Add checkpoint-5400 (step 5400/12387, CER=0.0913, CharAcc=90.9%)
Browse files- checkpoint-5400/README.md +207 -0
- checkpoint-5400/adapter_config.json +46 -0
- checkpoint-5400/adapter_model.safetensors +3 -0
- checkpoint-5400/optimizer.pt +3 -0
- checkpoint-5400/rng_state.pth +3 -0
- checkpoint-5400/scheduler.pt +3 -0
- checkpoint-5400/trainer_state.json +2140 -0
- checkpoint-5400/training_args.bin +3 -0
checkpoint-5400/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-VL-3B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen2.5-VL-3B-Instruct
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
|
| 21 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
- **Developed by:** [More Information Needed]
|
| 26 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 27 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 28 |
+
- **Model type:** [More Information Needed]
|
| 29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 30 |
+
- **License:** [More Information Needed]
|
| 31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 32 |
+
|
| 33 |
+
### Model Sources [optional]
|
| 34 |
+
|
| 35 |
+
<!-- Provide the basic links for the model. -->
|
| 36 |
+
|
| 37 |
+
- **Repository:** [More Information Needed]
|
| 38 |
+
- **Paper [optional]:** [More Information Needed]
|
| 39 |
+
- **Demo [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
## Uses
|
| 42 |
+
|
| 43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 44 |
+
|
| 45 |
+
### Direct Use
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Downstream Use [optional]
|
| 52 |
+
|
| 53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
### Out-of-Scope Use
|
| 58 |
+
|
| 59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
## Bias, Risks, and Limitations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 66 |
+
|
| 67 |
+
[More Information Needed]
|
| 68 |
+
|
| 69 |
+
### Recommendations
|
| 70 |
+
|
| 71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 72 |
+
|
| 73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 74 |
+
|
| 75 |
+
## How to Get Started with the Model
|
| 76 |
+
|
| 77 |
+
Use the code below to get started with the model.
|
| 78 |
+
|
| 79 |
+
[More Information Needed]
|
| 80 |
+
|
| 81 |
+
## Training Details
|
| 82 |
+
|
| 83 |
+
### Training Data
|
| 84 |
+
|
| 85 |
+
<!-- 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. -->
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
### Training Procedure
|
| 90 |
+
|
| 91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 92 |
+
|
| 93 |
+
#### Preprocessing [optional]
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
#### Training Hyperparameters
|
| 99 |
+
|
| 100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 101 |
+
|
| 102 |
+
#### Speeds, Sizes, Times [optional]
|
| 103 |
+
|
| 104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 105 |
+
|
| 106 |
+
[More Information Needed]
|
| 107 |
+
|
| 108 |
+
## Evaluation
|
| 109 |
+
|
| 110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 111 |
+
|
| 112 |
+
### Testing Data, Factors & Metrics
|
| 113 |
+
|
| 114 |
+
#### Testing Data
|
| 115 |
+
|
| 116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Factors
|
| 121 |
+
|
| 122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
#### Metrics
|
| 127 |
+
|
| 128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 129 |
+
|
| 130 |
+
[More Information Needed]
|
| 131 |
+
|
| 132 |
+
### Results
|
| 133 |
+
|
| 134 |
+
[More Information Needed]
|
| 135 |
+
|
| 136 |
+
#### Summary
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
## Model Examination [optional]
|
| 141 |
+
|
| 142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 143 |
+
|
| 144 |
+
[More Information Needed]
|
| 145 |
+
|
| 146 |
+
## Environmental Impact
|
| 147 |
+
|
| 148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 149 |
+
|
| 150 |
+
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).
|
| 151 |
+
|
| 152 |
+
- **Hardware Type:** [More Information Needed]
|
| 153 |
+
- **Hours used:** [More Information Needed]
|
| 154 |
+
- **Cloud Provider:** [More Information Needed]
|
| 155 |
+
- **Compute Region:** [More Information Needed]
|
| 156 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 157 |
+
|
| 158 |
+
## Technical Specifications [optional]
|
| 159 |
+
|
| 160 |
+
### Model Architecture and Objective
|
| 161 |
+
|
| 162 |
+
[More Information Needed]
|
| 163 |
+
|
| 164 |
+
### Compute Infrastructure
|
| 165 |
+
|
| 166 |
+
[More Information Needed]
|
| 167 |
+
|
| 168 |
+
#### Hardware
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
#### Software
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
## Citation [optional]
|
| 177 |
+
|
| 178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 179 |
+
|
| 180 |
+
**BibTeX:**
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
**APA:**
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## Glossary [optional]
|
| 189 |
+
|
| 190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 191 |
+
|
| 192 |
+
[More Information Needed]
|
| 193 |
+
|
| 194 |
+
## More Information [optional]
|
| 195 |
+
|
| 196 |
+
[More Information Needed]
|
| 197 |
+
|
| 198 |
+
## Model Card Authors [optional]
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## Model Card Contact
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
### Framework versions
|
| 206 |
+
|
| 207 |
+
- PEFT 0.18.1
|
checkpoint-5400/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 256,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.1",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 128,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"up_proj",
|
| 33 |
+
"o_proj",
|
| 34 |
+
"q_proj",
|
| 35 |
+
"gate_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"v_proj",
|
| 38 |
+
"k_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "CAUSAL_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_dora": false,
|
| 44 |
+
"use_qalora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
checkpoint-5400/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b9f5b5d6bd74fc8fbe574d1f323fbc21fb27b3abb73abb1dfb3f51ffe0463da
|
| 3 |
+
size 1188992112
|
checkpoint-5400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8de9c441bd7d63cdee75aa57648b228ede71f197b93530b7f047d40c2ea92014
|
| 3 |
+
size 2378375482
|
checkpoint-5400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3df69d755c047754e91577a68f31e02007d3fb1ad5078e2d1c31c2d889000540
|
| 3 |
+
size 14244
|
checkpoint-5400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78522cd509147d31f92bea000e92cf600e12079491e6a9ddd56cecdfdbbf1a16
|
| 3 |
+
size 1064
|
checkpoint-5400/trainer_state.json
ADDED
|
@@ -0,0 +1,2140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 3200,
|
| 3 |
+
"best_metric": 5.454287528991699,
|
| 4 |
+
"best_model_checkpoint": "/root/odia_ocr/checkpoints_improved/checkpoint-3200",
|
| 5 |
+
"epoch": 1.3078413563427187,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 5400,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004844081138359067,
|
| 14 |
+
"grad_norm": 12.812041282653809,
|
| 15 |
+
"learning_rate": 1.532258064516129e-06,
|
| 16 |
+
"loss": 12.957037353515625,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.009688162276718135,
|
| 21 |
+
"grad_norm": 5.143731117248535,
|
| 22 |
+
"learning_rate": 3.1451612903225806e-06,
|
| 23 |
+
"loss": 11.34280776977539,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.014532243415077202,
|
| 28 |
+
"grad_norm": 1.9331496953964233,
|
| 29 |
+
"learning_rate": 4.758064516129032e-06,
|
| 30 |
+
"loss": 8.1042724609375,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.01937632455343627,
|
| 35 |
+
"grad_norm": 0.4644749164581299,
|
| 36 |
+
"learning_rate": 6.370967741935484e-06,
|
| 37 |
+
"loss": 5.809648132324218,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.024220405691795337,
|
| 42 |
+
"grad_norm": 0.11639782786369324,
|
| 43 |
+
"learning_rate": 7.983870967741935e-06,
|
| 44 |
+
"loss": 5.1223915100097654,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.029064486830154404,
|
| 49 |
+
"grad_norm": 0.05908145383000374,
|
| 50 |
+
"learning_rate": 9.596774193548387e-06,
|
| 51 |
+
"loss": 4.9434257507324215,
|
| 52 |
+
"step": 120
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.03390856796851347,
|
| 56 |
+
"grad_norm": 0.04645635560154915,
|
| 57 |
+
"learning_rate": 1.1209677419354839e-05,
|
| 58 |
+
"loss": 4.949678802490235,
|
| 59 |
+
"step": 140
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03875264910687254,
|
| 63 |
+
"grad_norm": 0.05589432641863823,
|
| 64 |
+
"learning_rate": 1.2822580645161291e-05,
|
| 65 |
+
"loss": 4.812170791625976,
|
| 66 |
+
"step": 160
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.043596730245231606,
|
| 70 |
+
"grad_norm": 0.05051477253437042,
|
| 71 |
+
"learning_rate": 1.4435483870967741e-05,
|
| 72 |
+
"loss": 4.792440032958984,
|
| 73 |
+
"step": 180
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.04844081138359067,
|
| 77 |
+
"grad_norm": 0.0538371242582798,
|
| 78 |
+
"learning_rate": 1.6048387096774197e-05,
|
| 79 |
+
"loss": 5.007255172729492,
|
| 80 |
+
"step": 200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04844081138359067,
|
| 84 |
+
"eval_loss": 5.5122504234313965,
|
| 85 |
+
"eval_runtime": 481.6195,
|
| 86 |
+
"eval_samples_per_second": 15.24,
|
| 87 |
+
"eval_steps_per_second": 7.62,
|
| 88 |
+
"step": 200
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.05328489252194974,
|
| 92 |
+
"grad_norm": 0.07251875847578049,
|
| 93 |
+
"learning_rate": 1.7661290322580645e-05,
|
| 94 |
+
"loss": 4.900541305541992,
|
| 95 |
+
"step": 220
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.05812897366030881,
|
| 99 |
+
"grad_norm": 0.05386732146143913,
|
| 100 |
+
"learning_rate": 1.9274193548387097e-05,
|
| 101 |
+
"loss": 4.945923233032227,
|
| 102 |
+
"step": 240
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.06297305479866788,
|
| 106 |
+
"grad_norm": 0.07287013530731201,
|
| 107 |
+
"learning_rate": 2.088709677419355e-05,
|
| 108 |
+
"loss": 4.906622314453125,
|
| 109 |
+
"step": 260
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.06781713593702694,
|
| 113 |
+
"grad_norm": 0.06443014740943909,
|
| 114 |
+
"learning_rate": 2.25e-05,
|
| 115 |
+
"loss": 4.96992073059082,
|
| 116 |
+
"step": 280
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.07266121707538602,
|
| 120 |
+
"grad_norm": 0.051735080778598785,
|
| 121 |
+
"learning_rate": 2.4112903225806453e-05,
|
| 122 |
+
"loss": 4.886655044555664,
|
| 123 |
+
"step": 300
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.07750529821374508,
|
| 127 |
+
"grad_norm": 0.06519602984189987,
|
| 128 |
+
"learning_rate": 2.5725806451612905e-05,
|
| 129 |
+
"loss": 4.9916423797607425,
|
| 130 |
+
"step": 320
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.08234937935210415,
|
| 134 |
+
"grad_norm": 0.06522039324045181,
|
| 135 |
+
"learning_rate": 2.7338709677419354e-05,
|
| 136 |
+
"loss": 4.85333137512207,
|
| 137 |
+
"step": 340
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.08719346049046321,
|
| 141 |
+
"grad_norm": 0.09097781777381897,
|
| 142 |
+
"learning_rate": 2.8951612903225806e-05,
|
| 143 |
+
"loss": 5.001050186157227,
|
| 144 |
+
"step": 360
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.09203754162882229,
|
| 148 |
+
"grad_norm": 0.06196173280477524,
|
| 149 |
+
"learning_rate": 3.056451612903226e-05,
|
| 150 |
+
"loss": 4.854343032836914,
|
| 151 |
+
"step": 380
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.09688162276718135,
|
| 155 |
+
"grad_norm": 0.0945107564330101,
|
| 156 |
+
"learning_rate": 3.217741935483871e-05,
|
| 157 |
+
"loss": 4.964828872680664,
|
| 158 |
+
"step": 400
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.09688162276718135,
|
| 162 |
+
"eval_loss": 5.484151363372803,
|
| 163 |
+
"eval_runtime": 482.9864,
|
| 164 |
+
"eval_samples_per_second": 15.197,
|
| 165 |
+
"eval_steps_per_second": 7.599,
|
| 166 |
+
"step": 400
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.10172570390554042,
|
| 170 |
+
"grad_norm": 0.0707496702671051,
|
| 171 |
+
"learning_rate": 3.379032258064516e-05,
|
| 172 |
+
"loss": 5.008393859863281,
|
| 173 |
+
"step": 420
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.10656978504389948,
|
| 177 |
+
"grad_norm": 0.0661933496594429,
|
| 178 |
+
"learning_rate": 3.5403225806451614e-05,
|
| 179 |
+
"loss": 4.982975006103516,
|
| 180 |
+
"step": 440
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.11141386618225856,
|
| 184 |
+
"grad_norm": 0.07057442516088486,
|
| 185 |
+
"learning_rate": 3.701612903225807e-05,
|
| 186 |
+
"loss": 4.927794647216797,
|
| 187 |
+
"step": 460
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.11625794732061762,
|
| 191 |
+
"grad_norm": 0.05171314626932144,
|
| 192 |
+
"learning_rate": 3.862903225806452e-05,
|
| 193 |
+
"loss": 4.754631042480469,
|
| 194 |
+
"step": 480
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.12110202845897669,
|
| 198 |
+
"grad_norm": 0.0782339945435524,
|
| 199 |
+
"learning_rate": 4.024193548387097e-05,
|
| 200 |
+
"loss": 4.914446640014648,
|
| 201 |
+
"step": 500
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.12594610959733576,
|
| 205 |
+
"grad_norm": 0.07288593798875809,
|
| 206 |
+
"learning_rate": 4.1854838709677415e-05,
|
| 207 |
+
"loss": 4.860435485839844,
|
| 208 |
+
"step": 520
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.1307901907356948,
|
| 212 |
+
"grad_norm": 0.05010804161429405,
|
| 213 |
+
"learning_rate": 4.346774193548388e-05,
|
| 214 |
+
"loss": 4.710846328735352,
|
| 215 |
+
"step": 540
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.13563427187405389,
|
| 219 |
+
"grad_norm": 0.0925319567322731,
|
| 220 |
+
"learning_rate": 4.5080645161290326e-05,
|
| 221 |
+
"loss": 4.98031005859375,
|
| 222 |
+
"step": 560
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.14047835301241296,
|
| 226 |
+
"grad_norm": 0.047361522912979126,
|
| 227 |
+
"learning_rate": 4.6693548387096775e-05,
|
| 228 |
+
"loss": 4.936359405517578,
|
| 229 |
+
"step": 580
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.14532243415077203,
|
| 233 |
+
"grad_norm": 0.06307175010442734,
|
| 234 |
+
"learning_rate": 4.830645161290323e-05,
|
| 235 |
+
"loss": 4.697824478149414,
|
| 236 |
+
"step": 600
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.14532243415077203,
|
| 240 |
+
"eval_loss": 5.4713640213012695,
|
| 241 |
+
"eval_runtime": 483.5438,
|
| 242 |
+
"eval_samples_per_second": 15.18,
|
| 243 |
+
"eval_steps_per_second": 7.59,
|
| 244 |
+
"step": 600
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.15016651528913108,
|
| 248 |
+
"grad_norm": 0.06868302077054977,
|
| 249 |
+
"learning_rate": 4.991935483870968e-05,
|
| 250 |
+
"loss": 4.9246562957763675,
|
| 251 |
+
"step": 620
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.15501059642749015,
|
| 255 |
+
"grad_norm": 0.06361743062734604,
|
| 256 |
+
"learning_rate": 4.9999678349284276e-05,
|
| 257 |
+
"loss": 4.979264450073242,
|
| 258 |
+
"step": 640
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.15985467756584923,
|
| 262 |
+
"grad_norm": 0.06285427510738373,
|
| 263 |
+
"learning_rate": 4.999864479953565e-05,
|
| 264 |
+
"loss": 4.902791976928711,
|
| 265 |
+
"step": 660
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.1646987587042083,
|
| 269 |
+
"grad_norm": 0.048156049102544785,
|
| 270 |
+
"learning_rate": 4.999689848922155e-05,
|
| 271 |
+
"loss": 4.905753326416016,
|
| 272 |
+
"step": 680
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.16954283984256735,
|
| 276 |
+
"grad_norm": 0.036559417843818665,
|
| 277 |
+
"learning_rate": 4.999443946813271e-05,
|
| 278 |
+
"loss": 4.906116485595703,
|
| 279 |
+
"step": 700
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.17438692098092642,
|
| 283 |
+
"grad_norm": 0.04299989715218544,
|
| 284 |
+
"learning_rate": 4.999126780638068e-05,
|
| 285 |
+
"loss": 4.8410499572753904,
|
| 286 |
+
"step": 720
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.1792310021192855,
|
| 290 |
+
"grad_norm": 0.04031865671277046,
|
| 291 |
+
"learning_rate": 4.9987383594395764e-05,
|
| 292 |
+
"loss": 4.942621231079102,
|
| 293 |
+
"step": 740
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.18407508325764457,
|
| 297 |
+
"grad_norm": 0.0709218680858612,
|
| 298 |
+
"learning_rate": 4.99827869429245e-05,
|
| 299 |
+
"loss": 4.831058120727539,
|
| 300 |
+
"step": 760
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.18891916439600362,
|
| 304 |
+
"grad_norm": 0.04334535449743271,
|
| 305 |
+
"learning_rate": 4.9977477983026456e-05,
|
| 306 |
+
"loss": 4.815376663208008,
|
| 307 |
+
"step": 780
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.1937632455343627,
|
| 311 |
+
"grad_norm": 0.08114223182201385,
|
| 312 |
+
"learning_rate": 4.997145686607054e-05,
|
| 313 |
+
"loss": 4.922482681274414,
|
| 314 |
+
"step": 800
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.1937632455343627,
|
| 318 |
+
"eval_loss": 5.467911720275879,
|
| 319 |
+
"eval_runtime": 486.133,
|
| 320 |
+
"eval_samples_per_second": 15.099,
|
| 321 |
+
"eval_steps_per_second": 7.549,
|
| 322 |
+
"step": 800
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.19860732667272177,
|
| 326 |
+
"grad_norm": 0.03837033733725548,
|
| 327 |
+
"learning_rate": 4.996472376373064e-05,
|
| 328 |
+
"loss": 4.721331787109375,
|
| 329 |
+
"step": 820
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.20345140781108084,
|
| 333 |
+
"grad_norm": 0.042904820293188095,
|
| 334 |
+
"learning_rate": 4.995727886798076e-05,
|
| 335 |
+
"loss": 4.922665405273437,
|
| 336 |
+
"step": 840
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.20829548894943992,
|
| 340 |
+
"grad_norm": 0.042334090918302536,
|
| 341 |
+
"learning_rate": 4.994912239108953e-05,
|
| 342 |
+
"loss": 4.739095306396484,
|
| 343 |
+
"step": 860
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.21313957008779896,
|
| 347 |
+
"grad_norm": 0.05880925804376602,
|
| 348 |
+
"learning_rate": 4.994025456561415e-05,
|
| 349 |
+
"loss": 4.862358856201172,
|
| 350 |
+
"step": 880
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.21798365122615804,
|
| 354 |
+
"grad_norm": 0.05243176966905594,
|
| 355 |
+
"learning_rate": 4.99306756443938e-05,
|
| 356 |
+
"loss": 4.801820755004883,
|
| 357 |
+
"step": 900
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.2228277323645171,
|
| 361 |
+
"grad_norm": 0.04455817863345146,
|
| 362 |
+
"learning_rate": 4.992038590054235e-05,
|
| 363 |
+
"loss": 4.858511352539063,
|
| 364 |
+
"step": 920
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.22767181350287619,
|
| 368 |
+
"grad_norm": 0.052609678357839584,
|
| 369 |
+
"learning_rate": 4.990938562744067e-05,
|
| 370 |
+
"loss": 4.80189323425293,
|
| 371 |
+
"step": 940
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.23251589464123523,
|
| 375 |
+
"grad_norm": 0.03932235389947891,
|
| 376 |
+
"learning_rate": 4.9897675138728194e-05,
|
| 377 |
+
"loss": 4.971810150146484,
|
| 378 |
+
"step": 960
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.2373599757795943,
|
| 382 |
+
"grad_norm": 0.034223828464746475,
|
| 383 |
+
"learning_rate": 4.9885254768293993e-05,
|
| 384 |
+
"loss": 4.843924713134766,
|
| 385 |
+
"step": 980
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.24220405691795338,
|
| 389 |
+
"grad_norm": 0.052775464951992035,
|
| 390 |
+
"learning_rate": 4.9872124870267277e-05,
|
| 391 |
+
"loss": 5.065494537353516,
|
| 392 |
+
"step": 1000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.24220405691795338,
|
| 396 |
+
"eval_loss": 5.465411186218262,
|
| 397 |
+
"eval_runtime": 482.3283,
|
| 398 |
+
"eval_samples_per_second": 15.218,
|
| 399 |
+
"eval_steps_per_second": 7.609,
|
| 400 |
+
"step": 1000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.24704813805631246,
|
| 404 |
+
"grad_norm": 0.02837868221104145,
|
| 405 |
+
"learning_rate": 4.985828581900729e-05,
|
| 406 |
+
"loss": 4.921312713623047,
|
| 407 |
+
"step": 1020
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.25189221919467153,
|
| 411 |
+
"grad_norm": 0.03618283197283745,
|
| 412 |
+
"learning_rate": 4.984373800909262e-05,
|
| 413 |
+
"loss": 4.854024887084961,
|
| 414 |
+
"step": 1040
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.2567363003330306,
|
| 418 |
+
"grad_norm": 0.03154360130429268,
|
| 419 |
+
"learning_rate": 4.982848185530995e-05,
|
| 420 |
+
"loss": 4.909141540527344,
|
| 421 |
+
"step": 1060
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.2615803814713896,
|
| 425 |
+
"grad_norm": 0.03342705965042114,
|
| 426 |
+
"learning_rate": 4.981251779264227e-05,
|
| 427 |
+
"loss": 4.873151779174805,
|
| 428 |
+
"step": 1080
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.2664244626097487,
|
| 432 |
+
"grad_norm": 0.038160618394613266,
|
| 433 |
+
"learning_rate": 4.9795846276256395e-05,
|
| 434 |
+
"loss": 4.937899780273438,
|
| 435 |
+
"step": 1100
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.27126854374810777,
|
| 439 |
+
"grad_norm": 0.02787560038268566,
|
| 440 |
+
"learning_rate": 4.97784677814901e-05,
|
| 441 |
+
"loss": 4.889313888549805,
|
| 442 |
+
"step": 1120
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.2761126248864669,
|
| 446 |
+
"grad_norm": 0.03252527490258217,
|
| 447 |
+
"learning_rate": 4.976038280383847e-05,
|
| 448 |
+
"loss": 5.092146301269532,
|
| 449 |
+
"step": 1140
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.2809567060248259,
|
| 453 |
+
"grad_norm": 0.03215664252638817,
|
| 454 |
+
"learning_rate": 4.97415918589398e-05,
|
| 455 |
+
"loss": 4.881315994262695,
|
| 456 |
+
"step": 1160
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.28580078716318497,
|
| 460 |
+
"grad_norm": 0.056495729833841324,
|
| 461 |
+
"learning_rate": 4.972209548256093e-05,
|
| 462 |
+
"loss": 4.913896179199218,
|
| 463 |
+
"step": 1180
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.29064486830154407,
|
| 467 |
+
"grad_norm": 0.023406801745295525,
|
| 468 |
+
"learning_rate": 4.97018942305819e-05,
|
| 469 |
+
"loss": 5.040941619873047,
|
| 470 |
+
"step": 1200
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.29064486830154407,
|
| 474 |
+
"eval_loss": 5.464733123779297,
|
| 475 |
+
"eval_runtime": 479.1861,
|
| 476 |
+
"eval_samples_per_second": 15.318,
|
| 477 |
+
"eval_steps_per_second": 7.659,
|
| 478 |
+
"step": 1200
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.2954889494399031,
|
| 482 |
+
"grad_norm": 0.03091084584593773,
|
| 483 |
+
"learning_rate": 4.968098867898019e-05,
|
| 484 |
+
"loss": 4.7054706573486325,
|
| 485 |
+
"step": 1220
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.30033303057826216,
|
| 489 |
+
"grad_norm": 0.033658791333436966,
|
| 490 |
+
"learning_rate": 4.965937942381421e-05,
|
| 491 |
+
"loss": 4.971173858642578,
|
| 492 |
+
"step": 1240
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.30517711171662126,
|
| 496 |
+
"grad_norm": 0.03186121955513954,
|
| 497 |
+
"learning_rate": 4.963706708120635e-05,
|
| 498 |
+
"loss": 4.918471908569336,
|
| 499 |
+
"step": 1260
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.3100211928549803,
|
| 503 |
+
"grad_norm": 0.037234991788864136,
|
| 504 |
+
"learning_rate": 4.9614052287325426e-05,
|
| 505 |
+
"loss": 4.957798004150391,
|
| 506 |
+
"step": 1280
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.3148652739933394,
|
| 510 |
+
"grad_norm": 0.04513128846883774,
|
| 511 |
+
"learning_rate": 4.95903356983685e-05,
|
| 512 |
+
"loss": 4.933160400390625,
|
| 513 |
+
"step": 1300
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.31970935513169846,
|
| 517 |
+
"grad_norm": 0.021936912089586258,
|
| 518 |
+
"learning_rate": 4.95659179905422e-05,
|
| 519 |
+
"loss": 4.837236404418945,
|
| 520 |
+
"step": 1320
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3245534362700575,
|
| 524 |
+
"grad_norm": 0.047507770359516144,
|
| 525 |
+
"learning_rate": 4.954079986004345e-05,
|
| 526 |
+
"loss": 4.874291229248047,
|
| 527 |
+
"step": 1340
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3293975174084166,
|
| 531 |
+
"grad_norm": 0.02777005545794964,
|
| 532 |
+
"learning_rate": 4.951498202303957e-05,
|
| 533 |
+
"loss": 4.831377410888672,
|
| 534 |
+
"step": 1360
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.33424159854677565,
|
| 538 |
+
"grad_norm": 0.04671608284115791,
|
| 539 |
+
"learning_rate": 4.948846521564792e-05,
|
| 540 |
+
"loss": 4.9074962615966795,
|
| 541 |
+
"step": 1380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3390856796851347,
|
| 545 |
+
"grad_norm": 0.05117534101009369,
|
| 546 |
+
"learning_rate": 4.946125019391486e-05,
|
| 547 |
+
"loss": 4.955949783325195,
|
| 548 |
+
"step": 1400
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.3390856796851347,
|
| 552 |
+
"eval_loss": 5.462268829345703,
|
| 553 |
+
"eval_runtime": 480.5711,
|
| 554 |
+
"eval_samples_per_second": 15.273,
|
| 555 |
+
"eval_steps_per_second": 7.637,
|
| 556 |
+
"step": 1400
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.3439297608234938,
|
| 560 |
+
"grad_norm": 0.04413221776485443,
|
| 561 |
+
"learning_rate": 4.9433337733794225e-05,
|
| 562 |
+
"loss": 4.930236434936523,
|
| 563 |
+
"step": 1420
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.34877384196185285,
|
| 567 |
+
"grad_norm": 0.031841397285461426,
|
| 568 |
+
"learning_rate": 4.94047286311252e-05,
|
| 569 |
+
"loss": 4.9899742126464846,
|
| 570 |
+
"step": 1440
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.35361792310021195,
|
| 574 |
+
"grad_norm": 0.03400244191288948,
|
| 575 |
+
"learning_rate": 4.93754237016096e-05,
|
| 576 |
+
"loss": 4.879816055297852,
|
| 577 |
+
"step": 1460
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.358462004238571,
|
| 581 |
+
"grad_norm": 0.02796698734164238,
|
| 582 |
+
"learning_rate": 4.9345423780788655e-05,
|
| 583 |
+
"loss": 4.900162124633789,
|
| 584 |
+
"step": 1480
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.36330608537693004,
|
| 588 |
+
"grad_norm": 0.033209074288606644,
|
| 589 |
+
"learning_rate": 4.9314729724019135e-05,
|
| 590 |
+
"loss": 4.824586868286133,
|
| 591 |
+
"step": 1500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.36815016651528915,
|
| 595 |
+
"grad_norm": 0.03357836231589317,
|
| 596 |
+
"learning_rate": 4.928334240644903e-05,
|
| 597 |
+
"loss": 4.901557540893554,
|
| 598 |
+
"step": 1520
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.3729942476536482,
|
| 602 |
+
"grad_norm": 0.030524376779794693,
|
| 603 |
+
"learning_rate": 4.925126272299253e-05,
|
| 604 |
+
"loss": 4.955865097045899,
|
| 605 |
+
"step": 1540
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.37783832879200724,
|
| 609 |
+
"grad_norm": 0.02066030353307724,
|
| 610 |
+
"learning_rate": 4.921849158830455e-05,
|
| 611 |
+
"loss": 4.921824264526367,
|
| 612 |
+
"step": 1560
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.38268240993036634,
|
| 616 |
+
"grad_norm": 0.03722696006298065,
|
| 617 |
+
"learning_rate": 4.918502993675463e-05,
|
| 618 |
+
"loss": 4.897643661499023,
|
| 619 |
+
"step": 1580
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.3875264910687254,
|
| 623 |
+
"grad_norm": 0.03600393235683441,
|
| 624 |
+
"learning_rate": 4.915087872240034e-05,
|
| 625 |
+
"loss": 4.867633819580078,
|
| 626 |
+
"step": 1600
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.3875264910687254,
|
| 630 |
+
"eval_loss": 5.463290691375732,
|
| 631 |
+
"eval_runtime": 482.557,
|
| 632 |
+
"eval_samples_per_second": 15.211,
|
| 633 |
+
"eval_steps_per_second": 7.605,
|
| 634 |
+
"step": 1600
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.3923705722070845,
|
| 638 |
+
"grad_norm": 0.01853497512638569,
|
| 639 |
+
"learning_rate": 4.911603891896e-05,
|
| 640 |
+
"loss": 4.990079116821289,
|
| 641 |
+
"step": 1620
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.39721465334544354,
|
| 645 |
+
"grad_norm": 0.03120853751897812,
|
| 646 |
+
"learning_rate": 4.9080511519784975e-05,
|
| 647 |
+
"loss": 4.889575576782226,
|
| 648 |
+
"step": 1640
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.4020587344838026,
|
| 652 |
+
"grad_norm": 0.04181843250989914,
|
| 653 |
+
"learning_rate": 4.9044297537831355e-05,
|
| 654 |
+
"loss": 4.894519424438476,
|
| 655 |
+
"step": 1660
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.4069028156221617,
|
| 659 |
+
"grad_norm": 0.027956627309322357,
|
| 660 |
+
"learning_rate": 4.900739800563103e-05,
|
| 661 |
+
"loss": 5.025855255126953,
|
| 662 |
+
"step": 1680
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.41174689676052073,
|
| 666 |
+
"grad_norm": 0.025699257850646973,
|
| 667 |
+
"learning_rate": 4.896981397526229e-05,
|
| 668 |
+
"loss": 4.933831405639649,
|
| 669 |
+
"step": 1700
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.41659097789887983,
|
| 673 |
+
"grad_norm": 0.03355032578110695,
|
| 674 |
+
"learning_rate": 4.893154651831981e-05,
|
| 675 |
+
"loss": 4.883275985717773,
|
| 676 |
+
"step": 1720
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.4214350590372389,
|
| 680 |
+
"grad_norm": 0.02468765340745449,
|
| 681 |
+
"learning_rate": 4.8892596725884124e-05,
|
| 682 |
+
"loss": 4.825000762939453,
|
| 683 |
+
"step": 1740
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.4262791401755979,
|
| 687 |
+
"grad_norm": 0.04183134064078331,
|
| 688 |
+
"learning_rate": 4.885296570849045e-05,
|
| 689 |
+
"loss": 4.861746978759766,
|
| 690 |
+
"step": 1760
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.43112322131395703,
|
| 694 |
+
"grad_norm": 0.028777016326785088,
|
| 695 |
+
"learning_rate": 4.881265459609711e-05,
|
| 696 |
+
"loss": 4.734410095214844,
|
| 697 |
+
"step": 1780
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.4359673024523161,
|
| 701 |
+
"grad_norm": 0.11064556241035461,
|
| 702 |
+
"learning_rate": 4.877166453805325e-05,
|
| 703 |
+
"loss": 4.908732604980469,
|
| 704 |
+
"step": 1800
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.4359673024523161,
|
| 708 |
+
"eval_loss": 5.462699890136719,
|
| 709 |
+
"eval_runtime": 484.184,
|
| 710 |
+
"eval_samples_per_second": 15.16,
|
| 711 |
+
"eval_steps_per_second": 7.58,
|
| 712 |
+
"step": 1800
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.4408113835906751,
|
| 716 |
+
"grad_norm": 0.03197271004319191,
|
| 717 |
+
"learning_rate": 4.8729996703066117e-05,
|
| 718 |
+
"loss": 4.928284072875977,
|
| 719 |
+
"step": 1820
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.4456554647290342,
|
| 723 |
+
"grad_norm": 0.050927624106407166,
|
| 724 |
+
"learning_rate": 4.868765227916769e-05,
|
| 725 |
+
"loss": 4.886736297607422,
|
| 726 |
+
"step": 1840
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.45049954586739327,
|
| 730 |
+
"grad_norm": 0.02937314845621586,
|
| 731 |
+
"learning_rate": 4.864463247368082e-05,
|
| 732 |
+
"loss": 4.795632934570312,
|
| 733 |
+
"step": 1860
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.45534362700575237,
|
| 737 |
+
"grad_norm": 0.03579329699277878,
|
| 738 |
+
"learning_rate": 4.8600938513184847e-05,
|
| 739 |
+
"loss": 4.779296875,
|
| 740 |
+
"step": 1880
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.4601877081441114,
|
| 744 |
+
"grad_norm": 0.03522449731826782,
|
| 745 |
+
"learning_rate": 4.8556571643480585e-05,
|
| 746 |
+
"loss": 4.904380416870117,
|
| 747 |
+
"step": 1900
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.46503178928247046,
|
| 751 |
+
"grad_norm": 0.023437773808836937,
|
| 752 |
+
"learning_rate": 4.8511533129554816e-05,
|
| 753 |
+
"loss": 4.982876968383789,
|
| 754 |
+
"step": 1920
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.46987587042082957,
|
| 758 |
+
"grad_norm": 0.015325312502682209,
|
| 759 |
+
"learning_rate": 4.84658242555442e-05,
|
| 760 |
+
"loss": 4.990073394775391,
|
| 761 |
+
"step": 1940
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.4747199515591886,
|
| 765 |
+
"grad_norm": 0.030531391501426697,
|
| 766 |
+
"learning_rate": 4.841944632469872e-05,
|
| 767 |
+
"loss": 4.923136901855469,
|
| 768 |
+
"step": 1960
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.47956403269754766,
|
| 772 |
+
"grad_norm": 0.0198193471878767,
|
| 773 |
+
"learning_rate": 4.8372400659344444e-05,
|
| 774 |
+
"loss": 4.956871414184571,
|
| 775 |
+
"step": 1980
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.48440811383590676,
|
| 779 |
+
"grad_norm": 0.0377812422811985,
|
| 780 |
+
"learning_rate": 4.83246886008459e-05,
|
| 781 |
+
"loss": 4.910104370117187,
|
| 782 |
+
"step": 2000
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.48440811383590676,
|
| 786 |
+
"eval_loss": 5.462129592895508,
|
| 787 |
+
"eval_runtime": 481.7351,
|
| 788 |
+
"eval_samples_per_second": 15.237,
|
| 789 |
+
"eval_steps_per_second": 7.618,
|
| 790 |
+
"step": 2000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.4892521949742658,
|
| 794 |
+
"grad_norm": 0.03756606578826904,
|
| 795 |
+
"learning_rate": 4.8276311509567785e-05,
|
| 796 |
+
"loss": 4.961421203613281,
|
| 797 |
+
"step": 2020
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.4940962761126249,
|
| 801 |
+
"grad_norm": 0.025465775281190872,
|
| 802 |
+
"learning_rate": 4.8227270764836175e-05,
|
| 803 |
+
"loss": 4.971789932250976,
|
| 804 |
+
"step": 2040
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.49894035725098396,
|
| 808 |
+
"grad_norm": 0.04584196209907532,
|
| 809 |
+
"learning_rate": 4.817756776489923e-05,
|
| 810 |
+
"loss": 4.722394180297852,
|
| 811 |
+
"step": 2060
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.5037844383893431,
|
| 815 |
+
"grad_norm": 0.024054571986198425,
|
| 816 |
+
"learning_rate": 4.812720392688731e-05,
|
| 817 |
+
"loss": 4.861309432983399,
|
| 818 |
+
"step": 2080
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.508628519527702,
|
| 822 |
+
"grad_norm": 0.021322039887309074,
|
| 823 |
+
"learning_rate": 4.807618068677254e-05,
|
| 824 |
+
"loss": 4.906083679199218,
|
| 825 |
+
"step": 2100
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.5134726006660612,
|
| 829 |
+
"grad_norm": 0.024236466735601425,
|
| 830 |
+
"learning_rate": 4.802449949932796e-05,
|
| 831 |
+
"loss": 4.774163818359375,
|
| 832 |
+
"step": 2120
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.5183166818044203,
|
| 836 |
+
"grad_norm": 0.025150248780846596,
|
| 837 |
+
"learning_rate": 4.79721618380859e-05,
|
| 838 |
+
"loss": 5.06263427734375,
|
| 839 |
+
"step": 2140
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.5231607629427792,
|
| 843 |
+
"grad_norm": 0.016574619337916374,
|
| 844 |
+
"learning_rate": 4.791916919529611e-05,
|
| 845 |
+
"loss": 4.989673233032226,
|
| 846 |
+
"step": 2160
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.5280048440811383,
|
| 850 |
+
"grad_norm": 0.022480934858322144,
|
| 851 |
+
"learning_rate": 4.786552308188314e-05,
|
| 852 |
+
"loss": 4.921234130859375,
|
| 853 |
+
"step": 2180
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.5328489252194974,
|
| 857 |
+
"grad_norm": 0.018986444920301437,
|
| 858 |
+
"learning_rate": 4.781122502740329e-05,
|
| 859 |
+
"loss": 4.958284378051758,
|
| 860 |
+
"step": 2200
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.5328489252194974,
|
| 864 |
+
"eval_loss": 5.459774017333984,
|
| 865 |
+
"eval_runtime": 481.5781,
|
| 866 |
+
"eval_samples_per_second": 15.242,
|
| 867 |
+
"eval_steps_per_second": 7.621,
|
| 868 |
+
"step": 2200
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.5376930063578564,
|
| 872 |
+
"grad_norm": 0.024930085986852646,
|
| 873 |
+
"learning_rate": 4.775627658000091e-05,
|
| 874 |
+
"loss": 4.923190307617188,
|
| 875 |
+
"step": 2220
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.5425370874962155,
|
| 879 |
+
"grad_norm": 0.016377661377191544,
|
| 880 |
+
"learning_rate": 4.770067930636442e-05,
|
| 881 |
+
"loss": 4.9806373596191404,
|
| 882 |
+
"step": 2240
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.5473811686345746,
|
| 886 |
+
"grad_norm": 0.028611725196242332,
|
| 887 |
+
"learning_rate": 4.764443479168151e-05,
|
| 888 |
+
"loss": 4.843650054931641,
|
| 889 |
+
"step": 2260
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.5522252497729337,
|
| 893 |
+
"grad_norm": 0.02169787883758545,
|
| 894 |
+
"learning_rate": 4.758754463959401e-05,
|
| 895 |
+
"loss": 4.820799255371094,
|
| 896 |
+
"step": 2280
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.5570693309112927,
|
| 900 |
+
"grad_norm": 0.014351587742567062,
|
| 901 |
+
"learning_rate": 4.75300104721521e-05,
|
| 902 |
+
"loss": 4.888659286499023,
|
| 903 |
+
"step": 2300
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.5619134120496518,
|
| 907 |
+
"grad_norm": 0.02870621345937252,
|
| 908 |
+
"learning_rate": 4.747183392976815e-05,
|
| 909 |
+
"loss": 4.703000259399414,
|
| 910 |
+
"step": 2320
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.5667574931880109,
|
| 914 |
+
"grad_norm": 0.02605106681585312,
|
| 915 |
+
"learning_rate": 4.741301667116987e-05,
|
| 916 |
+
"loss": 4.83842658996582,
|
| 917 |
+
"step": 2340
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.5716015743263699,
|
| 921 |
+
"grad_norm": 0.029983455315232277,
|
| 922 |
+
"learning_rate": 4.735356037335309e-05,
|
| 923 |
+
"loss": 4.874066925048828,
|
| 924 |
+
"step": 2360
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.576445655464729,
|
| 928 |
+
"grad_norm": 0.022755078971385956,
|
| 929 |
+
"learning_rate": 4.729346673153386e-05,
|
| 930 |
+
"loss": 4.92518424987793,
|
| 931 |
+
"step": 2380
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.5812897366030881,
|
| 935 |
+
"grad_norm": 0.026459872722625732,
|
| 936 |
+
"learning_rate": 4.7232737459100206e-05,
|
| 937 |
+
"loss": 4.806256866455078,
|
| 938 |
+
"step": 2400
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.5812897366030881,
|
| 942 |
+
"eval_loss": 5.461882591247559,
|
| 943 |
+
"eval_runtime": 482.7564,
|
| 944 |
+
"eval_samples_per_second": 15.204,
|
| 945 |
+
"eval_steps_per_second": 7.602,
|
| 946 |
+
"step": 2400
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.5861338177414471,
|
| 950 |
+
"grad_norm": 0.03340192884206772,
|
| 951 |
+
"learning_rate": 4.7171374287563196e-05,
|
| 952 |
+
"loss": 4.913430786132812,
|
| 953 |
+
"step": 2420
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.5909778988798062,
|
| 957 |
+
"grad_norm": 0.027108795940876007,
|
| 958 |
+
"learning_rate": 4.710937896650763e-05,
|
| 959 |
+
"loss": 4.880179214477539,
|
| 960 |
+
"step": 2440
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.5958219800181653,
|
| 964 |
+
"grad_norm": 0.026677660644054413,
|
| 965 |
+
"learning_rate": 4.704675326354213e-05,
|
| 966 |
+
"loss": 4.978963470458984,
|
| 967 |
+
"step": 2460
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.6006660611565243,
|
| 971 |
+
"grad_norm": 0.023100655525922775,
|
| 972 |
+
"learning_rate": 4.698349896424874e-05,
|
| 973 |
+
"loss": 4.817289352416992,
|
| 974 |
+
"step": 2480
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.6055101422948834,
|
| 978 |
+
"grad_norm": 0.02461540326476097,
|
| 979 |
+
"learning_rate": 4.691961787213204e-05,
|
| 980 |
+
"loss": 4.825991821289063,
|
| 981 |
+
"step": 2500
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.6103542234332425,
|
| 985 |
+
"grad_norm": 0.02112703211605549,
|
| 986 |
+
"learning_rate": 4.68551118085677e-05,
|
| 987 |
+
"loss": 4.912199783325195,
|
| 988 |
+
"step": 2520
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.6151983045716016,
|
| 992 |
+
"grad_norm": 0.028458120301365852,
|
| 993 |
+
"learning_rate": 4.678998261275054e-05,
|
| 994 |
+
"loss": 4.932154846191406,
|
| 995 |
+
"step": 2540
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.6200423857099606,
|
| 999 |
+
"grad_norm": 0.014952564612030983,
|
| 1000 |
+
"learning_rate": 4.6724232141642133e-05,
|
| 1001 |
+
"loss": 4.791392517089844,
|
| 1002 |
+
"step": 2560
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.6248864668483197,
|
| 1006 |
+
"grad_norm": 0.024178558960556984,
|
| 1007 |
+
"learning_rate": 4.6657862269917805e-05,
|
| 1008 |
+
"loss": 4.836280822753906,
|
| 1009 |
+
"step": 2580
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.6297305479866788,
|
| 1013 |
+
"grad_norm": 0.03559703379869461,
|
| 1014 |
+
"learning_rate": 4.659087488991325e-05,
|
| 1015 |
+
"loss": 4.877938842773437,
|
| 1016 |
+
"step": 2600
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.6297305479866788,
|
| 1020 |
+
"eval_loss": 5.461455821990967,
|
| 1021 |
+
"eval_runtime": 477.3623,
|
| 1022 |
+
"eval_samples_per_second": 15.376,
|
| 1023 |
+
"eval_steps_per_second": 7.688,
|
| 1024 |
+
"step": 2600
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.6345746291250378,
|
| 1028 |
+
"grad_norm": 0.0435916930437088,
|
| 1029 |
+
"learning_rate": 4.6523271911570484e-05,
|
| 1030 |
+
"loss": 4.8993488311767575,
|
| 1031 |
+
"step": 2620
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.6394187102633969,
|
| 1035 |
+
"grad_norm": 0.03119947761297226,
|
| 1036 |
+
"learning_rate": 4.6455055262383504e-05,
|
| 1037 |
+
"loss": 4.764545059204101,
|
| 1038 |
+
"step": 2640
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.644262791401756,
|
| 1042 |
+
"grad_norm": 0.0388447642326355,
|
| 1043 |
+
"learning_rate": 4.6386226887343236e-05,
|
| 1044 |
+
"loss": 5.00665283203125,
|
| 1045 |
+
"step": 2660
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.649106872540115,
|
| 1049 |
+
"grad_norm": 0.018733784556388855,
|
| 1050 |
+
"learning_rate": 4.6316788748882114e-05,
|
| 1051 |
+
"loss": 4.9001209259033205,
|
| 1052 |
+
"step": 2680
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.6539509536784741,
|
| 1056 |
+
"grad_norm": 0.03436599299311638,
|
| 1057 |
+
"learning_rate": 4.6246742826818134e-05,
|
| 1058 |
+
"loss": 4.823849868774414,
|
| 1059 |
+
"step": 2700
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6587950348168332,
|
| 1063 |
+
"grad_norm": 0.014111216180026531,
|
| 1064 |
+
"learning_rate": 4.6176091118298406e-05,
|
| 1065 |
+
"loss": 4.89782943725586,
|
| 1066 |
+
"step": 2720
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.6636391159551922,
|
| 1070 |
+
"grad_norm": 0.012464863248169422,
|
| 1071 |
+
"learning_rate": 4.610483563774218e-05,
|
| 1072 |
+
"loss": 4.9627235412597654,
|
| 1073 |
+
"step": 2740
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.6684831970935513,
|
| 1077 |
+
"grad_norm": 0.027146505191922188,
|
| 1078 |
+
"learning_rate": 4.603297841678346e-05,
|
| 1079 |
+
"loss": 4.825485610961914,
|
| 1080 |
+
"step": 2760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.6733272782319104,
|
| 1084 |
+
"grad_norm": 0.025906676426529884,
|
| 1085 |
+
"learning_rate": 4.596052150421306e-05,
|
| 1086 |
+
"loss": 4.924727249145508,
|
| 1087 |
+
"step": 2780
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.6781713593702694,
|
| 1091 |
+
"grad_norm": 0.030369574204087257,
|
| 1092 |
+
"learning_rate": 4.588746696592014e-05,
|
| 1093 |
+
"loss": 4.913991928100586,
|
| 1094 |
+
"step": 2800
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.6781713593702694,
|
| 1098 |
+
"eval_loss": 5.460803508758545,
|
| 1099 |
+
"eval_runtime": 483.5598,
|
| 1100 |
+
"eval_samples_per_second": 15.179,
|
| 1101 |
+
"eval_steps_per_second": 7.59,
|
| 1102 |
+
"step": 2800
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6830154405086285,
|
| 1106 |
+
"grad_norm": 0.01944783516228199,
|
| 1107 |
+
"learning_rate": 4.5813816884833394e-05,
|
| 1108 |
+
"loss": 4.978294754028321,
|
| 1109 |
+
"step": 2820
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.6878595216469876,
|
| 1113 |
+
"grad_norm": 0.023732610046863556,
|
| 1114 |
+
"learning_rate": 4.573957336086157e-05,
|
| 1115 |
+
"loss": 4.956566238403321,
|
| 1116 |
+
"step": 2840
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.6927036027853467,
|
| 1120 |
+
"grad_norm": 0.01582464762032032,
|
| 1121 |
+
"learning_rate": 4.566473851083369e-05,
|
| 1122 |
+
"loss": 4.86058464050293,
|
| 1123 |
+
"step": 2860
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.6975476839237057,
|
| 1127 |
+
"grad_norm": 0.01658930629491806,
|
| 1128 |
+
"learning_rate": 4.558931446843861e-05,
|
| 1129 |
+
"loss": 4.795158386230469,
|
| 1130 |
+
"step": 2880
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.7023917650620648,
|
| 1134 |
+
"grad_norm": 0.0260655265301466,
|
| 1135 |
+
"learning_rate": 4.55133033841642e-05,
|
| 1136 |
+
"loss": 4.9587970733642575,
|
| 1137 |
+
"step": 2900
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.7072358462004239,
|
| 1141 |
+
"grad_norm": 0.021988550201058388,
|
| 1142 |
+
"learning_rate": 4.543670742523611e-05,
|
| 1143 |
+
"loss": 4.91474723815918,
|
| 1144 |
+
"step": 2920
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.7120799273387829,
|
| 1148 |
+
"grad_norm": 0.017105242237448692,
|
| 1149 |
+
"learning_rate": 4.535952877555587e-05,
|
| 1150 |
+
"loss": 4.704911804199218,
|
| 1151 |
+
"step": 2940
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.716924008477142,
|
| 1155 |
+
"grad_norm": 0.018221445381641388,
|
| 1156 |
+
"learning_rate": 4.52817696356387e-05,
|
| 1157 |
+
"loss": 4.996733856201172,
|
| 1158 |
+
"step": 2960
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.7217680896155011,
|
| 1162 |
+
"grad_norm": 0.022833779454231262,
|
| 1163 |
+
"learning_rate": 4.52034322225507e-05,
|
| 1164 |
+
"loss": 4.984310531616211,
|
| 1165 |
+
"step": 2980
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.7266121707538601,
|
| 1169 |
+
"grad_norm": 0.0188573207706213,
|
| 1170 |
+
"learning_rate": 4.5124518769845715e-05,
|
| 1171 |
+
"loss": 4.887367630004883,
|
| 1172 |
+
"step": 3000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.7266121707538601,
|
| 1176 |
+
"eval_loss": 5.459744453430176,
|
| 1177 |
+
"eval_runtime": 482.3857,
|
| 1178 |
+
"eval_samples_per_second": 15.216,
|
| 1179 |
+
"eval_steps_per_second": 7.608,
|
| 1180 |
+
"step": 3000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.7314562518922192,
|
| 1184 |
+
"grad_norm": 0.033990390598773956,
|
| 1185 |
+
"learning_rate": 4.5045031527501604e-05,
|
| 1186 |
+
"loss": 4.899966049194336,
|
| 1187 |
+
"step": 3020
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.7363003330305783,
|
| 1191 |
+
"grad_norm": 0.02148909866809845,
|
| 1192 |
+
"learning_rate": 4.4964972761856084e-05,
|
| 1193 |
+
"loss": 4.8198493957519535,
|
| 1194 |
+
"step": 3040
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.7411444141689373,
|
| 1198 |
+
"grad_norm": 0.019260123372077942,
|
| 1199 |
+
"learning_rate": 4.4884344755542134e-05,
|
| 1200 |
+
"loss": 4.738033294677734,
|
| 1201 |
+
"step": 3060
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.7459884953072964,
|
| 1205 |
+
"grad_norm": 0.024531004950404167,
|
| 1206 |
+
"learning_rate": 4.480314980742291e-05,
|
| 1207 |
+
"loss": 4.879784774780274,
|
| 1208 |
+
"step": 3080
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.7508325764456555,
|
| 1212 |
+
"grad_norm": 0.022741004824638367,
|
| 1213 |
+
"learning_rate": 4.472139023252619e-05,
|
| 1214 |
+
"loss": 4.864042663574219,
|
| 1215 |
+
"step": 3100
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.7556766575840145,
|
| 1219 |
+
"grad_norm": 0.03277403116226196,
|
| 1220 |
+
"learning_rate": 4.4639068361978375e-05,
|
| 1221 |
+
"loss": 4.944465255737304,
|
| 1222 |
+
"step": 3120
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.7605207387223736,
|
| 1226 |
+
"grad_norm": 0.01316901296377182,
|
| 1227 |
+
"learning_rate": 4.455618654293801e-05,
|
| 1228 |
+
"loss": 4.936913299560547,
|
| 1229 |
+
"step": 3140
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.7653648198607327,
|
| 1233 |
+
"grad_norm": 0.017750350758433342,
|
| 1234 |
+
"learning_rate": 4.44727471385289e-05,
|
| 1235 |
+
"loss": 4.916695785522461,
|
| 1236 |
+
"step": 3160
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.7702089009990918,
|
| 1240 |
+
"grad_norm": 0.024009494110941887,
|
| 1241 |
+
"learning_rate": 4.4388752527772677e-05,
|
| 1242 |
+
"loss": 4.825696182250977,
|
| 1243 |
+
"step": 3180
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.7750529821374508,
|
| 1247 |
+
"grad_norm": 0.019279325380921364,
|
| 1248 |
+
"learning_rate": 4.4304205105521015e-05,
|
| 1249 |
+
"loss": 4.900424575805664,
|
| 1250 |
+
"step": 3200
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.7750529821374508,
|
| 1254 |
+
"eval_loss": 5.454287528991699,
|
| 1255 |
+
"eval_runtime": 483.1463,
|
| 1256 |
+
"eval_samples_per_second": 15.192,
|
| 1257 |
+
"eval_steps_per_second": 7.596,
|
| 1258 |
+
"step": 3200
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.7798970632758099,
|
| 1262 |
+
"grad_norm": 0.011572799645364285,
|
| 1263 |
+
"learning_rate": 4.421910728238733e-05,
|
| 1264 |
+
"loss": 4.900468826293945,
|
| 1265 |
+
"step": 3220
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.784741144414169,
|
| 1269 |
+
"grad_norm": 0.022734951227903366,
|
| 1270 |
+
"learning_rate": 4.413346148467804e-05,
|
| 1271 |
+
"loss": 4.889355850219727,
|
| 1272 |
+
"step": 3240
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.789585225552528,
|
| 1276 |
+
"grad_norm": 0.010450748726725578,
|
| 1277 |
+
"learning_rate": 4.4047270154323425e-05,
|
| 1278 |
+
"loss": 4.801429748535156,
|
| 1279 |
+
"step": 3260
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.7944293066908871,
|
| 1283 |
+
"grad_norm": 0.02443559840321541,
|
| 1284 |
+
"learning_rate": 4.396053574880794e-05,
|
| 1285 |
+
"loss": 4.850070190429688,
|
| 1286 |
+
"step": 3280
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.7992733878292462,
|
| 1290 |
+
"grad_norm": 0.01849784515798092,
|
| 1291 |
+
"learning_rate": 4.38732607411002e-05,
|
| 1292 |
+
"loss": 4.954670333862305,
|
| 1293 |
+
"step": 3300
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.8041174689676052,
|
| 1297 |
+
"grad_norm": 0.018099434673786163,
|
| 1298 |
+
"learning_rate": 4.378544761958244e-05,
|
| 1299 |
+
"loss": 4.958530044555664,
|
| 1300 |
+
"step": 3320
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.8089615501059643,
|
| 1304 |
+
"grad_norm": 0.027655702084302902,
|
| 1305 |
+
"learning_rate": 4.36970988879796e-05,
|
| 1306 |
+
"loss": 5.005998611450195,
|
| 1307 |
+
"step": 3340
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.8138056312443234,
|
| 1311 |
+
"grad_norm": 0.01677539013326168,
|
| 1312 |
+
"learning_rate": 4.3608217065287904e-05,
|
| 1313 |
+
"loss": 4.924520874023438,
|
| 1314 |
+
"step": 3360
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.8186497123826824,
|
| 1318 |
+
"grad_norm": 0.03358837217092514,
|
| 1319 |
+
"learning_rate": 4.351880468570305e-05,
|
| 1320 |
+
"loss": 4.904378128051758,
|
| 1321 |
+
"step": 3380
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.8234937935210415,
|
| 1325 |
+
"grad_norm": 0.02544589340686798,
|
| 1326 |
+
"learning_rate": 4.3428864298547965e-05,
|
| 1327 |
+
"loss": 4.933415222167969,
|
| 1328 |
+
"step": 3400
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.8234937935210415,
|
| 1332 |
+
"eval_loss": 5.461795330047607,
|
| 1333 |
+
"eval_runtime": 483.8187,
|
| 1334 |
+
"eval_samples_per_second": 15.171,
|
| 1335 |
+
"eval_steps_per_second": 7.585,
|
| 1336 |
+
"step": 3400
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.8283378746594006,
|
| 1340 |
+
"grad_norm": 0.023529496043920517,
|
| 1341 |
+
"learning_rate": 4.3338398468200104e-05,
|
| 1342 |
+
"loss": 4.9913169860839846,
|
| 1343 |
+
"step": 3420
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.8331819557977597,
|
| 1347 |
+
"grad_norm": 0.014854267239570618,
|
| 1348 |
+
"learning_rate": 4.324740977401834e-05,
|
| 1349 |
+
"loss": 4.914155960083008,
|
| 1350 |
+
"step": 3440
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.8380260369361187,
|
| 1354 |
+
"grad_norm": 0.028307568281888962,
|
| 1355 |
+
"learning_rate": 4.3155900810269445e-05,
|
| 1356 |
+
"loss": 4.852661514282227,
|
| 1357 |
+
"step": 3460
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.8428701180744778,
|
| 1361 |
+
"grad_norm": 0.017718417569994926,
|
| 1362 |
+
"learning_rate": 4.306387418605407e-05,
|
| 1363 |
+
"loss": 4.959287643432617,
|
| 1364 |
+
"step": 3480
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.8477141992128369,
|
| 1368 |
+
"grad_norm": 0.01476296130567789,
|
| 1369 |
+
"learning_rate": 4.297133252523239e-05,
|
| 1370 |
+
"loss": 4.727375411987305,
|
| 1371 |
+
"step": 3500
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.8525582803511959,
|
| 1375 |
+
"grad_norm": 0.024725649505853653,
|
| 1376 |
+
"learning_rate": 4.2878278466349316e-05,
|
| 1377 |
+
"loss": 4.893677520751953,
|
| 1378 |
+
"step": 3520
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.857402361489555,
|
| 1382 |
+
"grad_norm": 0.01822960376739502,
|
| 1383 |
+
"learning_rate": 4.27847146625592e-05,
|
| 1384 |
+
"loss": 4.89503288269043,
|
| 1385 |
+
"step": 3540
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.8622464426279141,
|
| 1389 |
+
"grad_norm": 0.026599068194627762,
|
| 1390 |
+
"learning_rate": 4.2690643781550245e-05,
|
| 1391 |
+
"loss": 4.930253219604492,
|
| 1392 |
+
"step": 3560
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.867090523766273,
|
| 1396 |
+
"grad_norm": 0.0182630755007267,
|
| 1397 |
+
"learning_rate": 4.259606850546841e-05,
|
| 1398 |
+
"loss": 4.800619888305664,
|
| 1399 |
+
"step": 3580
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.8719346049046321,
|
| 1403 |
+
"grad_norm": 0.015945954248309135,
|
| 1404 |
+
"learning_rate": 4.250099153084097e-05,
|
| 1405 |
+
"loss": 4.828668594360352,
|
| 1406 |
+
"step": 3600
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.8719346049046321,
|
| 1410 |
+
"eval_loss": 5.460173606872559,
|
| 1411 |
+
"eval_runtime": 484.3695,
|
| 1412 |
+
"eval_samples_per_second": 15.154,
|
| 1413 |
+
"eval_steps_per_second": 7.577,
|
| 1414 |
+
"step": 3600
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 0.8767786860429913,
|
| 1418 |
+
"grad_norm": 0.014371720142662525,
|
| 1419 |
+
"learning_rate": 4.240541556849961e-05,
|
| 1420 |
+
"loss": 4.865261459350586,
|
| 1421 |
+
"step": 3620
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 0.8816227671813502,
|
| 1425 |
+
"grad_norm": 0.01884741522371769,
|
| 1426 |
+
"learning_rate": 4.23093433435031e-05,
|
| 1427 |
+
"loss": 4.983065032958985,
|
| 1428 |
+
"step": 3640
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.8864668483197093,
|
| 1432 |
+
"grad_norm": 0.0102775227278471,
|
| 1433 |
+
"learning_rate": 4.221277759505968e-05,
|
| 1434 |
+
"loss": 4.936088943481446,
|
| 1435 |
+
"step": 3660
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.8913109294580684,
|
| 1439 |
+
"grad_norm": 0.02810431458055973,
|
| 1440 |
+
"learning_rate": 4.211572107644891e-05,
|
| 1441 |
+
"loss": 4.9662517547607425,
|
| 1442 |
+
"step": 3680
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.8961550105964274,
|
| 1446 |
+
"grad_norm": 0.014943272806704044,
|
| 1447 |
+
"learning_rate": 4.201817655494315e-05,
|
| 1448 |
+
"loss": 4.909831237792969,
|
| 1449 |
+
"step": 3700
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.9009990917347865,
|
| 1453 |
+
"grad_norm": 0.018770508468151093,
|
| 1454 |
+
"learning_rate": 4.192014681172869e-05,
|
| 1455 |
+
"loss": 4.761404418945313,
|
| 1456 |
+
"step": 3720
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.9058431728731456,
|
| 1460 |
+
"grad_norm": 0.01450326107442379,
|
| 1461 |
+
"learning_rate": 4.182163464182646e-05,
|
| 1462 |
+
"loss": 4.860451507568359,
|
| 1463 |
+
"step": 3740
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.9106872540115047,
|
| 1467 |
+
"grad_norm": 0.010839094407856464,
|
| 1468 |
+
"learning_rate": 4.172264285401232e-05,
|
| 1469 |
+
"loss": 4.847282028198242,
|
| 1470 |
+
"step": 3760
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.9155313351498637,
|
| 1474 |
+
"grad_norm": 0.009730652906000614,
|
| 1475 |
+
"learning_rate": 4.162317427073695e-05,
|
| 1476 |
+
"loss": 4.987754821777344,
|
| 1477 |
+
"step": 3780
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.9203754162882228,
|
| 1481 |
+
"grad_norm": 0.010914390906691551,
|
| 1482 |
+
"learning_rate": 4.1523231728045466e-05,
|
| 1483 |
+
"loss": 4.858595657348633,
|
| 1484 |
+
"step": 3800
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.9203754162882228,
|
| 1488 |
+
"eval_loss": 5.4581074714660645,
|
| 1489 |
+
"eval_runtime": 490.4204,
|
| 1490 |
+
"eval_samples_per_second": 14.967,
|
| 1491 |
+
"eval_steps_per_second": 7.483,
|
| 1492 |
+
"step": 3800
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.9252194974265819,
|
| 1496 |
+
"grad_norm": 0.017502611503005028,
|
| 1497 |
+
"learning_rate": 4.142281807549644e-05,
|
| 1498 |
+
"loss": 4.870289611816406,
|
| 1499 |
+
"step": 3820
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.9300635785649409,
|
| 1503 |
+
"grad_norm": 0.017291737720370293,
|
| 1504 |
+
"learning_rate": 4.1321936176080755e-05,
|
| 1505 |
+
"loss": 4.889853286743164,
|
| 1506 |
+
"step": 3840
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.9349076597033,
|
| 1510 |
+
"grad_norm": 0.017816677689552307,
|
| 1511 |
+
"learning_rate": 4.122058890613991e-05,
|
| 1512 |
+
"loss": 4.910069274902344,
|
| 1513 |
+
"step": 3860
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.9397517408416591,
|
| 1517 |
+
"grad_norm": 0.027295643463730812,
|
| 1518 |
+
"learning_rate": 4.111877915528406e-05,
|
| 1519 |
+
"loss": 5.048255538940429,
|
| 1520 |
+
"step": 3880
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 0.9445958219800181,
|
| 1524 |
+
"grad_norm": 0.035314708948135376,
|
| 1525 |
+
"learning_rate": 4.101650982630956e-05,
|
| 1526 |
+
"loss": 4.915079498291016,
|
| 1527 |
+
"step": 3900
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.9494399031183772,
|
| 1531 |
+
"grad_norm": 0.01960872672498226,
|
| 1532 |
+
"learning_rate": 4.091378383511628e-05,
|
| 1533 |
+
"loss": 4.810525894165039,
|
| 1534 |
+
"step": 3920
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 0.9542839842567363,
|
| 1538 |
+
"grad_norm": 0.013185371644794941,
|
| 1539 |
+
"learning_rate": 4.08106041106244e-05,
|
| 1540 |
+
"loss": 4.84496841430664,
|
| 1541 |
+
"step": 3940
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.9591280653950953,
|
| 1545 |
+
"grad_norm": 0.020618990063667297,
|
| 1546 |
+
"learning_rate": 4.0706973594690964e-05,
|
| 1547 |
+
"loss": 4.8005413055419925,
|
| 1548 |
+
"step": 3960
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 0.9639721465334544,
|
| 1552 |
+
"grad_norm": 0.016433637589216232,
|
| 1553 |
+
"learning_rate": 4.060289524202594e-05,
|
| 1554 |
+
"loss": 4.936908721923828,
|
| 1555 |
+
"step": 3980
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.9688162276718135,
|
| 1559 |
+
"grad_norm": 0.020894834771752357,
|
| 1560 |
+
"learning_rate": 4.0498372020108e-05,
|
| 1561 |
+
"loss": 4.909790802001953,
|
| 1562 |
+
"step": 4000
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.9688162276718135,
|
| 1566 |
+
"eval_loss": 5.458165168762207,
|
| 1567 |
+
"eval_runtime": 480.7799,
|
| 1568 |
+
"eval_samples_per_second": 15.267,
|
| 1569 |
+
"eval_steps_per_second": 7.633,
|
| 1570 |
+
"step": 4000
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.9736603088101726,
|
| 1574 |
+
"grad_norm": 0.016745753586292267,
|
| 1575 |
+
"learning_rate": 4.0393406909099925e-05,
|
| 1576 |
+
"loss": 4.82120361328125,
|
| 1577 |
+
"step": 4020
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.9785043899485316,
|
| 1581 |
+
"grad_norm": 0.018331704661250114,
|
| 1582 |
+
"learning_rate": 4.028800290176362e-05,
|
| 1583 |
+
"loss": 4.880381393432617,
|
| 1584 |
+
"step": 4040
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.9833484710868907,
|
| 1588 |
+
"grad_norm": 0.023544512689113617,
|
| 1589 |
+
"learning_rate": 4.01821630033748e-05,
|
| 1590 |
+
"loss": 4.834738922119141,
|
| 1591 |
+
"step": 4060
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.9881925522252498,
|
| 1595 |
+
"grad_norm": 0.020899208262562752,
|
| 1596 |
+
"learning_rate": 4.007589023163727e-05,
|
| 1597 |
+
"loss": 4.852277374267578,
|
| 1598 |
+
"step": 4080
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.9930366333636088,
|
| 1602 |
+
"grad_norm": 0.013782848604023457,
|
| 1603 |
+
"learning_rate": 3.996918761659694e-05,
|
| 1604 |
+
"loss": 4.841725921630859,
|
| 1605 |
+
"step": 4100
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.9978807145019679,
|
| 1609 |
+
"grad_norm": 0.018252292647957802,
|
| 1610 |
+
"learning_rate": 3.986205820055534e-05,
|
| 1611 |
+
"loss": 4.945264434814453,
|
| 1612 |
+
"step": 4120
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 1.0026642446260974,
|
| 1616 |
+
"grad_norm": 0.019553977996110916,
|
| 1617 |
+
"learning_rate": 3.9754505037983004e-05,
|
| 1618 |
+
"loss": 4.959503555297852,
|
| 1619 |
+
"step": 4140
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.0075083257644566,
|
| 1623 |
+
"grad_norm": 0.015189483761787415,
|
| 1624 |
+
"learning_rate": 3.964653119543227e-05,
|
| 1625 |
+
"loss": 4.9404754638671875,
|
| 1626 |
+
"step": 4160
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.0123524069028156,
|
| 1630 |
+
"grad_norm": 0.06231527775526047,
|
| 1631 |
+
"learning_rate": 3.953813975144991e-05,
|
| 1632 |
+
"loss": 4.842787551879883,
|
| 1633 |
+
"step": 4180
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.0171964880411748,
|
| 1637 |
+
"grad_norm": 0.01840846799314022,
|
| 1638 |
+
"learning_rate": 3.942933379648932e-05,
|
| 1639 |
+
"loss": 4.911764144897461,
|
| 1640 |
+
"step": 4200
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.0171964880411748,
|
| 1644 |
+
"eval_loss": 5.460827827453613,
|
| 1645 |
+
"eval_runtime": 484.9137,
|
| 1646 |
+
"eval_samples_per_second": 15.137,
|
| 1647 |
+
"eval_steps_per_second": 7.568,
|
| 1648 |
+
"step": 4200
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.0220405691795338,
|
| 1652 |
+
"grad_norm": 0.021854782477021217,
|
| 1653 |
+
"learning_rate": 3.932011643282243e-05,
|
| 1654 |
+
"loss": 4.853986358642578,
|
| 1655 |
+
"step": 4220
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.0268846503178928,
|
| 1659 |
+
"grad_norm": 0.017591115087270737,
|
| 1660 |
+
"learning_rate": 3.9210490774451235e-05,
|
| 1661 |
+
"loss": 4.8760326385498045,
|
| 1662 |
+
"step": 4240
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.031728731456252,
|
| 1666 |
+
"grad_norm": 0.03734872490167618,
|
| 1667 |
+
"learning_rate": 3.910045994701903e-05,
|
| 1668 |
+
"loss": 4.93592529296875,
|
| 1669 |
+
"step": 4260
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.036572812594611,
|
| 1673 |
+
"grad_norm": 0.009241367690265179,
|
| 1674 |
+
"learning_rate": 3.899002708772126e-05,
|
| 1675 |
+
"loss": 4.926780700683594,
|
| 1676 |
+
"step": 4280
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.04141689373297,
|
| 1680 |
+
"grad_norm": 0.01902877353131771,
|
| 1681 |
+
"learning_rate": 3.88791953452161e-05,
|
| 1682 |
+
"loss": 5.037494277954101,
|
| 1683 |
+
"step": 4300
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.0462609748713292,
|
| 1687 |
+
"grad_norm": 0.02036813460290432,
|
| 1688 |
+
"learning_rate": 3.876796787953466e-05,
|
| 1689 |
+
"loss": 4.970469665527344,
|
| 1690 |
+
"step": 4320
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.0511050560096882,
|
| 1694 |
+
"grad_norm": 0.012490912340581417,
|
| 1695 |
+
"learning_rate": 3.865634786199092e-05,
|
| 1696 |
+
"loss": 4.780771636962891,
|
| 1697 |
+
"step": 4340
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.0559491371480472,
|
| 1701 |
+
"grad_norm": 0.020513946190476418,
|
| 1702 |
+
"learning_rate": 3.854433847509126e-05,
|
| 1703 |
+
"loss": 4.8549247741699215,
|
| 1704 |
+
"step": 4360
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.0607932182864064,
|
| 1708 |
+
"grad_norm": 0.018364248797297478,
|
| 1709 |
+
"learning_rate": 3.8431942912443754e-05,
|
| 1710 |
+
"loss": 4.861563873291016,
|
| 1711 |
+
"step": 4380
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.0656372994247654,
|
| 1715 |
+
"grad_norm": 0.014563582837581635,
|
| 1716 |
+
"learning_rate": 3.831916437866711e-05,
|
| 1717 |
+
"loss": 4.935742568969727,
|
| 1718 |
+
"step": 4400
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.0656372994247654,
|
| 1722 |
+
"eval_loss": 5.46129035949707,
|
| 1723 |
+
"eval_runtime": 488.8363,
|
| 1724 |
+
"eval_samples_per_second": 15.015,
|
| 1725 |
+
"eval_steps_per_second": 7.508,
|
| 1726 |
+
"step": 4400
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 1.0704813805631244,
|
| 1730 |
+
"grad_norm": 0.013871117495000362,
|
| 1731 |
+
"learning_rate": 3.82060060892993e-05,
|
| 1732 |
+
"loss": 4.791946792602539,
|
| 1733 |
+
"step": 4420
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 1.0753254617014836,
|
| 1737 |
+
"grad_norm": 0.016447104513645172,
|
| 1738 |
+
"learning_rate": 3.809247127070588e-05,
|
| 1739 |
+
"loss": 4.91345443725586,
|
| 1740 |
+
"step": 4440
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 1.0801695428398426,
|
| 1744 |
+
"grad_norm": 0.01683361642062664,
|
| 1745 |
+
"learning_rate": 3.797856315998797e-05,
|
| 1746 |
+
"loss": 4.959566116333008,
|
| 1747 |
+
"step": 4460
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 1.0850136239782016,
|
| 1751 |
+
"grad_norm": 0.013085919432342052,
|
| 1752 |
+
"learning_rate": 3.786428500489001e-05,
|
| 1753 |
+
"loss": 4.8983619689941404,
|
| 1754 |
+
"step": 4480
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 1.0898577051165608,
|
| 1758 |
+
"grad_norm": 0.009764457121491432,
|
| 1759 |
+
"learning_rate": 3.7749640063707115e-05,
|
| 1760 |
+
"loss": 4.951383209228515,
|
| 1761 |
+
"step": 4500
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 1.0947017862549198,
|
| 1765 |
+
"grad_norm": 0.015614672563970089,
|
| 1766 |
+
"learning_rate": 3.763463160519222e-05,
|
| 1767 |
+
"loss": 4.869015502929687,
|
| 1768 |
+
"step": 4520
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 1.0995458673932788,
|
| 1772 |
+
"grad_norm": 0.024334661662578583,
|
| 1773 |
+
"learning_rate": 3.751926290846282e-05,
|
| 1774 |
+
"loss": 4.924750137329101,
|
| 1775 |
+
"step": 4540
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 1.104389948531638,
|
| 1779 |
+
"grad_norm": 0.03006790392100811,
|
| 1780 |
+
"learning_rate": 3.740353726290753e-05,
|
| 1781 |
+
"loss": 4.894016265869141,
|
| 1782 |
+
"step": 4560
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 1.109234029669997,
|
| 1786 |
+
"grad_norm": 0.016674896702170372,
|
| 1787 |
+
"learning_rate": 3.7287457968092286e-05,
|
| 1788 |
+
"loss": 4.868609237670898,
|
| 1789 |
+
"step": 4580
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 1.114078110808356,
|
| 1793 |
+
"grad_norm": 0.01684091053903103,
|
| 1794 |
+
"learning_rate": 3.717102833366624e-05,
|
| 1795 |
+
"loss": 4.794527816772461,
|
| 1796 |
+
"step": 4600
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 1.114078110808356,
|
| 1800 |
+
"eval_loss": 5.460610389709473,
|
| 1801 |
+
"eval_runtime": 482.5493,
|
| 1802 |
+
"eval_samples_per_second": 15.211,
|
| 1803 |
+
"eval_steps_per_second": 7.605,
|
| 1804 |
+
"step": 4600
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 1.1189221919467152,
|
| 1808 |
+
"grad_norm": 0.007340766489505768,
|
| 1809 |
+
"learning_rate": 3.705425167926743e-05,
|
| 1810 |
+
"loss": 4.731179046630859,
|
| 1811 |
+
"step": 4620
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 1.1237662730850742,
|
| 1815 |
+
"grad_norm": 0.014017272740602493,
|
| 1816 |
+
"learning_rate": 3.69371313344281e-05,
|
| 1817 |
+
"loss": 5.037481307983398,
|
| 1818 |
+
"step": 4640
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 1.1286103542234334,
|
| 1822 |
+
"grad_norm": 0.01410000678151846,
|
| 1823 |
+
"learning_rate": 3.681967063847981e-05,
|
| 1824 |
+
"loss": 4.686013793945312,
|
| 1825 |
+
"step": 4660
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 1.1334544353617924,
|
| 1829 |
+
"grad_norm": 0.0066877431236207485,
|
| 1830 |
+
"learning_rate": 3.6701872940458186e-05,
|
| 1831 |
+
"loss": 4.932219696044922,
|
| 1832 |
+
"step": 4680
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 1.1382985165001513,
|
| 1836 |
+
"grad_norm": 0.01702740788459778,
|
| 1837 |
+
"learning_rate": 3.658374159900744e-05,
|
| 1838 |
+
"loss": 4.854273986816406,
|
| 1839 |
+
"step": 4700
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 1.1431425976385103,
|
| 1843 |
+
"grad_norm": 0.014306023716926575,
|
| 1844 |
+
"learning_rate": 3.646527998228464e-05,
|
| 1845 |
+
"loss": 4.978992462158203,
|
| 1846 |
+
"step": 4720
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 1.1479866787768696,
|
| 1850 |
+
"grad_norm": 0.013222994282841682,
|
| 1851 |
+
"learning_rate": 3.634649146786361e-05,
|
| 1852 |
+
"loss": 4.848846817016602,
|
| 1853 |
+
"step": 4740
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 1.1528307599152285,
|
| 1857 |
+
"grad_norm": 0.005920600611716509,
|
| 1858 |
+
"learning_rate": 3.622737944263872e-05,
|
| 1859 |
+
"loss": 4.912345123291016,
|
| 1860 |
+
"step": 4760
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 1.1576748410535878,
|
| 1864 |
+
"grad_norm": 0.013458259403705597,
|
| 1865 |
+
"learning_rate": 3.6107947302728236e-05,
|
| 1866 |
+
"loss": 4.936886596679687,
|
| 1867 |
+
"step": 4780
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 1.1625189221919467,
|
| 1871 |
+
"grad_norm": 0.013781394809484482,
|
| 1872 |
+
"learning_rate": 3.598819845337752e-05,
|
| 1873 |
+
"loss": 4.750154113769531,
|
| 1874 |
+
"step": 4800
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 1.1625189221919467,
|
| 1878 |
+
"eval_loss": 5.460769176483154,
|
| 1879 |
+
"eval_runtime": 482.0557,
|
| 1880 |
+
"eval_samples_per_second": 15.226,
|
| 1881 |
+
"eval_steps_per_second": 7.613,
|
| 1882 |
+
"step": 4800
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 1.1673630033303057,
|
| 1886 |
+
"grad_norm": 0.014957944862544537,
|
| 1887 |
+
"learning_rate": 3.5868136308861973e-05,
|
| 1888 |
+
"loss": 4.829911804199218,
|
| 1889 |
+
"step": 4820
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 1.1722070844686647,
|
| 1893 |
+
"grad_norm": 0.016118552535772324,
|
| 1894 |
+
"learning_rate": 3.5747764292389626e-05,
|
| 1895 |
+
"loss": 4.940299606323242,
|
| 1896 |
+
"step": 4840
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 1.177051165607024,
|
| 1900 |
+
"grad_norm": 0.01738092489540577,
|
| 1901 |
+
"learning_rate": 3.56270858360036e-05,
|
| 1902 |
+
"loss": 4.805704116821289,
|
| 1903 |
+
"step": 4860
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 1.181895246745383,
|
| 1907 |
+
"grad_norm": 0.013412545435130596,
|
| 1908 |
+
"learning_rate": 3.550610438048419e-05,
|
| 1909 |
+
"loss": 4.848656463623047,
|
| 1910 |
+
"step": 4880
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 1.1867393278837421,
|
| 1914 |
+
"grad_norm": 0.020154351368546486,
|
| 1915 |
+
"learning_rate": 3.5384823375250825e-05,
|
| 1916 |
+
"loss": 4.836146545410156,
|
| 1917 |
+
"step": 4900
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 1.1915834090221011,
|
| 1921 |
+
"grad_norm": 0.012981275096535683,
|
| 1922 |
+
"learning_rate": 3.526324627826366e-05,
|
| 1923 |
+
"loss": 4.94176139831543,
|
| 1924 |
+
"step": 4920
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 1.1964274901604601,
|
| 1928 |
+
"grad_norm": 0.02052425593137741,
|
| 1929 |
+
"learning_rate": 3.514137655592501e-05,
|
| 1930 |
+
"loss": 4.940605545043946,
|
| 1931 |
+
"step": 4940
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 1.2012715712988193,
|
| 1935 |
+
"grad_norm": 0.009783861227333546,
|
| 1936 |
+
"learning_rate": 3.501921768298054e-05,
|
| 1937 |
+
"loss": 4.762470245361328,
|
| 1938 |
+
"step": 4960
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 1.2061156524371783,
|
| 1942 |
+
"grad_norm": 0.01635117270052433,
|
| 1943 |
+
"learning_rate": 3.4896773142420134e-05,
|
| 1944 |
+
"loss": 4.848318099975586,
|
| 1945 |
+
"step": 4980
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 1.2109597335755373,
|
| 1949 |
+
"grad_norm": 0.013676351867616177,
|
| 1950 |
+
"learning_rate": 3.477404642537865e-05,
|
| 1951 |
+
"loss": 4.775520324707031,
|
| 1952 |
+
"step": 5000
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 1.2109597335755373,
|
| 1956 |
+
"eval_loss": 5.459352493286133,
|
| 1957 |
+
"eval_runtime": 481.9172,
|
| 1958 |
+
"eval_samples_per_second": 15.231,
|
| 1959 |
+
"eval_steps_per_second": 7.615,
|
| 1960 |
+
"step": 5000
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 1.2158038147138965,
|
| 1964 |
+
"grad_norm": 0.025599844753742218,
|
| 1965 |
+
"learning_rate": 3.465104103103633e-05,
|
| 1966 |
+
"loss": 5.030489730834961,
|
| 1967 |
+
"step": 5020
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 1.2206478958522555,
|
| 1971 |
+
"grad_norm": 0.010839181020855904,
|
| 1972 |
+
"learning_rate": 3.4527760466519065e-05,
|
| 1973 |
+
"loss": 4.919123840332031,
|
| 1974 |
+
"step": 5040
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 1.2254919769906145,
|
| 1978 |
+
"grad_norm": 0.01727098785340786,
|
| 1979 |
+
"learning_rate": 3.440420824679841e-05,
|
| 1980 |
+
"loss": 4.916360092163086,
|
| 1981 |
+
"step": 5060
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 1.2303360581289737,
|
| 1985 |
+
"grad_norm": 0.015268294140696526,
|
| 1986 |
+
"learning_rate": 3.42803878945913e-05,
|
| 1987 |
+
"loss": 4.849533462524414,
|
| 1988 |
+
"step": 5080
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 1.2351801392673327,
|
| 1992 |
+
"grad_norm": 0.017013756558299065,
|
| 1993 |
+
"learning_rate": 3.4156302940259707e-05,
|
| 1994 |
+
"loss": 4.718303680419922,
|
| 1995 |
+
"step": 5100
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 1.2400242204056917,
|
| 1999 |
+
"grad_norm": 0.016048861667513847,
|
| 2000 |
+
"learning_rate": 3.403195692170987e-05,
|
| 2001 |
+
"loss": 4.887918090820312,
|
| 2002 |
+
"step": 5120
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 1.244868301544051,
|
| 2006 |
+
"grad_norm": 0.018063582479953766,
|
| 2007 |
+
"learning_rate": 3.390735338429153e-05,
|
| 2008 |
+
"loss": 4.8720966339111325,
|
| 2009 |
+
"step": 5140
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 1.24971238268241,
|
| 2013 |
+
"grad_norm": 0.020126111805438995,
|
| 2014 |
+
"learning_rate": 3.378249588069679e-05,
|
| 2015 |
+
"loss": 4.978098297119141,
|
| 2016 |
+
"step": 5160
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 1.254556463820769,
|
| 2020 |
+
"grad_norm": 0.013375598937273026,
|
| 2021 |
+
"learning_rate": 3.365738797085881e-05,
|
| 2022 |
+
"loss": 4.952982330322266,
|
| 2023 |
+
"step": 5180
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 1.2594005449591281,
|
| 2027 |
+
"grad_norm": 0.015132354572415352,
|
| 2028 |
+
"learning_rate": 3.353203322185035e-05,
|
| 2029 |
+
"loss": 4.908714294433594,
|
| 2030 |
+
"step": 5200
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 1.2594005449591281,
|
| 2034 |
+
"eval_loss": 5.45740270614624,
|
| 2035 |
+
"eval_runtime": 481.4693,
|
| 2036 |
+
"eval_samples_per_second": 15.245,
|
| 2037 |
+
"eval_steps_per_second": 7.623,
|
| 2038 |
+
"step": 5200
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 1.2642446260974871,
|
| 2042 |
+
"grad_norm": 0.012495392933487892,
|
| 2043 |
+
"learning_rate": 3.340643520778201e-05,
|
| 2044 |
+
"loss": 4.851836776733398,
|
| 2045 |
+
"step": 5220
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 1.2690887072358463,
|
| 2049 |
+
"grad_norm": 0.01966176927089691,
|
| 2050 |
+
"learning_rate": 3.328059750970038e-05,
|
| 2051 |
+
"loss": 4.94261474609375,
|
| 2052 |
+
"step": 5240
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 1.2739327883742053,
|
| 2056 |
+
"grad_norm": 0.022419588640332222,
|
| 2057 |
+
"learning_rate": 3.315452371548592e-05,
|
| 2058 |
+
"loss": 4.894690704345703,
|
| 2059 |
+
"step": 5260
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 1.2787768695125643,
|
| 2063 |
+
"grad_norm": 0.008414322510361671,
|
| 2064 |
+
"learning_rate": 3.302821741975061e-05,
|
| 2065 |
+
"loss": 4.914752197265625,
|
| 2066 |
+
"step": 5280
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 1.2836209506509233,
|
| 2070 |
+
"grad_norm": 0.014880464412271976,
|
| 2071 |
+
"learning_rate": 3.290168222373557e-05,
|
| 2072 |
+
"loss": 4.73625602722168,
|
| 2073 |
+
"step": 5300
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 1.2884650317892825,
|
| 2077 |
+
"grad_norm": 0.012800327502191067,
|
| 2078 |
+
"learning_rate": 3.2774921735208255e-05,
|
| 2079 |
+
"loss": 4.73109245300293,
|
| 2080 |
+
"step": 5320
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 1.2933091129276415,
|
| 2084 |
+
"grad_norm": 0.0207191351801157,
|
| 2085 |
+
"learning_rate": 3.26479395683597e-05,
|
| 2086 |
+
"loss": 4.839684295654297,
|
| 2087 |
+
"step": 5340
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 1.2981531940660007,
|
| 2091 |
+
"grad_norm": 0.016082677990198135,
|
| 2092 |
+
"learning_rate": 3.2520739343701415e-05,
|
| 2093 |
+
"loss": 4.872611999511719,
|
| 2094 |
+
"step": 5360
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 1.3029972752043597,
|
| 2098 |
+
"grad_norm": 0.012835017405450344,
|
| 2099 |
+
"learning_rate": 3.2393324687962145e-05,
|
| 2100 |
+
"loss": 4.883394241333008,
|
| 2101 |
+
"step": 5380
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 1.3078413563427187,
|
| 2105 |
+
"grad_norm": 0.01141536794602871,
|
| 2106 |
+
"learning_rate": 3.2265699233984506e-05,
|
| 2107 |
+
"loss": 4.8918407440185545,
|
| 2108 |
+
"step": 5400
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 1.3078413563427187,
|
| 2112 |
+
"eval_loss": 5.4619011878967285,
|
| 2113 |
+
"eval_runtime": 484.2168,
|
| 2114 |
+
"eval_samples_per_second": 15.158,
|
| 2115 |
+
"eval_steps_per_second": 7.579,
|
| 2116 |
+
"step": 5400
|
| 2117 |
+
}
|
| 2118 |
+
],
|
| 2119 |
+
"logging_steps": 20,
|
| 2120 |
+
"max_steps": 12387,
|
| 2121 |
+
"num_input_tokens_seen": 0,
|
| 2122 |
+
"num_train_epochs": 3,
|
| 2123 |
+
"save_steps": 200,
|
| 2124 |
+
"stateful_callbacks": {
|
| 2125 |
+
"TrainerControl": {
|
| 2126 |
+
"args": {
|
| 2127 |
+
"should_epoch_stop": false,
|
| 2128 |
+
"should_evaluate": false,
|
| 2129 |
+
"should_log": false,
|
| 2130 |
+
"should_save": true,
|
| 2131 |
+
"should_training_stop": false
|
| 2132 |
+
},
|
| 2133 |
+
"attributes": {}
|
| 2134 |
+
}
|
| 2135 |
+
},
|
| 2136 |
+
"total_flos": 9.955629705945416e+17,
|
| 2137 |
+
"train_batch_size": 4,
|
| 2138 |
+
"trial_name": null,
|
| 2139 |
+
"trial_params": null
|
| 2140 |
+
}
|
checkpoint-5400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de45ce1530ef5dd6b60e376397509faefbc8c5e5d445923323fa47100671263e
|
| 3 |
+
size 4856
|