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 0.17.0

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "v_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 sha256:470d98028af018e20983649927e22380528d8a9e1e69182ec9e9a5ed4874690f
+size 645975704

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 %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b2adb2ca460a795b45fd57ca998f6e61f468fe1ac42ea4198c50fc4c2c8c13
+size 1292087499

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5291934866a70ac9f1e1e5c64f2109d985d93f37c1cef1792e32699acf1d3b69
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda3169588cd5e5b980f3cc1a99824b676ce20e1bed8dd75d485ed41bcb5613e
+size 1465

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f9d93e80cff961819dcba7d892cf9656e086a0cf83cdbef23f10c1a493faa2
+size 11422061

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": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,668 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1660,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.060350030175015085,
+      "grad_norm": 0.25875431299209595,
+      "learning_rate": 0.00013636363636363637,
+      "loss": 1.8139,
+      "mean_token_accuracy": 0.6307312214374542,
+      "num_tokens": 156890.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.12070006035003017,
+      "grad_norm": 0.2245057374238968,
+      "learning_rate": 0.0002784090909090909,
+      "loss": 0.8686,
+      "mean_token_accuracy": 0.7807172381877899,
+      "num_tokens": 283625.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.18105009052504525,
+      "grad_norm": 0.18950718641281128,
+      "learning_rate": 0.0004204545454545455,
+      "loss": 0.6245,
+      "mean_token_accuracy": 0.8282737296819687,
+      "num_tokens": 439023.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.24140012070006034,
+      "grad_norm": 0.24096715450286865,
+      "learning_rate": 0.0004999811888222022,
+      "loss": 0.4905,
+      "mean_token_accuracy": 0.8619039803743362,
+      "num_tokens": 563539.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.30175015087507545,
+      "grad_norm": 0.17966966331005096,
+      "learning_rate": 0.0004997985428296869,
+      "loss": 0.3821,
+      "mean_token_accuracy": 0.8908107584714889,
+      "num_tokens": 722861.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.3621001810500905,
+      "grad_norm": 0.21009193360805511,
+      "learning_rate": 0.0004994217332277896,
+      "loss": 0.3269,
+      "mean_token_accuracy": 0.9061362200975418,
+      "num_tokens": 850582.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.4224502112251056,
+      "grad_norm": 0.23502632975578308,
+      "learning_rate": 0.0004988510529033761,
+      "loss": 0.2387,
+      "mean_token_accuracy": 0.9319302082061768,
+      "num_tokens": 1009486.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.4828002414001207,
+      "grad_norm": 0.2148028463125229,
+      "learning_rate": 0.0004980869454353018,
+      "loss": 0.2076,
+      "mean_token_accuracy": 0.9411827009916306,
+      "num_tokens": 1137451.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.5431502715751357,
+      "grad_norm": 0.1632697582244873,
+      "learning_rate": 0.0004971300047496247,
+      "loss": 0.1619,
+      "mean_token_accuracy": 0.9540650862455368,
+      "num_tokens": 1293610.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.6035003017501509,
+      "grad_norm": 0.26104432344436646,
+      "learning_rate": 0.0004959809746579596,
+      "loss": 0.164,
+      "mean_token_accuracy": 0.9534644478559494,
+      "num_tokens": 1420307.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.663850331925166,
+      "grad_norm": 0.12273592501878738,
+      "learning_rate": 0.0004946407482793272,
+      "loss": 0.1295,
+      "mean_token_accuracy": 0.9624715512990951,
+      "num_tokens": 1578380.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.724200362100181,
+      "grad_norm": 0.32087773084640503,
+      "learning_rate": 0.0004931103673459494,
+      "loss": 0.1113,
+      "mean_token_accuracy": 0.9689557248353958,
+      "num_tokens": 1706886.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.7845503922751962,
+      "grad_norm": 0.1366167813539505,
+      "learning_rate": 0.0004913910213935311,
+      "loss": 0.1113,
+      "mean_token_accuracy": 0.9688878679275512,
+      "num_tokens": 1866557.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.8449004224502112,
+      "grad_norm": 0.24156679213047028,
+      "learning_rate": 0.000489484046836657,
+      "loss": 0.1045,
+      "mean_token_accuracy": 0.9704328417778015,
+      "num_tokens": 1992314.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.9052504526252263,
+      "grad_norm": 0.14394783973693848,
+      "learning_rate": 0.0004873909259300225,
+      "loss": 0.0948,
+      "mean_token_accuracy": 0.9738239508867264,
+      "num_tokens": 2149150.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.9656004828002414,
+      "grad_norm": 0.22457388043403625,
+      "learning_rate": 0.0004851132856163051,
+      "loss": 0.0826,
+      "mean_token_accuracy": 0.9772097253799439,
+      "num_tokens": 2275425.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.09257517755031586,
+      "eval_mean_token_accuracy": 0.9736895409790245,
+      "eval_num_tokens": 2354180.0,
+      "eval_runtime": 15.7044,
+      "eval_samples_per_second": 23.497,
+      "eval_steps_per_second": 11.78,
+      "step": 415
+    },
+    {
+      "epoch": 1.024140012070006,
+      "grad_norm": 0.15583111345767975,
+      "learning_rate": 0.0004826528962615731,
+      "loss": 0.0995,
+      "mean_token_accuracy": 0.9726028952401938,
+      "num_tokens": 2422079.0,
+      "step": 425
+    },
+    {
+      "epoch": 1.0844900422450212,
+      "grad_norm": 0.11416012048721313,
+      "learning_rate": 0.0004800116702792146,
+      "loss": 0.0592,
+      "mean_token_accuracy": 0.9830048185586929,
+      "num_tokens": 2563265.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.1448400724200363,
+      "grad_norm": 0.0843014195561409,
+      "learning_rate": 0.00047719166064345484,
+      "loss": 0.0773,
+      "mean_token_accuracy": 0.977996414899826,
+      "num_tokens": 2706077.0,
+      "step": 475
+    },
+    {
+      "epoch": 1.2051901025950513,
+      "grad_norm": 0.11646401882171631,
+      "learning_rate": 0.0004741950592936188,
+      "loss": 0.0494,
+      "mean_token_accuracy": 0.9854312521219254,
+      "num_tokens": 2847990.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.2655401327700664,
+      "grad_norm": 0.08569753915071487,
+      "learning_rate": 0.00047102419543037903,
+      "loss": 0.0834,
+      "mean_token_accuracy": 0.9780280828475952,
+      "num_tokens": 2989791.0,
+      "step": 525
+    },
+    {
+      "epoch": 1.3258901629450814,
+      "grad_norm": 0.10648876428604126,
+      "learning_rate": 0.00046768153370531276,
+      "loss": 0.0572,
+      "mean_token_accuracy": 0.9838361299037933,
+      "num_tokens": 3132225.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.3862401931200965,
+      "grad_norm": 0.07524841278791428,
+      "learning_rate": 0.00046416967230517524,
+      "loss": 0.0674,
+      "mean_token_accuracy": 0.9807477170228958,
+      "num_tokens": 3272843.0,
+      "step": 575
+    },
+    {
+      "epoch": 1.4465902232951118,
+      "grad_norm": 0.07833650708198547,
+      "learning_rate": 0.00046049134093237943,
+      "loss": 0.0472,
+      "mean_token_accuracy": 0.9861810153722763,
+      "num_tokens": 3417150.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.5069402534701268,
+      "grad_norm": 0.06221695989370346,
+      "learning_rate": 0.0004566493986832504,
+      "loss": 0.0606,
+      "mean_token_accuracy": 0.9831046575307846,
+      "num_tokens": 3558624.0,
+      "step": 625
+    },
+    {
+      "epoch": 1.567290283645142,
+      "grad_norm": 0.1267794370651245,
+      "learning_rate": 0.0004526468318257052,
+      "loss": 0.0452,
+      "mean_token_accuracy": 0.9872009134292603,
+      "num_tokens": 3701282.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.627640313820157,
+      "grad_norm": 0.08861544728279114,
+      "learning_rate": 0.0004484867514780834,
+      "loss": 0.0608,
+      "mean_token_accuracy": 0.9829268258810043,
+      "num_tokens": 3846134.0,
+      "step": 675
+    },
+    {
+      "epoch": 1.687990343995172,
+      "grad_norm": 0.12759177386760712,
+      "learning_rate": 0.0004441723911909354,
+      "loss": 0.0434,
+      "mean_token_accuracy": 0.9877904134988785,
+      "num_tokens": 3989906.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.748340374170187,
+      "grad_norm": 0.08757840096950531,
+      "learning_rate": 0.00043970710443364506,
+      "loss": 0.055,
+      "mean_token_accuracy": 0.9843549174070358,
+      "num_tokens": 4130356.0,
+      "step": 725
+    },
+    {
+      "epoch": 1.8086904043452021,
+      "grad_norm": 0.0843178927898407,
+      "learning_rate": 0.0004350943619878427,
+      "loss": 0.0433,
+      "mean_token_accuracy": 0.9873012232780457,
+      "num_tokens": 4272859.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.8690404345202172,
+      "grad_norm": 0.07654984295368195,
+      "learning_rate": 0.00043033774924963297,
+      "loss": 0.0586,
+      "mean_token_accuracy": 0.9836700081825256,
+      "num_tokens": 4414328.0,
+      "step": 775
+    },
+    {
+      "epoch": 1.9293904646952322,
+      "grad_norm": 0.08279535174369812,
+      "learning_rate": 0.00042544096344273566,
+      "loss": 0.0406,
+      "mean_token_accuracy": 0.9882488793134689,
+      "num_tokens": 4555974.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.9897404948702473,
+      "grad_norm": 0.09290555119514465,
+      "learning_rate": 0.00042040781074470415,
+      "loss": 0.0464,
+      "mean_token_accuracy": 0.9870415306091309,
+      "num_tokens": 4689001.0,
+      "step": 825
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.05456389859318733,
+      "eval_mean_token_accuracy": 0.9851698475915033,
+      "eval_num_tokens": 4708360.0,
+      "eval_runtime": 15.7238,
+      "eval_samples_per_second": 23.468,
+      "eval_steps_per_second": 11.766,
+      "step": 830
+    },
+    {
+      "epoch": 2.048280024140012,
+      "grad_norm": 0.05181082338094711,
+      "learning_rate": 0.0004152422033284574,
+      "loss": 0.0445,
+      "mean_token_accuracy": 0.9867442065907508,
+      "num_tokens": 4838142.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.1086300543150274,
+      "grad_norm": 0.05355146527290344,
+      "learning_rate": 0.0004099481563214226,
+      "loss": 0.0314,
+      "mean_token_accuracy": 0.990835223197937,
+      "num_tokens": 4971140.0,
+      "step": 875
+    },
+    {
+      "epoch": 2.1689800844900424,
+      "grad_norm": 0.04749223589897156,
+      "learning_rate": 0.00040452978468465383,
+      "loss": 0.0446,
+      "mean_token_accuracy": 0.9865801340341568,
+      "num_tokens": 5122361.0,
+      "step": 900
+    },
+    {
+      "epoch": 2.2293301146650575,
+      "grad_norm": 0.06724860519170761,
+      "learning_rate": 0.00039899130001435203,
+      "loss": 0.0321,
+      "mean_token_accuracy": 0.9902541941404343,
+      "num_tokens": 5255402.0,
+      "step": 925
+    },
+    {
+      "epoch": 2.2896801448400725,
+      "grad_norm": 0.07366824150085449,
+      "learning_rate": 0.000393337007268272,
+      "loss": 0.0414,
+      "mean_token_accuracy": 0.9877721995115281,
+      "num_tokens": 5406401.0,
+      "step": 950
+    },
+    {
+      "epoch": 2.3500301750150876,
+      "grad_norm": 0.04158030077815056,
+      "learning_rate": 0.0003875713014195614,
+      "loss": 0.0304,
+      "mean_token_accuracy": 0.9910214012861251,
+      "num_tokens": 5538594.0,
+      "step": 975
+    },
+    {
+      "epoch": 2.4103802051901027,
+      "grad_norm": 0.05240670219063759,
+      "learning_rate": 0.0003816986640406329,
+      "loss": 0.0474,
+      "mean_token_accuracy": 0.9857887053489685,
+      "num_tokens": 5690102.0,
+      "step": 1000
+    },
+    {
+      "epoch": 2.4707302353651177,
+      "grad_norm": 0.077730692923069,
+      "learning_rate": 0.00037572365981972333,
+      "loss": 0.0334,
+      "mean_token_accuracy": 0.9903035759925842,
+      "num_tokens": 5823065.0,
+      "step": 1025
+    },
+    {
+      "epoch": 2.5310802655401328,
+      "grad_norm": 0.04822751507163048,
+      "learning_rate": 0.00036965093301284994,
+      "loss": 0.0449,
+      "mean_token_accuracy": 0.9864302569627762,
+      "num_tokens": 5974567.0,
+      "step": 1050
+    },
+    {
+      "epoch": 2.591430295715148,
+      "grad_norm": 0.07845977693796158,
+      "learning_rate": 0.00036348520383391885,
+      "loss": 0.031,
+      "mean_token_accuracy": 0.9906397736072541,
+      "num_tokens": 6107171.0,
+      "step": 1075
+    },
+    {
+      "epoch": 2.651780325890163,
+      "grad_norm": 0.04880121350288391,
+      "learning_rate": 0.00035723126478579383,
+      "loss": 0.0432,
+      "mean_token_accuracy": 0.9871418106555939,
+      "num_tokens": 6257293.0,
+      "step": 1100
+    },
+    {
+      "epoch": 2.712130356065178,
+      "grad_norm": 0.05152444541454315,
+      "learning_rate": 0.00035089397693517546,
+      "loss": 0.0308,
+      "mean_token_accuracy": 0.9905445170402527,
+      "num_tokens": 6389689.0,
+      "step": 1125
+    },
+    {
+      "epoch": 2.772480386240193,
+      "grad_norm": 0.04494641348719597,
+      "learning_rate": 0.00034447826613418793,
+      "loss": 0.0418,
+      "mean_token_accuracy": 0.9878531390428543,
+      "num_tokens": 6541638.0,
+      "step": 1150
+    },
+    {
+      "epoch": 2.832830416415208,
+      "grad_norm": 0.07286397367715836,
+      "learning_rate": 0.0003379891191916081,
+      "loss": 0.0299,
+      "mean_token_accuracy": 0.9908888912200928,
+      "num_tokens": 6674920.0,
+      "step": 1175
+    },
+    {
+      "epoch": 2.8931804465902236,
+      "grad_norm": 0.04308425635099411,
+      "learning_rate": 0.0003314315799967154,
+      "loss": 0.0438,
+      "mean_token_accuracy": 0.9870698708295822,
+      "num_tokens": 6827190.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.9535304767652386,
+      "grad_norm": 0.0426165796816349,
+      "learning_rate": 0.00032481074559877334,
+      "loss": 0.0287,
+      "mean_token_accuracy": 0.9914436733722687,
+      "num_tokens": 6960777.0,
+      "step": 1225
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.04540110006928444,
+      "eval_mean_token_accuracy": 0.9879436412373105,
+      "eval_num_tokens": 7062540.0,
+      "eval_runtime": 15.6959,
+      "eval_samples_per_second": 23.509,
+      "eval_steps_per_second": 11.787,
+      "step": 1245
+    },
+    {
+      "epoch": 3.012070006035003,
+      "grad_norm": 0.07265770435333252,
+      "learning_rate": 0.00031813176224519094,
+      "loss": 0.0375,
+      "mean_token_accuracy": 0.988736727188543,
+      "num_tokens": 7098630.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0724200362100182,
+      "grad_norm": 0.04602326080203056,
+      "learning_rate": 0.00031139982138144356,
+      "loss": 0.0255,
+      "mean_token_accuracy": 0.9921631121635437,
+      "num_tokens": 7246165.0,
+      "step": 1275
+    },
+    {
+      "epoch": 3.1327700663850333,
+      "grad_norm": 0.05525028705596924,
+      "learning_rate": 0.00030462015561586223,
+      "loss": 0.0283,
+      "mean_token_accuracy": 0.9914786797761918,
+      "num_tokens": 7382497.0,
+      "step": 1300
+    },
+    {
+      "epoch": 3.1931200965600484,
+      "grad_norm": 0.06040743738412857,
+      "learning_rate": 0.00029779803465242714,
+      "loss": 0.0252,
+      "mean_token_accuracy": 0.9920045024156571,
+      "num_tokens": 7530566.0,
+      "step": 1325
+    },
+    {
+      "epoch": 3.2534701267350634,
+      "grad_norm": 0.060027897357940674,
+      "learning_rate": 0.0002909387611947288,
+      "loss": 0.0298,
+      "mean_token_accuracy": 0.9905391663312912,
+      "num_tokens": 7665061.0,
+      "step": 1350
+    },
+    {
+      "epoch": 3.3138201569100785,
+      "grad_norm": 0.048240501433610916,
+      "learning_rate": 0.00028404766682427733,
+      "loss": 0.0272,
+      "mean_token_accuracy": 0.9913672947883606,
+      "num_tokens": 7813164.0,
+      "step": 1375
+    },
+    {
+      "epoch": 3.3741701870850935,
+      "grad_norm": 0.05628271773457527,
+      "learning_rate": 0.00027713010785636777,
+      "loss": 0.033,
+      "mean_token_accuracy": 0.9899055260419846,
+      "num_tokens": 7949121.0,
+      "step": 1400
+    },
+    {
+      "epoch": 3.4345202172601086,
+      "grad_norm": 0.033114247024059296,
+      "learning_rate": 0.000270191461176718,
+      "loss": 0.0279,
+      "mean_token_accuracy": 0.9911431854963303,
+      "num_tokens": 8099015.0,
+      "step": 1425
+    },
+    {
+      "epoch": 3.4948702474351236,
+      "grad_norm": 0.04663868620991707,
+      "learning_rate": 0.0002632371200621192,
+      "loss": 0.0282,
+      "mean_token_accuracy": 0.9910573524236679,
+      "num_tokens": 8235915.0,
+      "step": 1450
+    },
+    {
+      "epoch": 3.5552202776101387,
+      "grad_norm": 0.03652872517704964,
+      "learning_rate": 0.0002562724899883458,
+      "loss": 0.0256,
+      "mean_token_accuracy": 0.9919676816463471,
+      "num_tokens": 8383028.0,
+      "step": 1475
+    },
+    {
+      "epoch": 3.6155703077851538,
+      "grad_norm": 0.04912243038415909,
+      "learning_rate": 0.000249302984428582,
+      "loss": 0.0281,
+      "mean_token_accuracy": 0.9909066534042359,
+      "num_tokens": 8518849.0,
+      "step": 1500
+    },
+    {
+      "epoch": 3.675920337960169,
+      "grad_norm": 0.05316564068198204,
+      "learning_rate": 0.0002423340206456343,
+      "loss": 0.0243,
+      "mean_token_accuracy": 0.9922403633594513,
+      "num_tokens": 8667137.0,
+      "step": 1525
+    },
+    {
+      "epoch": 3.736270368135184,
+      "grad_norm": 0.04942823201417923,
+      "learning_rate": 0.0002353710154811956,
+      "loss": 0.0304,
+      "mean_token_accuracy": 0.9901957029104232,
+      "num_tokens": 8803207.0,
+      "step": 1550
+    },
+    {
+      "epoch": 3.796620398310199,
+      "grad_norm": 0.048614613711833954,
+      "learning_rate": 0.00022841938114543994,
+      "loss": 0.0232,
+      "mean_token_accuracy": 0.992570984363556,
+      "num_tokens": 8952156.0,
+      "step": 1575
+    },
+    {
+      "epoch": 3.856970428485214,
+      "grad_norm": 0.07217000424861908,
+      "learning_rate": 0.00022148452101021426,
+      "loss": 0.0285,
+      "mean_token_accuracy": 0.9912155508995056,
+      "num_tokens": 9089351.0,
+      "step": 1600
+    },
+    {
+      "epoch": 3.9173204586602295,
+      "grad_norm": 0.037683308124542236,
+      "learning_rate": 0.0002145718254091014,
+      "loss": 0.0246,
+      "mean_token_accuracy": 0.99214375436306,
+      "num_tokens": 9237851.0,
+      "step": 1625
+    },
+    {
+      "epoch": 3.9776704888352445,
+      "grad_norm": 0.0592164620757103,
+      "learning_rate": 0.00020768666744761807,
+      "loss": 0.0251,
+      "mean_token_accuracy": 0.992121371626854,
+      "num_tokens": 9369536.0,
+      "step": 1650
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.0407879464328289,
+      "eval_mean_token_accuracy": 0.9889527398186762,
+      "eval_num_tokens": 9416720.0,
+      "eval_runtime": 15.6983,
+      "eval_samples_per_second": 23.506,
+      "eval_steps_per_second": 11.785,
+      "step": 1660
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 2905,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 4.0910125805961216e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e321db5422f68207443830c649e098ab4918648692f5b03fd817fe9a80c1ed
+size 6097