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 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.1

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/Qwen2.5-7B-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": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "down_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:fbcc188320ae41be545a2655a90cd22d851eb2b2ed60b576a6a350ccb4d4e413
+size 2583745128

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<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 %}

loss.txt

@@ -0,0 +1 @@
+271,no_eval

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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 +1,520 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9963235294117647,
+  "eval_steps": 500,
+  "global_step": 271,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01838235294117647,
+      "grad_norm": 40.77878189086914,
+      "learning_rate": 4.917142857142858e-06,
+      "loss": 4.3405,
+      "mean_token_accuracy": 0.6079744696617126,
+      "num_tokens": 396575.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.03676470588235294,
+      "grad_norm": 8.723130226135254,
+      "learning_rate": 1.106357142857143e-05,
+      "loss": 1.5241,
+      "mean_token_accuracy": 0.7754200756549835,
+      "num_tokens": 784215.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.05514705882352941,
+      "grad_norm": 2.6150617599487305,
+      "learning_rate": 1.7210000000000003e-05,
+      "loss": 0.2611,
+      "mean_token_accuracy": 0.9413737654685974,
+      "num_tokens": 1175812.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 10.302824974060059,
+      "learning_rate": 2.3356428571428574e-05,
+      "loss": 0.0494,
+      "mean_token_accuracy": 0.9854643404483795,
+      "num_tokens": 1568846.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.09191176470588236,
+      "grad_norm": 0.31368523836135864,
+      "learning_rate": 2.950285714285715e-05,
+      "loss": 0.0329,
+      "mean_token_accuracy": 0.9888089418411254,
+      "num_tokens": 1953541.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.11029411764705882,
+      "grad_norm": 0.36221420764923096,
+      "learning_rate": 3.5649285714285724e-05,
+      "loss": 0.022,
+      "mean_token_accuracy": 0.9924580335617066,
+      "num_tokens": 2343960.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.12867647058823528,
+      "grad_norm": 0.24492664635181427,
+      "learning_rate": 4.179571428571429e-05,
+      "loss": 0.0179,
+      "mean_token_accuracy": 0.9932528793811798,
+      "num_tokens": 2734906.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 0.27344170212745667,
+      "learning_rate": 4.3002325201486e-05,
+      "loss": 0.0125,
+      "mean_token_accuracy": 0.9953317403793335,
+      "num_tokens": 3119789.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.16544117647058823,
+      "grad_norm": 0.25588464736938477,
+      "learning_rate": 4.291031805163528e-05,
+      "loss": 0.012,
+      "mean_token_accuracy": 0.9955625712871552,
+      "num_tokens": 3511752.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.18382352941176472,
+      "grad_norm": 0.28750279545783997,
+      "learning_rate": 4.274796508682312e-05,
+      "loss": 0.0084,
+      "mean_token_accuracy": 0.9966519951820374,
+      "num_tokens": 3897740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.20220588235294118,
+      "grad_norm": 0.25286757946014404,
+      "learning_rate": 4.251597923279562e-05,
+      "loss": 0.0114,
+      "mean_token_accuracy": 0.9952130198478699,
+      "num_tokens": 4285139.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.22058823529411764,
+      "grad_norm": 0.14998362958431244,
+      "learning_rate": 4.221537918784545e-05,
+      "loss": 0.0135,
+      "mean_token_accuracy": 0.9948176205158233,
+      "num_tokens": 4682575.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.23897058823529413,
+      "grad_norm": 0.12603914737701416,
+      "learning_rate": 4.184748494949514e-05,
+      "loss": 0.0096,
+      "mean_token_accuracy": 0.9962626159191131,
+      "num_tokens": 5066810.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.25735294117647056,
+      "grad_norm": 0.19672255218029022,
+      "learning_rate": 4.141391201811243e-05,
+      "loss": 0.0089,
+      "mean_token_accuracy": 0.9965241849422455,
+      "num_tokens": 5463729.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.2757352941176471,
+      "grad_norm": 0.12892723083496094,
+      "learning_rate": 4.0916564302911154e-05,
+      "loss": 0.008,
+      "mean_token_accuracy": 0.9969832301139832,
+      "num_tokens": 5850128.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.13913273811340332,
+      "learning_rate": 4.035762576148849e-05,
+      "loss": 0.0078,
+      "mean_token_accuracy": 0.9973669826984406,
+      "num_tokens": 6244002.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.09209585934877396,
+      "learning_rate": 3.973955080961153e-05,
+      "loss": 0.0067,
+      "mean_token_accuracy": 0.9973081052303314,
+      "num_tokens": 6620382.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.33088235294117646,
+      "grad_norm": 0.1415279358625412,
+      "learning_rate": 3.9065053543365454e-05,
+      "loss": 0.0065,
+      "mean_token_accuracy": 0.9977279663085937,
+      "num_tokens": 7000568.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.3492647058823529,
+      "grad_norm": 0.09117847681045532,
+      "learning_rate": 3.833709582099125e-05,
+      "loss": 0.006,
+      "mean_token_accuracy": 0.9978210866451264,
+      "num_tokens": 7386388.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.36764705882352944,
+      "grad_norm": 0.08553037792444229,
+      "learning_rate": 3.7558874256748195e-05,
+      "loss": 0.0052,
+      "mean_token_accuracy": 0.9980245590209961,
+      "num_tokens": 7786489.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.3860294117647059,
+      "grad_norm": 0.08987542241811752,
+      "learning_rate": 3.673380618391356e-05,
+      "loss": 0.0065,
+      "mean_token_accuracy": 0.9980957508087158,
+      "num_tokens": 8179170.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.40441176470588236,
+      "grad_norm": 0.12981808185577393,
+      "learning_rate": 3.5865514648559164e-05,
+      "loss": 0.0064,
+      "mean_token_accuracy": 0.9980520904064178,
+      "num_tokens": 8576123.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.4227941176470588,
+      "grad_norm": 0.049204424023628235,
+      "learning_rate": 3.495781250000001e-05,
+      "loss": 0.0067,
+      "mean_token_accuracy": 0.9976665556430817,
+      "num_tokens": 8977664.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.4411764705882353,
+      "grad_norm": 0.09803196042776108,
+      "learning_rate": 3.401468564777736e-05,
+      "loss": 0.0052,
+      "mean_token_accuracy": 0.9982431530952454,
+      "num_tokens": 9371923.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.45955882352941174,
+      "grad_norm": 0.064445860683918,
+      "learning_rate": 3.304027555869822e-05,
+      "loss": 0.0045,
+      "mean_token_accuracy": 0.9983674705028533,
+      "num_tokens": 9747750.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.47794117647058826,
+      "grad_norm": 0.11150972545146942,
+      "learning_rate": 3.203886107079038e-05,
+      "loss": 0.0049,
+      "mean_token_accuracy": 0.9983975529670716,
+      "num_tokens": 10138347.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.4963235294117647,
+      "grad_norm": 0.06595049798488617,
+      "learning_rate": 3.101483960403179e-05,
+      "loss": 0.0038,
+      "mean_token_accuracy": 0.9987940490245819,
+      "num_tokens": 10519930.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.5147058823529411,
+      "grad_norm": 0.06900100409984589,
+      "learning_rate": 2.997270785036188e-05,
+      "loss": 0.0045,
+      "mean_token_accuracy": 0.9984328985214234,
+      "num_tokens": 10923657.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.5330882352941176,
+      "grad_norm": 0.08975087106227875,
+      "learning_rate": 2.891704202776889e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9988918602466583,
+      "num_tokens": 11308146.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.5514705882352942,
+      "grad_norm": 0.06893062591552734,
+      "learning_rate": 2.7852477785161814e-05,
+      "loss": 0.0045,
+      "mean_token_accuracy": 0.9988150656223297,
+      "num_tokens": 11698084.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.5698529411764706,
+      "grad_norm": 0.1488070785999298,
+      "learning_rate": 2.6783689846268743e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9985724210739135,
+      "num_tokens": 12080500.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.11203882098197937,
+      "learning_rate": 2.5715371481949467e-05,
+      "loss": 0.006,
+      "mean_token_accuracy": 0.9976416766643524,
+      "num_tokens": 12475518.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.6066176470588235,
+      "grad_norm": 0.08506222069263458,
+      "learning_rate": 2.4652213901063884e-05,
+      "loss": 0.0039,
+      "mean_token_accuracy": 0.9987370252609253,
+      "num_tokens": 12871598.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.06337340176105499,
+      "learning_rate": 2.3598885650394917e-05,
+      "loss": 0.0048,
+      "mean_token_accuracy": 0.9986328899860382,
+      "num_tokens": 13272176.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.6433823529411765,
+      "grad_norm": 0.08344393223524094,
+      "learning_rate": 2.256001211408547e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9988697469234467,
+      "num_tokens": 13673743.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.6617647058823529,
+      "grad_norm": 0.08593422174453735,
+      "learning_rate": 2.1540155202611485e-05,
+      "loss": 0.0041,
+      "mean_token_accuracy": 0.9986071050167084,
+      "num_tokens": 14066523.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.6801470588235294,
+      "grad_norm": 0.10229282081127167,
+      "learning_rate": 2.054379332048112e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9987092971801758,
+      "num_tokens": 14462689.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.6985294117647058,
+      "grad_norm": 0.11607314646244049,
+      "learning_rate": 1.957530170062605e-05,
+      "loss": 0.0042,
+      "mean_token_accuracy": 0.9986791372299194,
+      "num_tokens": 14847962.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.7169117647058824,
+      "grad_norm": 0.02692285180091858,
+      "learning_rate": 1.863893319184073e-05,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9986750185489655,
+      "num_tokens": 15237420.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.7352941176470589,
+      "grad_norm": 0.053456008434295654,
+      "learning_rate": 1.7738799583635873e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9988762140274048,
+      "num_tokens": 15626132.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.7536764705882353,
+      "grad_norm": 0.05752914026379585,
+      "learning_rate": 1.6878853550512764e-05,
+      "loss": 0.0041,
+      "mean_token_accuracy": 0.9984098911285401,
+      "num_tokens": 16018063.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.7720588235294118,
+      "grad_norm": 0.08336920291185379,
+      "learning_rate": 1.6062871294944667e-05,
+      "loss": 0.0044,
+      "mean_token_accuracy": 0.9985141575336456,
+      "num_tokens": 16409175.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.7904411764705882,
+      "grad_norm": 0.11755795776844025,
+      "learning_rate": 1.5294435965283893e-05,
+      "loss": 0.0047,
+      "mean_token_accuracy": 0.9981832683086396,
+      "num_tokens": 16803906.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.8088235294117647,
+      "grad_norm": 0.08356364071369171,
+      "learning_rate": 1.4576921921409594e-05,
+      "loss": 0.0047,
+      "mean_token_accuracy": 0.9984434008598327,
+      "num_tokens": 17187152.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.8272058823529411,
+      "grad_norm": 0.09949304908514023,
+      "learning_rate": 1.3913479917209507e-05,
+      "loss": 0.003,
+      "mean_token_accuracy": 0.9990458905696868,
+      "num_tokens": 17574580.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.8455882352941176,
+      "grad_norm": 0.0650205984711647,
+      "learning_rate": 1.3307023264962129e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9989714860916138,
+      "num_tokens": 17961330.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.8639705882352942,
+      "grad_norm": 0.0479765459895134,
+      "learning_rate": 1.2760215042374612e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9988696932792663,
+      "num_tokens": 18349709.0,
+      "step": 235
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.10548855364322662,
+      "learning_rate": 1.2275456398452826e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9990268647670746,
+      "num_tokens": 18733145.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.9007352941176471,
+      "grad_norm": 0.030466251075267792,
+      "learning_rate": 1.1854876009555089e-05,
+      "loss": 0.0029,
+      "mean_token_accuracy": 0.9990714967250824,
+      "num_tokens": 19123886.0,
+      "step": 245
+    },
+    {
+      "epoch": 0.9191176470588235,
+      "grad_norm": 0.07559388130903244,
+      "learning_rate": 1.1500320731930042e-05,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9988040447235107,
+      "num_tokens": 19506834.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.11076359450817108,
+      "learning_rate": 1.1213347491785512e-05,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9992827951908112,
+      "num_tokens": 19894291.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.9558823529411765,
+      "grad_norm": 0.04865700751543045,
+      "learning_rate": 1.0995216448500645e-05,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9993002355098725,
+      "num_tokens": 20272252.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.9742647058823529,
+      "grad_norm": 0.07477735728025436,
+      "learning_rate": 1.0846885461003128e-05,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9991890132427216,
+      "num_tokens": 20650206.0,
+      "step": 265
+    },
+    {
+      "epoch": 0.9926470588235294,
+      "grad_norm": 0.10289261490106583,
+      "learning_rate": 1.0769005881610753e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9989068508148193,
+      "num_tokens": 21044381.0,
+      "step": 270
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 272,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7390843485875077e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755a03ad6473fd63dde13d25ff6129fde4b4d9ab002e14ab85ce91b8c84778eb
+size 6481