Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-14B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-14B-Instruct
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2879e227e5c053e1670774b72b0210d9e010977e47f10ff4e885bee9828a4e2d
+size 6487665104

added_tokens.json

@@ -0,0 +1,27 @@
+{
+  "</tool_call>": 151658,
+  "<obs>": 151667,
+  "<response>": 151666,
+  "<think>": 151665,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c2a387ce39511b174f3c686cc50ae7507dbef21addb167bbe454c9f0d8d7f7
+size 551080387

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5f7f8e8008941b8a3e11610c8c74e2cba093cb067735d7b273a336eaaa09c0b
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a719675fab8cb1b9be2401d867a6bfb533aeaeadf3e62f393c5566ceb52ad9d6
+size 1465

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<obs>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063ac76c8e7790eabef1a7dba3a2ba571208518187f9bccef8b776490137d5e3
+size 11422548

tokenizer_config.json

@@ -0,0 +1,221 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "<response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<obs>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<think>",
+    "<response>",
+    "<obs>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,566 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 200,
+  "global_step": 1900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013157894736842105,
+      "grad_norm": 0.7272480130195618,
+      "learning_rate": 8.421052631578948e-05,
+      "loss": 1.9563,
+      "step": 25
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 0.3988882899284363,
+      "learning_rate": 0.00017192982456140353,
+      "loss": 0.78,
+      "step": 50
+    },
+    {
+      "epoch": 0.039473684210526314,
+      "grad_norm": 0.23908574879169464,
+      "learning_rate": 0.00019995801573733038,
+      "loss": 0.5912,
+      "step": 75
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 0.22981883585453033,
+      "learning_rate": 0.00019974382771078473,
+      "loss": 0.5734,
+      "step": 100
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 0.22677601873874664,
+      "learning_rate": 0.00019934852677927834,
+      "loss": 0.5326,
+      "step": 125
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 0.23226918280124664,
+      "learning_rate": 0.00019877283072256436,
+      "loss": 0.4978,
+      "step": 150
+    },
+    {
+      "epoch": 0.09210526315789473,
+      "grad_norm": 0.265936017036438,
+      "learning_rate": 0.00019801778487836048,
+      "loss": 0.5083,
+      "step": 175
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.2562519609928131,
+      "learning_rate": 0.00019708476024424477,
+      "loss": 0.5017,
+      "step": 200
+    },
+    {
+      "epoch": 0.11842105263157894,
+      "grad_norm": 0.24657155573368073,
+      "learning_rate": 0.00019597545098822504,
+      "loss": 0.5355,
+      "step": 225
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 0.2717723548412323,
+      "learning_rate": 0.00019469187137250148,
+      "loss": 0.5057,
+      "step": 250
+    },
+    {
+      "epoch": 0.14473684210526316,
+      "grad_norm": 0.14394891262054443,
+      "learning_rate": 0.00019323635209600841,
+      "loss": 0.5435,
+      "step": 275
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.2538720369338989,
+      "learning_rate": 0.00019161153606237651,
+      "loss": 0.4619,
+      "step": 300
+    },
+    {
+      "epoch": 0.17105263157894737,
+      "grad_norm": 0.2302940934896469,
+      "learning_rate": 0.00018982037358099963,
+      "loss": 0.5144,
+      "step": 325
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 0.23402678966522217,
+      "learning_rate": 0.00018786611700992044,
+      "loss": 0.5385,
+      "step": 350
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 0.2835828363895416,
+      "learning_rate": 0.0001857523148502617,
+      "loss": 0.5324,
+      "step": 375
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.2346741110086441,
+      "learning_rate": 0.00018348280530292713,
+      "loss": 0.5538,
+      "step": 400
+    },
+    {
+      "epoch": 0.2236842105263158,
+      "grad_norm": 0.20240184664726257,
+      "learning_rate": 0.00018106170929927035,
+      "loss": 0.4757,
+      "step": 425
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 0.23748184740543365,
+      "learning_rate": 0.0001784934230183882,
+      "loss": 0.4722,
+      "step": 450
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.24441654980182648,
+      "learning_rate": 0.00017578260990462372,
+      "loss": 0.4765,
+      "step": 475
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.21534137427806854,
+      "learning_rate": 0.00017293419219977486,
+      "loss": 0.511,
+      "step": 500
+    },
+    {
+      "epoch": 0.27631578947368424,
+      "grad_norm": 0.18411624431610107,
+      "learning_rate": 0.0001699533420053832,
+      "loss": 0.459,
+      "step": 525
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 0.22512228786945343,
+      "learning_rate": 0.0001668454718913325,
+      "loss": 0.4602,
+      "step": 550
+    },
+    {
+      "epoch": 0.3026315789473684,
+      "grad_norm": 0.3007086515426636,
+      "learning_rate": 0.00016361622506780944,
+      "loss": 0.4723,
+      "step": 575
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.24483013153076172,
+      "learning_rate": 0.0001602714651384722,
+      "loss": 0.4825,
+      "step": 600
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 0.19368383288383484,
+      "learning_rate": 0.0001568172654534328,
+      "loss": 0.5199,
+      "step": 625
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 0.27732446789741516,
+      "learning_rate": 0.0001532598980813858,
+      "loss": 0.4766,
+      "step": 650
+    },
+    {
+      "epoch": 0.35526315789473684,
+      "grad_norm": 0.2359321564435959,
+      "learning_rate": 0.0001496058224209082,
+      "loss": 0.4315,
+      "step": 675
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.25275617837905884,
+      "learning_rate": 0.00014586167347160846,
+      "loss": 0.4361,
+      "step": 700
+    },
+    {
+      "epoch": 0.3815789473684211,
+      "grad_norm": 0.1912153959274292,
+      "learning_rate": 0.00014203424978642337,
+      "loss": 0.4467,
+      "step": 725
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 0.23994949460029602,
+      "learning_rate": 0.00013813050112693778,
+      "loss": 0.4927,
+      "step": 750
+    },
+    {
+      "epoch": 0.40789473684210525,
+      "grad_norm": 0.23791591823101044,
+      "learning_rate": 0.00013415751584414215,
+      "loss": 0.4032,
+      "step": 775
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.2177554816007614,
+      "learning_rate": 0.00013012250800754284,
+      "loss": 0.5174,
+      "step": 800
+    },
+    {
+      "epoch": 0.4342105263157895,
+      "grad_norm": 0.2537310719490051,
+      "learning_rate": 0.0001260328043059947,
+      "loss": 0.5024,
+      "step": 825
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 0.3210338056087494,
+      "learning_rate": 0.00012189583074404174,
+      "loss": 0.4572,
+      "step": 850
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 0.1832045167684555,
+      "learning_rate": 0.0001177190991579223,
+      "loss": 0.4374,
+      "step": 875
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.21890908479690552,
+      "learning_rate": 0.00011351019357572274,
+      "loss": 0.446,
+      "step": 900
+    },
+    {
+      "epoch": 0.4868421052631579,
+      "grad_norm": 0.2524813115596771,
+      "learning_rate": 0.00010927675644644666,
+      "loss": 0.4316,
+      "step": 925
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.2024998813867569,
+      "learning_rate": 0.0001050264747630043,
+      "loss": 0.4264,
+      "step": 950
+    },
+    {
+      "epoch": 0.5131578947368421,
+      "grad_norm": 0.23862822353839874,
+      "learning_rate": 0.00010076706610432009,
+      "loss": 0.4809,
+      "step": 975
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.21620877087116241,
+      "learning_rate": 9.650626462190294e-05,
+      "loss": 0.4528,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5394736842105263,
+      "grad_norm": 0.2496652454137802,
+      "learning_rate": 9.2251806996324e-05,
+      "loss": 0.5165,
+      "step": 1025
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.18958808481693268,
+      "learning_rate": 8.801141838910238e-05,
+      "loss": 0.461,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5657894736842105,
+      "grad_norm": 0.2566398084163666,
+      "learning_rate": 8.379279841550693e-05,
+      "loss": 0.4917,
+      "step": 1075
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.2727346122264862,
+      "learning_rate": 7.960360716374442e-05,
+      "loss": 0.4035,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.2812783718109131,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 0.4062,
+      "step": 1125
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.13381074368953705,
+      "learning_rate": 7.134387018602659e-05,
+      "loss": 0.4147,
+      "step": 1150
+    },
+    {
+      "epoch": 0.618421052631579,
+      "grad_norm": 0.24165485799312592,
+      "learning_rate": 6.728832233004054e-05,
+      "loss": 0.4694,
+      "step": 1175
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.1850873976945877,
+      "learning_rate": 6.329217170298507e-05,
+      "loss": 0.5144,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6447368421052632,
+      "grad_norm": 0.3044758439064026,
+      "learning_rate": 5.936267443754863e-05,
+      "loss": 0.448,
+      "step": 1225
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.25881174206733704,
+      "learning_rate": 5.550696563854032e-05,
+      "loss": 0.4331,
+      "step": 1250
+    },
+    {
+      "epoch": 0.6710526315789473,
+      "grad_norm": 0.1471320539712906,
+      "learning_rate": 5.173204642710514e-05,
+      "loss": 0.4162,
+      "step": 1275
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.23026077449321747,
+      "learning_rate": 4.804477122822432e-05,
+      "loss": 0.4321,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6973684210526315,
+      "grad_norm": 0.2941257655620575,
+      "learning_rate": 4.4451835324583326e-05,
+      "loss": 0.4041,
+      "step": 1325
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.2662881016731262,
+      "learning_rate": 4.0959762699407766e-05,
+      "loss": 0.4282,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.27813515067100525,
+      "learning_rate": 3.7574894190341404e-05,
+      "loss": 0.4424,
+      "step": 1375
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.25936228036880493,
+      "learning_rate": 3.430337597587622e-05,
+      "loss": 0.4325,
+      "step": 1400
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.2591690421104431,
+      "learning_rate": 3.1151148415241035e-05,
+      "loss": 0.4389,
+      "step": 1425
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.2798675298690796,
+      "learning_rate": 2.8123935262012447e-05,
+      "loss": 0.4832,
+      "step": 1450
+    },
+    {
+      "epoch": 0.7763157894736842,
+      "grad_norm": 0.28093063831329346,
+      "learning_rate": 2.5227233271034322e-05,
+      "loss": 0.4171,
+      "step": 1475
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.292204350233078,
+      "learning_rate": 2.2466302217517133e-05,
+      "loss": 0.4802,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8026315789473685,
+      "grad_norm": 0.2873384654521942,
+      "learning_rate": 1.984615534644032e-05,
+      "loss": 0.4688,
+      "step": 1525
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.23933933675289154,
+      "learning_rate": 1.7371550269599323e-05,
+      "loss": 0.4687,
+      "step": 1550
+    },
+    {
+      "epoch": 0.8289473684210527,
+      "grad_norm": 0.27426981925964355,
+      "learning_rate": 1.50469803268267e-05,
+      "loss": 0.4475,
+      "step": 1575
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.2896619439125061,
+      "learning_rate": 1.2876666427072703e-05,
+      "loss": 0.4643,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.15856152772903442,
+      "learning_rate": 1.0864549384160927e-05,
+      "loss": 0.4614,
+      "step": 1625
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.32572880387306213,
+      "learning_rate": 9.014282761135084e-06,
+      "loss": 0.3922,
+      "step": 1650
+    },
+    {
+      "epoch": 0.881578947368421,
+      "grad_norm": 0.2075156420469284,
+      "learning_rate": 7.329226236190201e-06,
+      "loss": 0.4834,
+      "step": 1675
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.2609516978263855,
+      "learning_rate": 5.81243950223419e-06,
+      "loss": 0.4424,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9078947368421053,
+      "grad_norm": 0.27902549505233765,
+      "learning_rate": 4.4666767111569474e-06,
+      "loss": 0.4107,
+      "step": 1725
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.1807645708322525,
+      "learning_rate": 3.294381472894781e-06,
+      "loss": 0.4095,
+      "step": 1750
+    },
+    {
+      "epoch": 0.9342105263157895,
+      "grad_norm": 0.27969783544540405,
+      "learning_rate": 2.2976824183709835e-06,
+      "loss": 0.4665,
+      "step": 1775
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.27561429142951965,
+      "learning_rate": 1.4783893343691458e-06,
+      "loss": 0.4077,
+      "step": 1800
+    },
+    {
+      "epoch": 0.9605263157894737,
+      "grad_norm": 0.2988797426223755,
+      "learning_rate": 8.379898773574924e-07,
+      "loss": 0.4332,
+      "step": 1825
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.2036939263343811,
+      "learning_rate": 3.7764687223110773e-07,
+      "loss": 0.401,
+      "step": 1850
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.21864855289459229,
+      "learning_rate": 9.8196200877132e-08,
+      "loss": 0.4638,
+      "step": 1875
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2675096392631531,
+      "learning_rate": 1.452843966354145e-10,
+      "loss": 0.465,
+      "step": 1900
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.7343723267668173e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a2a85f387e0819a00ee9eabb4e3b84779e478f1a5521e197820e7529d9dad2
+size 5841