
"grad_norm": 0.648298467437291,
|
| 295 |
+
"learning_rate": 8.790662305960899e-06,
|
| 296 |
+
"loss": 0.2556,
|
| 297 |
+
"step": 820
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.3113922290957114,
|
| 301 |
+
"grad_norm": 0.7821424784357656,
|
| 302 |
+
"learning_rate": 8.705027155625034e-06,
|
| 303 |
+
"loss": 0.2465,
|
| 304 |
+
"step": 840
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.31880632978846646,
|
| 308 |
+
"grad_norm": 0.7859052019683617,
|
| 309 |
+
"learning_rate": 8.616910989483773e-06,
|
| 310 |
+
"loss": 0.2624,
|
| 311 |
+
"step": 860
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.32622043048122146,
|
| 315 |
+
"grad_norm": 0.75339069893752,
|
| 316 |
+
"learning_rate": 8.526372813204749e-06,
|
| 317 |
+
"loss": 0.2511,
|
| 318 |
+
"step": 880
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3336345311739765,
|
| 322 |
+
"grad_norm": 1.4580418599743148,
|
| 323 |
+
"learning_rate": 8.433473254318313e-06,
|
| 324 |
+
"loss": 0.2571,
|
| 325 |
+
"step": 900
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.34104863186673157,
|
| 329 |
+
"grad_norm": 0.8481013751282837,
|
| 330 |
+
"learning_rate": 8.33827452161923e-06,
|
| 331 |
+
"loss": 0.2512,
|
| 332 |
+
"step": 920
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.34846273255948657,
|
| 336 |
+
"grad_norm": 0.8089440081418998,
|
| 337 |
+
"learning_rate": 8.240840363509482e-06,
|
| 338 |
+
"loss": 0.2549,
|
| 339 |
+
"step": 940
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3558768332522416,
|
| 343 |
+
"grad_norm": 0.7352455790133732,
|
| 344 |
+
"learning_rate": 8.141236025310118e-06,
|
| 345 |
+
"loss": 0.2594,
|
| 346 |
+
"step": 960
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3632909339449966,
|
| 350 |
+
"grad_norm": 1.0831597837201794,
|
| 351 |
+
"learning_rate": 8.039528205570695e-06,
|
| 352 |
+
"loss": 0.2444,
|
| 353 |
+
"step": 980
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.3707050346377517,
|
| 357 |
+
"grad_norm": 0.7585612413284839,
|
| 358 |
+
"learning_rate": 7.935785011405605e-06,
|
| 359 |
+
"loss": 0.2478,
|
| 360 |
+
"step": 1000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.37811913533050673,
|
| 364 |
+
"grad_norm": 0.727649147663723,
|
| 365 |
+
"learning_rate": 7.83007591288716e-06,
|
| 366 |
+
"loss": 0.2523,
|
| 367 |
+
"step": 1020
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3855332360232617,
|
| 371 |
+
"grad_norm": 0.7787866088201918,
|
| 372 |
+
"learning_rate": 7.722471696526007e-06,
|
| 373 |
+
"loss": 0.2589,
|
| 374 |
+
"step": 1040
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3929473367160168,
|
| 378 |
+
"grad_norm": 0.7765136850082168,
|
| 379 |
+
"learning_rate": 7.613044417870006e-06,
|
| 380 |
+
"loss": 0.2491,
|
| 381 |
+
"step": 1060
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.4003614374087718,
|
| 385 |
+
"grad_norm": 0.690468569324881,
|
| 386 |
+
"learning_rate": 7.501867353253301e-06,
|
| 387 |
+
"loss": 0.2462,
|
| 388 |
+
"step": 1080
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.40777553810152684,
|
| 392 |
+
"grad_norm": 0.7182183611659085,
|
| 393 |
+
"learning_rate": 7.389014950727938e-06,
|
| 394 |
+
"loss": 0.2582,
|
| 395 |
+
"step": 1100
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.4151896387942819,
|
| 399 |
+
"grad_norm": 0.6634951338167964,
|
| 400 |
+
"learning_rate": 7.274562780210837e-06,
|
| 401 |
+
"loss": 0.2399,
|
| 402 |
+
"step": 1120
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.4226037394870369,
|
| 406 |
+
"grad_norm": 0.7930541091163981,
|
| 407 |
+
"learning_rate": 7.158587482879542e-06,
|
| 408 |
+
"loss": 0.2419,
|
| 409 |
+
"step": 1140
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.43001784017979194,
|
| 413 |
+
"grad_norm": 0.7591718992979861,
|
| 414 |
+
"learning_rate": 7.041166719850585e-06,
|
| 415 |
+
"loss": 0.2361,
|
| 416 |
+
"step": 1160
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.437431940872547,
|
| 420 |
+
"grad_norm": 0.657480629189675,
|
| 421 |
+
"learning_rate": 6.922379120174911e-06,
|
| 422 |
+
"loss": 0.2426,
|
| 423 |
+
"step": 1180
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.444846041565302,
|
| 427 |
+
"grad_norm": 0.856188180561323,
|
| 428 |
+
"learning_rate": 6.802304228185097e-06,
|
| 429 |
+
"loss": 0.2499,
|
| 430 |
+
"step": 1200
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.45226014225805705,
|
| 434 |
+
"grad_norm": 0.7103672994416902,
|
| 435 |
+
"learning_rate": 6.6810224502296924e-06,
|
| 436 |
+
"loss": 0.2431,
|
| 437 |
+
"step": 1220
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.45967424295081205,
|
| 441 |
+
"grad_norm": 0.7655598824506112,
|
| 442 |
+
"learning_rate": 6.55861500083031e-06,
|
| 443 |
+
"loss": 0.2475,
|
| 444 |
+
"step": 1240
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.4670883436435671,
|
| 448 |
+
"grad_norm": 0.7285887684926099,
|
| 449 |
+
"learning_rate": 6.435163848297549e-06,
|
| 450 |
+
"loss": 0.2434,
|
| 451 |
+
"step": 1260
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.47450244433632216,
|
| 455 |
+
"grad_norm": 0.7404441533804746,
|
| 456 |
+
"learning_rate": 6.310751659842136e-06,
|
| 457 |
+
"loss": 0.2446,
|
| 458 |
+
"step": 1280
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.48191654502907716,
|
| 462 |
+
"grad_norm": 0.7192394640726304,
|
| 463 |
+
"learning_rate": 6.185461746218072e-06,
|
| 464 |
+
"loss": 0.2402,
|
| 465 |
+
"step": 1300
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.4893306457218322,
|
| 469 |
+
"grad_norm": 0.6374798064639219,
|
| 470 |
+
"learning_rate": 6.05937800593485e-06,
|
| 471 |
+
"loss": 0.24,
|
| 472 |
+
"step": 1320
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.49674474641458727,
|
| 476 |
+
"grad_norm": 0.7031390506652865,
|
| 477 |
+
"learning_rate": 5.932584869076049e-06,
|
| 478 |
+
"loss": 0.2493,
|
| 479 |
+
"step": 1340
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.5041588471073423,
|
| 483 |
+
"grad_norm": 0.7586530636558019,
|
| 484 |
+
"learning_rate": 5.8051672407620295e-06,
|
| 485 |
+
"loss": 0.2351,
|
| 486 |
+
"step": 1360
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.5115729478000973,
|
| 490 |
+
"grad_norm": 0.7281460672456646,
|
| 491 |
+
"learning_rate": 5.6772104442944674e-06,
|
| 492 |
+
"loss": 0.2434,
|
| 493 |
+
"step": 1380
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.5189870484928524,
|
| 497 |
+
"grad_norm": 0.7585358565709085,
|
| 498 |
+
"learning_rate": 5.548800164020905e-06,
|
| 499 |
+
"loss": 0.2427,
|
| 500 |
+
"step": 1400
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.5264011491856074,
|
| 504 |
+
"grad_norm": 0.6534120478200554,
|
| 505 |
+
"learning_rate": 5.420022387957501e-06,
|
| 506 |
+
"loss": 0.2408,
|
| 507 |
+
"step": 1420
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.5338152498783624,
|
| 511 |
+
"grad_norm": 1.0252998400955873,
|
| 512 |
+
"learning_rate": 5.290963350208455e-06,
|
| 513 |
+
"loss": 0.2353,
|
| 514 |
+
"step": 1440
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.5412293505711174,
|
| 518 |
+
"grad_norm": 0.7331074205501853,
|
| 519 |
+
"learning_rate": 5.161709473220628e-06,
|
| 520 |
+
"loss": 0.237,
|
| 521 |
+
"step": 1460
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.5486434512638725,
|
| 525 |
+
"grad_norm": 0.6449563139414835,
|
| 526 |
+
"learning_rate": 5.032347309912058e-06,
|
| 527 |
+
"loss": 0.2418,
|
| 528 |
+
"step": 1480
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.5560575519566275,
|
| 532 |
+
"grad_norm": 0.6315702237924259,
|
| 533 |
+
"learning_rate": 4.902963485713087e-06,
|
| 534 |
+
"loss": 0.2381,
|
| 535 |
+
"step": 1500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.5634716526493826,
|
| 539 |
+
"grad_norm": 0.6051123125654648,
|
| 540 |
+
"learning_rate": 4.773644640558944e-06,
|
| 541 |
+
"loss": 0.2388,
|
| 542 |
+
"step": 1520
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.5708857533421375,
|
| 546 |
+
"grad_norm": 0.6580102590702694,
|
| 547 |
+
"learning_rate": 4.644477370872627e-06,
|
| 548 |
+
"loss": 0.2388,
|
| 549 |
+
"step": 1540
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.5782998540348926,
|
| 553 |
+
"grad_norm": 0.7237643321863204,
|
| 554 |
+
"learning_rate": 4.515548171576886e-06,
|
| 555 |
+
"loss": 0.2363,
|
| 556 |
+
"step": 1560
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.5857139547276476,
|
| 560 |
+
"grad_norm": 0.6923389676943642,
|
| 561 |
+
"learning_rate": 4.386943378174214e-06,
|
| 562 |
+
"loss": 0.236,
|
| 563 |
+
"step": 1580
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.5931280554204027,
|
| 567 |
+
"grad_norm": 0.6934233196397561,
|
| 568 |
+
"learning_rate": 4.258749108933571e-06,
|
| 569 |
+
"loss": 0.2369,
|
| 570 |
+
"step": 1600
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.6005421561131578,
|
| 574 |
+
"grad_norm": 0.6182921314601578,
|
| 575 |
+
"learning_rate": 4.131051207222571e-06,
|
| 576 |
+
"loss": 0.2387,
|
| 577 |
+
"step": 1620
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.6079562568059127,
|
| 581 |
+
"grad_norm": 0.7468100667443839,
|
| 582 |
+
"learning_rate": 4.003935184023768e-06,
|
| 583 |
+
"loss": 0.2479,
|
| 584 |
+
"step": 1640
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.6153703574986678,
|
| 588 |
+
"grad_norm": 0.623631126507463,
|
| 589 |
+
"learning_rate": 3.877486160673502e-06,
|
| 590 |
+
"loss": 0.235,
|
| 591 |
+
"step": 1660
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.6227844581914228,
|
| 595 |
+
"grad_norm": 0.7107052234543987,
|
| 596 |
+
"learning_rate": 3.7517888118616853e-06,
|
| 597 |
+
"loss": 0.2346,
|
| 598 |
+
"step": 1680
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.6301985588841779,
|
| 602 |
+
"grad_norm": 0.8029055529060507,
|
| 603 |
+
"learning_rate": 3.626927308930658e-06,
|
| 604 |
+
"loss": 0.2457,
|
| 605 |
+
"step": 1700
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.6376126595769329,
|
| 609 |
+
"grad_norm": 0.6874508607391684,
|
| 610 |
+
"learning_rate": 3.5029852635111172e-06,
|
| 611 |
+
"loss": 0.2308,
|
| 612 |
+
"step": 1720
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.6450267602696879,
|
| 616 |
+
"grad_norm": 0.6908040428007661,
|
| 617 |
+
"learning_rate": 3.380045671532839e-06,
|
| 618 |
+
"loss": 0.2329,
|
| 619 |
+
"step": 1740
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.6524408609624429,
|
| 623 |
+
"grad_norm": 0.5547457031999729,
|
| 624 |
+
"learning_rate": 3.2581908576477127e-06,
|
| 625 |
+
"loss": 0.2334,
|
| 626 |
+
"step": 1760
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.659854961655198,
|
| 630 |
+
"grad_norm": 0.6349433771354605,
|
| 631 |
+
"learning_rate": 3.1375024201022563e-06,
|
| 632 |
+
"loss": 0.2349,
|
| 633 |
+
"step": 1780
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.667269062347953,
|
| 637 |
+
"grad_norm": 0.6010959441423943,
|
| 638 |
+
"learning_rate": 3.0180611760965877e-06,
|
| 639 |
+
"loss": 0.2297,
|
| 640 |
+
"step": 1800
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.6746831630407081,
|
| 644 |
+
"grad_norm": 0.699521154565116,
|
| 645 |
+
"learning_rate": 2.8999471076663967e-06,
|
| 646 |
+
"loss": 0.2367,
|
| 647 |
+
"step": 1820
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.6820972637334631,
|
| 651 |
+
"grad_norm": 0.6187654276233007,
|
| 652 |
+
"learning_rate": 2.783239308124178e-06,
|
| 653 |
+
"loss": 0.231,
|
| 654 |
+
"step": 1840
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.6895113644262181,
|
| 658 |
+
"grad_norm": 0.6044970045544199,
|
| 659 |
+
"learning_rate": 2.6680159290955777e-06,
|
| 660 |
+
"loss": 0.2285,
|
| 661 |
+
"step": 1860
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.6969254651189731,
|
| 665 |
+
"grad_norm": 0.7284350015662899,
|
| 666 |
+
"learning_rate": 2.5543541281863334e-06,
|
| 667 |
+
"loss": 0.2365,
|
| 668 |
+
"step": 1880
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.7043395658117282,
|
| 672 |
+
"grad_norm": 0.7220795849243428,
|
| 673 |
+
"learning_rate": 2.4423300173148407e-06,
|
| 674 |
+
"loss": 0.2293,
|
| 675 |
+
"step": 1900
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.7117536665044832,
|
| 679 |
+
"grad_norm": 0.6987651618762949,
|
| 680 |
+
"learning_rate": 2.332018611744952e-06,
|
| 681 |
+
"loss": 0.2317,
|
| 682 |
+
"step": 1920
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.7191677671972383,
|
| 686 |
+
"grad_norm": 0.6900248322430578,
|
| 687 |
+
"learning_rate": 2.22349377985313e-06,
|
| 688 |
+
"loss": 0.2212,
|
| 689 |
+
"step": 1940
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.7265818678899932,
|
| 693 |
+
"grad_norm": 0.6517311748768397,
|
| 694 |
+
"learning_rate": 2.1168281936635964e-06,
|
| 695 |
+
"loss": 0.2265,
|
| 696 |
+
"step": 1960
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.7339959685827483,
|
| 700 |
+
"grad_norm": 0.6933857965660299,
|
| 701 |
+
"learning_rate": 2.012093280184607e-06,
|
| 702 |
+
"loss": 0.2192,
|
| 703 |
+
"step": 1980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.7414100692755033,
|
| 707 |
+
"grad_norm": 0.6690150882563629,
|
| 708 |
+
"learning_rate": 1.909359173578424e-06,
|
| 709 |
+
"loss": 0.2311,
|
| 710 |
+
"step": 2000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.7488241699682584,
|
| 714 |
+
"grad_norm": 0.6880821782327176,
|
| 715 |
+
"learning_rate": 1.8086946681970274e-06,
|
| 716 |
+
"loss": 0.223,
|
| 717 |
+
"step": 2020
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.7562382706610135,
|
| 721 |
+
"grad_norm": 0.7671933520011451,
|
| 722 |
+
"learning_rate": 1.710167172515011e-06,
|
| 723 |
+
"loss": 0.2266,
|
| 724 |
+
"step": 2040
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.7636523713537684,
|
| 728 |
+
"grad_norm": 0.7073742558100695,
|
| 729 |
+
"learning_rate": 1.6138426639905163e-06,
|
| 730 |
+
"loss": 0.2262,
|
| 731 |
+
"step": 2060
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.7710664720465235,
|
| 735 |
+
"grad_norm": 0.6602266104494168,
|
| 736 |
+
"learning_rate": 1.5197856448844e-06,
|
| 737 |
+
"loss": 0.2256,
|
| 738 |
+
"step": 2080
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.7784805727392785,
|
| 742 |
+
"grad_norm": 0.6504469232479442,
|
| 743 |
+
"learning_rate": 1.4280590990672827e-06,
|
| 744 |
+
"loss": 0.2259,
|
| 745 |
+
"step": 2100
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.7858946734320336,
|
| 749 |
+
"grad_norm": 0.6423895377225716,
|
| 750 |
+
"learning_rate": 1.3387244498433389e-06,
|
| 751 |
+
"loss": 0.2286,
|
| 752 |
+
"step": 2120
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.7933087741247886,
|
| 756 |
+
"grad_norm": 0.6849903734668334,
|
| 757 |
+
"learning_rate": 1.2518415188191008e-06,
|
| 758 |
+
"loss": 0.2236,
|
| 759 |
+
"step": 2140
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.8007228748175436,
|
| 763 |
+
"grad_norm": 0.6536439344710893,
|
| 764 |
+
"learning_rate": 1.1674684858448164e-06,
|
| 765 |
+
"loss": 0.225,
|
| 766 |
+
"step": 2160
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.8081369755102986,
|
| 770 |
+
"grad_norm": 0.8214938667433946,
|
| 771 |
+
"learning_rate": 1.085661850055193e-06,
|
| 772 |
+
"loss": 0.2276,
|
| 773 |
+
"step": 2180
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.8155510762030537,
|
| 777 |
+
"grad_norm": 0.7409010792932056,
|
| 778 |
+
"learning_rate": 1.006476392035598e-06,
|
| 779 |
+
"loss": 0.2188,
|
| 780 |
+
"step": 2200
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.8229651768958087,
|
| 784 |
+
"grad_norm": 0.6696568442942546,
|
| 785 |
+
"learning_rate": 9.299651371390589e-07,
|
| 786 |
+
"loss": 0.2172,
|
| 787 |
+
"step": 2220
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.8303792775885638,
|
| 791 |
+
"grad_norm": 0.6913664887131121,
|
| 792 |
+
"learning_rate": 8.561793199786339e-07,
|
| 793 |
+
"loss": 0.2243,
|
| 794 |
+
"step": 2240
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.8377933782813188,
|
| 798 |
+
"grad_norm": 0.6651230207577203,
|
| 799 |
+
"learning_rate": 7.8516835011892e-07,
|
| 800 |
+
"loss": 0.2271,
|
| 801 |
+
"step": 2260
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.8452074789740738,
|
| 805 |
+
"grad_norm": 0.6718428566405614,
|
| 806 |
+
"learning_rate": 7.169797789896876e-07,
|
| 807 |
+
"loss": 0.2237,
|
| 808 |
+
"step": 2280
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.8526215796668288,
|
| 812 |
+
"grad_norm": 0.7501096157117769,
|
| 813 |
+
"learning_rate": 6.516592680437717e-07,
|
| 814 |
+
"loss": 0.2236,
|
| 815 |
+
"step": 2300
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.8600356803595839,
|
| 819 |
+
"grad_norm": 0.625025697061966,
|
| 820 |
+
"learning_rate": 5.892505581805669e-07,
|
| 821 |
+
"loss": 0.2216,
|
| 822 |
+
"step": 2320
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.8674497810523389,
|
| 826 |
+
"grad_norm": 0.6238881264357159,
|
| 827 |
+
"learning_rate": 5.297954404555944e-07,
|
| 828 |
+
"loss": 0.2232,
|
| 829 |
+
"step": 2340
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.874863881745094,
|
| 833 |
+
"grad_norm": 0.5852724716452957,
|
| 834 |
+
"learning_rate": 4.7333372809574616e-07,
|
| 835 |
+
"loss": 0.2279,
|
| 836 |
+
"step": 2360
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.8822779824378489,
|
| 840 |
+
"grad_norm": 0.6481022641381101,
|
| 841 |
+
"learning_rate": 4.199032298389549e-07,
|
| 842 |
+
"loss": 0.2232,
|
| 843 |
+
"step": 2380
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.889692083130604,
|
| 847 |
+
"grad_norm": 0.7060913539739083,
|
| 848 |
+
"learning_rate": 3.6953972461614364e-07,
|
| 849 |
+
"loss": 0.2217,
|
| 850 |
+
"step": 2400
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.897106183823359,
|
| 854 |
+
"grad_norm": 0.6677018339279599,
|
| 855 |
+
"learning_rate": 3.2227693759239785e-07,
|
| 856 |
+
"loss": 0.2161,
|
| 857 |
+
"step": 2420
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.9045202845161141,
|
| 861 |
+
"grad_norm": 0.6581848099265243,
|
| 862 |
+
"learning_rate": 2.781465175834186e-07,
|
| 863 |
+
"loss": 0.2228,
|
| 864 |
+
"step": 2440
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.9119343852088692,
|
| 868 |
+
"grad_norm": 0.7113437251505971,
|
| 869 |
+
"learning_rate": 2.3717801586236544e-07,
|
| 870 |
+
"loss": 0.2144,
|
| 871 |
+
"step": 2460
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.9193484859016241,
|
| 875 |
+
"grad_norm": 0.6220302232780794,
|
| 876 |
+
"learning_rate": 1.9939886637129145e-07,
|
| 877 |
+
"loss": 0.2173,
|
| 878 |
+
"step": 2480
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.9267625865943792,
|
| 882 |
+
"grad_norm": 0.6691128505437876,
|
| 883 |
+
"learning_rate": 1.648343673504166e-07,
|
| 884 |
+
"loss": 0.2184,
|
| 885 |
+
"step": 2500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.9341766872871342,
|
| 889 |
+
"grad_norm": 0.6487345437674443,
|
| 890 |
+
"learning_rate": 1.3350766439753914e-07,
|
| 891 |
+
"loss": 0.2193,
|
| 892 |
+
"step": 2520
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.9415907879798893,
|
| 896 |
+
"grad_norm": 0.7736974881210988,
|
| 897 |
+
"learning_rate": 1.0543973496893401e-07,
|
| 898 |
+
"loss": 0.2232,
|
| 899 |
+
"step": 2540
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.9490048886726443,
|
| 903 |
+
"grad_norm": 0.7116280365195675,
|
| 904 |
+
"learning_rate": 8.064937433211518e-08,
|
| 905 |
+
"loss": 0.22,
|
| 906 |
+
"step": 2560
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.9564189893653993,
|
| 910 |
+
"grad_norm": 0.6630183579839392,
|
| 911 |
+
"learning_rate": 5.91531829798675e-08,
|
| 912 |
+
"loss": 0.2249,
|
| 913 |
+
"step": 2580
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.9638330900581543,
|
| 917 |
+
"grad_norm": 0.6777889817351815,
|
| 918 |
+
"learning_rate": 4.0965555513974297e-08,
|
| 919 |
+
"loss": 0.2203,
|
| 920 |
+
"step": 2600
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.9712471907509094,
|
| 924 |
+
"grad_norm": 0.6925637296642155,
|
| 925 |
+
"learning_rate": 2.6098671006087873e-08,
|
| 926 |
+
"loss": 0.2224,
|
| 927 |
+
"step": 2620
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.9786612914436644,
|
| 931 |
+
"grad_norm": 0.736161972188353,
|
| 932 |
+
"learning_rate": 1.4562484842199354e-08,
|
| 933 |
+
"loss": 0.2204,
|
| 934 |
+
"step": 2640
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.9860753921364195,
|
| 938 |
+
"grad_norm": 0.6366143976132524,
|
| 939 |
+
"learning_rate": 6.3647220561624535e-09,
|
| 940 |
+
"loss": 0.222,
|
| 941 |
+
"step": 2660
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.9934894928291745,
|
| 945 |
+
"grad_norm": 0.6355076829280015,
|
| 946 |
+
"learning_rate": 1.5108721567419493e-09,
|
| 947 |
+
"loss": 0.2176,
|
| 948 |
+
"step": 2680
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.0,
|
| 952 |
+
"step": 2698,
|
| 953 |
+
"total_flos": 1877022766792704.0,
|
| 954 |
+
"train_loss": 0.2793045342631301,
|
| 955 |
+
"train_runtime": 58447.463,
|
| 956 |
+
"train_samples_per_second": 5.908,
|
| 957 |
+
"train_steps_per_second": 0.046
|
| 958 |
+
}
|
| 959 |
+
],
|
| 960 |
+
"logging_steps": 20,
|
| 961 |
+
"max_steps": 2698,
|
| 962 |
+
"num_input_tokens_seen": 0,
|
| 963 |
+
"num_train_epochs": 1,
|
| 964 |
+
"save_steps": 1000,
|
| 965 |
+
"stateful_callbacks": {
|
| 966 |
+
"TrainerControl": {
|
| 967 |
+
"args": {
|
| 968 |
+
"should_epoch_stop": false,
|
| 969 |
+
"should_evaluate": false,
|
| 970 |
+
"should_log": false,
|
| 971 |
+
"should_save": true,
|
| 972 |
+
"should_training_stop": true
|
| 973 |
+
},
|
| 974 |
+
"attributes": {}
|
| 975 |
+
}
|
| 976 |
+
},
|
| 977 |
+
"total_flos": 1877022766792704.0,
|
| 978 |
+
"train_batch_size": 1,
|
| 979 |
+
"trial_name": null,
|
| 980 |
+
"trial_params": null
|
| 981 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42dc531a9c88f9485972ca19346447ec1da0174d1a92f218b1cb7b443fd6b6eb
|
| 3 |
+
size 8337
|
training_loss.png
ADDED
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"do_sample_frames": true,
|
| 12 |
+
"fps": 2,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_frames": 768,
|
| 25 |
+
"merge_size": 2,
|
| 26 |
+
"min_frames": 4,
|
| 27 |
+
"num_frames": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_metadata": false,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 25165824,
|
| 36 |
+
"shortest_edge": 4096
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2,
|
| 39 |
+
"video_metadata": null,
|
| 40 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 41 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|