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": [
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "o_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:f1ad531e2263b4a4c0dfb5a0f6c34cafba2ffb098cce266b53b685a1f8cceeac
+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 sha256:09f296960b719f3a9d5918e88f1b806ffb07feb65252deddb0a7343b416c1a9f
+size 1292087499

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8401b92d25d476e9ec6b38f25c4deaa341b791606c2cb2a3c119469db0e84ad
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f8ecaffebf91eb93f28ef945426cc3912353e25ed85e7bf9c37c3b59e7b39d
+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 +1,505 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1245,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.060350030175015085,
+      "grad_norm": 0.2716701030731201,
+      "learning_rate": 0.00013963636363636362,
+      "loss": 1.7977,
+      "mean_token_accuracy": 0.6328366297483444,
+      "num_tokens": 156326.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.12070006035003017,
+      "grad_norm": 0.2526017725467682,
+      "learning_rate": 0.00028509090909090905,
+      "loss": 0.8743,
+      "mean_token_accuracy": 0.7787316054105758,
+      "num_tokens": 282083.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.18105009052504525,
+      "grad_norm": 0.19058053195476532,
+      "learning_rate": 0.00043054545454545456,
+      "loss": 0.6236,
+      "mean_token_accuracy": 0.8299106657505035,
+      "num_tokens": 439671.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.24140012070006034,
+      "grad_norm": 0.21313656866550446,
+      "learning_rate": 0.000511980737353935,
+      "loss": 0.496,
+      "mean_token_accuracy": 0.8596594697237014,
+      "num_tokens": 567445.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.30175015087507545,
+      "grad_norm": 0.19823844730854034,
+      "learning_rate": 0.0005117937078575993,
+      "loss": 0.3458,
+      "mean_token_accuracy": 0.9001932269334794,
+      "num_tokens": 722851.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.3621001810500905,
+      "grad_norm": 0.2446502149105072,
+      "learning_rate": 0.0005114078548252564,
+      "loss": 0.3064,
+      "mean_token_accuracy": 0.911021100282669,
+      "num_tokens": 849117.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.4224502112251056,
+      "grad_norm": 0.1619698852300644,
+      "learning_rate": 0.0005108234781730571,
+      "loss": 0.2402,
+      "mean_token_accuracy": 0.930964640378952,
+      "num_tokens": 1007875.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.4828002414001207,
+      "grad_norm": 0.27491629123687744,
+      "learning_rate": 0.0005100410321257489,
+      "loss": 0.2161,
+      "mean_token_accuracy": 0.938733617067337,
+      "num_tokens": 1135042.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.5431502715751357,
+      "grad_norm": 0.18663127720355988,
+      "learning_rate": 0.0005090611248636156,
+      "loss": 0.1748,
+      "mean_token_accuracy": 0.9507552969455719,
+      "num_tokens": 1294935.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.6035003017501509,
+      "grad_norm": 0.23655210435390472,
+      "learning_rate": 0.0005078845180497507,
+      "loss": 0.1534,
+      "mean_token_accuracy": 0.9558097630739212,
+      "num_tokens": 1421875.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.663850331925166,
+      "grad_norm": 0.1793680489063263,
+      "learning_rate": 0.0005065121262380311,
+      "loss": 0.1339,
+      "mean_token_accuracy": 0.9624842357635498,
+      "num_tokens": 1582177.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.724200362100181,
+      "grad_norm": 0.21529488265514374,
+      "learning_rate": 0.0005049450161622521,
+      "loss": 0.1082,
+      "mean_token_accuracy": 0.9684510946273803,
+      "num_tokens": 1709697.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.7845503922751962,
+      "grad_norm": 0.10737641900777817,
+      "learning_rate": 0.0005031844059069758,
+      "loss": 0.1139,
+      "mean_token_accuracy": 0.9678166025876999,
+      "num_tokens": 1866595.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.8449004224502112,
+      "grad_norm": 0.25487855076789856,
+      "learning_rate": 0.0005012316639607367,
+      "loss": 0.1061,
+      "mean_token_accuracy": 0.9704786598682403,
+      "num_tokens": 1992513.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.9052504526252263,
+      "grad_norm": 0.11293583363294601,
+      "learning_rate": 0.000499088308152343,
+      "loss": 0.1044,
+      "mean_token_accuracy": 0.9708359962701798,
+      "num_tokens": 2148616.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.9656004828002414,
+      "grad_norm": 0.24543644487857819,
+      "learning_rate": 0.0004967560044710963,
+      "loss": 0.0913,
+      "mean_token_accuracy": 0.9756689429283142,
+      "num_tokens": 2275044.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.08796942234039307,
+      "eval_mean_token_accuracy": 0.9756118339461249,
+      "eval_num_tokens": 2354180.0,
+      "eval_runtime": 15.8439,
+      "eval_samples_per_second": 23.29,
+      "eval_steps_per_second": 11.676,
+      "step": 415
+    },
+    {
+      "epoch": 1.024140012070006,
+      "grad_norm": 0.11087150126695633,
+      "learning_rate": 0.0004942365657718508,
+      "loss": 0.086,
+      "mean_token_accuracy": 0.9767568179012573,
+      "num_tokens": 2421983.0,
+      "step": 425
+    },
+    {
+      "epoch": 1.0844900422450212,
+      "grad_norm": 0.13107234239578247,
+      "learning_rate": 0.0004915319503659158,
+      "loss": 0.0582,
+      "mean_token_accuracy": 0.9829362910985947,
+      "num_tokens": 2563714.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.1448400724200363,
+      "grad_norm": 0.08740212023258209,
+      "learning_rate": 0.0004886442604988977,
+      "loss": 0.0729,
+      "mean_token_accuracy": 0.978913226723671,
+      "num_tokens": 2705420.0,
+      "step": 475
+    },
+    {
+      "epoch": 1.2051901025950513,
+      "grad_norm": 0.106731116771698,
+      "learning_rate": 0.0004855757407166656,
+      "loss": 0.0571,
+      "mean_token_accuracy": 0.9836699557304383,
+      "num_tokens": 2846774.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.2655401327700664,
+      "grad_norm": 0.08578667789697647,
+      "learning_rate": 0.00048232877612070814,
+      "loss": 0.0772,
+      "mean_token_accuracy": 0.9792935186624527,
+      "num_tokens": 2988445.0,
+      "step": 525
+    },
+    {
+      "epoch": 1.3258901629450814,
+      "grad_norm": 0.07904712110757828,
+      "learning_rate": 0.0004789058905142402,
+      "loss": 0.0509,
+      "mean_token_accuracy": 0.985254094004631,
+      "num_tokens": 3131701.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.3862401931200965,
+      "grad_norm": 0.08005515486001968,
+      "learning_rate": 0.0004753097444404994,
+      "loss": 0.0672,
+      "mean_token_accuracy": 0.9816042059659957,
+      "num_tokens": 3273618.0,
+      "step": 575
+    },
+    {
+      "epoch": 1.4465902232951118,
+      "grad_norm": 0.11021016538143158,
+      "learning_rate": 0.0004715431331147565,
+      "loss": 0.0522,
+      "mean_token_accuracy": 0.9851613295078278,
+      "num_tokens": 3417492.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.5069402534701268,
+      "grad_norm": 0.12960106134414673,
+      "learning_rate": 0.0004676089842516484,
+      "loss": 0.0725,
+      "mean_token_accuracy": 0.9796771186590195,
+      "num_tokens": 3560878.0,
+      "step": 625
+    },
+    {
+      "epoch": 1.567290283645142,
+      "grad_norm": 0.14702805876731873,
+      "learning_rate": 0.00046351035578952207,
+      "loss": 0.0469,
+      "mean_token_accuracy": 0.986492536664009,
+      "num_tokens": 3704626.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.627640313820157,
+      "grad_norm": 0.07580998539924622,
+      "learning_rate": 0.0004592504335135573,
+      "loss": 0.0634,
+      "mean_token_accuracy": 0.9821663647890091,
+      "num_tokens": 3847508.0,
+      "step": 675
+    },
+    {
+      "epoch": 1.687990343995172,
+      "grad_norm": 0.10504812747240067,
+      "learning_rate": 0.0004548325285795178,
+      "loss": 0.0478,
+      "mean_token_accuracy": 0.9862841880321502,
+      "num_tokens": 3989632.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.748340374170187,
+      "grad_norm": 0.09579284489154816,
+      "learning_rate": 0.00045026007494005255,
+      "loss": 0.0627,
+      "mean_token_accuracy": 0.9824772262573243,
+      "num_tokens": 4130651.0,
+      "step": 725
+    },
+    {
+      "epoch": 1.8086904043452021,
+      "grad_norm": 0.09132307767868042,
+      "learning_rate": 0.0004455366266755509,
+      "loss": 0.0453,
+      "mean_token_accuracy": 0.9872566330432891,
+      "num_tokens": 4272783.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.8690404345202172,
+      "grad_norm": 0.11937957257032394,
+      "learning_rate": 0.00044066585523162415,
+      "loss": 0.0623,
+      "mean_token_accuracy": 0.9824487656354904,
+      "num_tokens": 4413897.0,
+      "step": 775
+    },
+    {
+      "epoch": 1.9293904646952322,
+      "grad_norm": 0.10511502623558044,
+      "learning_rate": 0.0004356515465653613,
+      "loss": 0.0445,
+      "mean_token_accuracy": 0.98703648686409,
+      "num_tokens": 4556054.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.9897404948702473,
+      "grad_norm": 0.07509177178144455,
+      "learning_rate": 0.000430497598202577,
+      "loss": 0.0534,
+      "mean_token_accuracy": 0.9852619272470474,
+      "num_tokens": 4688140.0,
+      "step": 825
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.05571499839425087,
+      "eval_mean_token_accuracy": 0.9846324215064177,
+      "eval_num_tokens": 4708360.0,
+      "eval_runtime": 15.8265,
+      "eval_samples_per_second": 23.315,
+      "eval_steps_per_second": 11.689,
+      "step": 830
+    },
+    {
+      "epoch": 2.048280024140012,
+      "grad_norm": 0.10296711325645447,
+      "learning_rate": 0.0004252080162083404,
+      "loss": 0.0488,
+      "mean_token_accuracy": 0.9856051372498581,
+      "num_tokens": 4834012.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.1086300543150274,
+      "grad_norm": 0.13229815661907196,
+      "learning_rate": 0.0004197869120731367,
+      "loss": 0.0341,
+      "mean_token_accuracy": 0.9902466797828674,
+      "num_tokens": 4965876.0,
+      "step": 875
+    },
+    {
+      "epoch": 2.1689800844900424,
+      "grad_norm": 0.10297457873821259,
+      "learning_rate": 0.0004142384995170855,
+      "loss": 0.0452,
+      "mean_token_accuracy": 0.986401349902153,
+      "num_tokens": 5119378.0,
+      "step": 900
+    },
+    {
+      "epoch": 2.2293301146650575,
+      "grad_norm": 0.04365512356162071,
+      "learning_rate": 0.0004085670912146964,
+      "loss": 0.031,
+      "mean_token_accuracy": 0.9906719970703125,
+      "num_tokens": 5252167.0,
+      "step": 925
+    },
+    {
+      "epoch": 2.2896801448400725,
+      "grad_norm": 0.04382198303937912,
+      "learning_rate": 0.0004027770954427105,
+      "loss": 0.0487,
+      "mean_token_accuracy": 0.9857749968767167,
+      "num_tokens": 5403450.0,
+      "step": 950
+    },
+    {
+      "epoch": 2.3500301750150876,
+      "grad_norm": 0.10280822962522507,
+      "learning_rate": 0.00039687301265363086,
+      "loss": 0.033,
+      "mean_token_accuracy": 0.99033636033535,
+      "num_tokens": 5535695.0,
+      "step": 975
+    },
+    {
+      "epoch": 2.4103802051901027,
+      "grad_norm": 0.04137711599469185,
+      "learning_rate": 0.00039085943197760806,
+      "loss": 0.0446,
+      "mean_token_accuracy": 0.9868948411941528,
+      "num_tokens": 5686536.0,
+      "step": 1000
+    },
+    {
+      "epoch": 2.4707302353651177,
+      "grad_norm": 0.04095058888196945,
+      "learning_rate": 0.00038474102765539666,
+      "loss": 0.0324,
+      "mean_token_accuracy": 0.990428722500801,
+      "num_tokens": 5819478.0,
+      "step": 1025
+    },
+    {
+      "epoch": 2.5310802655401328,
+      "grad_norm": 0.06750275939702988,
+      "learning_rate": 0.0003785225554051583,
+      "loss": 0.0484,
+      "mean_token_accuracy": 0.9855219483375549,
+      "num_tokens": 5973334.0,
+      "step": 1050
+    },
+    {
+      "epoch": 2.591430295715148,
+      "grad_norm": 0.03156557306647301,
+      "learning_rate": 0.0003722088487259329,
+      "loss": 0.0301,
+      "mean_token_accuracy": 0.9906777936220169,
+      "num_tokens": 6106945.0,
+      "step": 1075
+    },
+    {
+      "epoch": 2.651780325890163,
+      "grad_norm": 0.0798354223370552,
+      "learning_rate": 0.00036580481514065285,
+      "loss": 0.041,
+      "mean_token_accuracy": 0.9879147779941558,
+      "num_tokens": 6258955.0,
+      "step": 1100
+    },
+    {
+      "epoch": 2.712130356065178,
+      "grad_norm": 0.0534820593893528,
+      "learning_rate": 0.00035931543238161963,
+      "loss": 0.031,
+      "mean_token_accuracy": 0.9908862364292145,
+      "num_tokens": 6391949.0,
+      "step": 1125
+    },
+    {
+      "epoch": 2.772480386240193,
+      "grad_norm": 0.0678093433380127,
+      "learning_rate": 0.0003527457445214084,
+      "loss": 0.0416,
+      "mean_token_accuracy": 0.9876690626144409,
+      "num_tokens": 6542859.0,
+      "step": 1150
+    },
+    {
+      "epoch": 2.832830416415208,
+      "grad_norm": 0.058269429951906204,
+      "learning_rate": 0.00034610085805220666,
+      "loss": 0.0288,
+      "mean_token_accuracy": 0.9910433840751648,
+      "num_tokens": 6676094.0,
+      "step": 1175
+    },
+    {
+      "epoch": 2.8931804465902236,
+      "grad_norm": 0.044238071888685226,
+      "learning_rate": 0.00033938593791663655,
+      "loss": 0.041,
+      "mean_token_accuracy": 0.9880746394395828,
+      "num_tokens": 6826469.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.9535304767652386,
+      "grad_norm": 0.02994498796761036,
+      "learning_rate": 0.0003326062034931439,
+      "loss": 0.0276,
+      "mean_token_accuracy": 0.9915395766496659,
+      "num_tokens": 6958335.0,
+      "step": 1225
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.04431217536330223,
+      "eval_mean_token_accuracy": 0.9878581050279979,
+      "eval_num_tokens": 7062540.0,
+      "eval_runtime": 15.7984,
+      "eval_samples_per_second": 23.357,
+      "eval_steps_per_second": 11.71,
+      "step": 1245
+    }
+  ],
+  "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": 3.068266812188928e+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 sha256:1d1cd585d92e1fab6c50d0a34d882d00289e6b0352aee1a1b083d95156c044d5
+size 6097