Upload 15 files

.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

@@ -1,3 +1,208 @@
----
-license: apache-2.0
----
+---
+base_model: Qwen2.5-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen2.5-1.5B-Instruct
+- 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 +1,33 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "block_share": false,
+  "coft": false,
+  "eps": 6e-05,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "module_dropout": 0.0,
+  "modules_to_save": null,
+  "num_cayley_neumann_terms": 5,
+  "oft_block_size": 32,
+  "peft_type": "OFT",
+  "peft_version": "0.18.1",
+  "r": 0,
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_cayley_neumann": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6518d2f0a7ec415fb35d11a144c5dfed67f86c139cffcf23cc34ea36635d8778
+size 31579160

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 sha256:0d4e8af718f71ac16a84e76b7a7109f3ef1e99e6b7fc8bf1e89c634734dbbfe1
+size 63272459

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428aed83766f09a6a2d9ccfb86972eeda646225b3b0cd6accec4a90e4f900161
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6cffd29d107485fd65a3291d66df7b87424f25de973bb529c2fbe605d9c752
+size 1465

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 +1,664 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 25,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6712856006622314,
+      "epoch": 0.1,
+      "grad_norm": 0.6304148435592651,
+      "learning_rate": 0.0001999990663152786,
+      "loss": 2.0491,
+      "mean_token_accuracy": 0.6684889650344848,
+      "num_tokens": 122580.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "eval_entropy": 0.9992010481655598,
+      "eval_loss": 0.9745309948921204,
+      "eval_mean_token_accuracy": 0.815976720303297,
+      "eval_num_tokens": 122580.0,
+      "eval_runtime": 66.8951,
+      "eval_samples_per_second": 29.898,
+      "eval_steps_per_second": 0.478,
+      "step": 25
+    },
+    {
+      "entropy": 0.9771250176429749,
+      "epoch": 0.2,
+      "grad_norm": 0.4267440736293793,
+      "learning_rate": 0.0001993694918299864,
+      "loss": 0.9676,
+      "mean_token_accuracy": 0.8179380083084107,
+      "num_tokens": 244723.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "eval_entropy": 0.9376886244863272,
+      "eval_loss": 0.940742015838623,
+      "eval_mean_token_accuracy": 0.8212726972997189,
+      "eval_num_tokens": 244723.0,
+      "eval_runtime": 66.3094,
+      "eval_samples_per_second": 30.162,
+      "eval_steps_per_second": 0.483,
+      "step": 50
+    },
+    {
+      "entropy": 0.9467579674720764,
+      "epoch": 0.3,
+      "grad_norm": 0.39123401045799255,
+      "learning_rate": 0.0001975812958575343,
+      "loss": 0.9473,
+      "mean_token_accuracy": 0.820980327129364,
+      "num_tokens": 366803.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.3,
+      "eval_entropy": 0.930314002558589,
+      "eval_loss": 0.9318345785140991,
+      "eval_mean_token_accuracy": 0.8218902982771397,
+      "eval_num_tokens": 366803.0,
+      "eval_runtime": 66.1507,
+      "eval_samples_per_second": 30.234,
+      "eval_steps_per_second": 0.484,
+      "step": 75
+    },
+    {
+      "entropy": 0.9574691414833069,
+      "epoch": 0.4,
+      "grad_norm": 0.3710257112979889,
+      "learning_rate": 0.00019465532828090735,
+      "loss": 0.9545,
+      "mean_token_accuracy": 0.8186049485206603,
+      "num_tokens": 489374.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.4,
+      "eval_entropy": 0.9250399190932512,
+      "eval_loss": 0.927577555179596,
+      "eval_mean_token_accuracy": 0.8226032145321369,
+      "eval_num_tokens": 489374.0,
+      "eval_runtime": 66.6912,
+      "eval_samples_per_second": 29.989,
+      "eval_steps_per_second": 0.48,
+      "step": 100
+    },
+    {
+      "entropy": 0.9415939354896545,
+      "epoch": 0.5,
+      "grad_norm": 0.3609308898448944,
+      "learning_rate": 0.00019062570509327992,
+      "loss": 0.938,
+      "mean_token_accuracy": 0.8219008255004883,
+      "num_tokens": 611509.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.5,
+      "eval_entropy": 0.9134028796106577,
+      "eval_loss": 0.9236319661140442,
+      "eval_mean_token_accuracy": 0.8233284279704094,
+      "eval_num_tokens": 611509.0,
+      "eval_runtime": 67.9585,
+      "eval_samples_per_second": 29.43,
+      "eval_steps_per_second": 0.471,
+      "step": 125
+    },
+    {
+      "entropy": 0.9313359212875366,
+      "epoch": 0.6,
+      "grad_norm": 0.3689591586589813,
+      "learning_rate": 0.00018553941061473218,
+      "loss": 0.9277,
+      "mean_token_accuracy": 0.8244240188598633,
+      "num_tokens": 733437.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.6,
+      "eval_entropy": 0.9121778700500727,
+      "eval_loss": 0.9206869006156921,
+      "eval_mean_token_accuracy": 0.8243093993514776,
+      "eval_num_tokens": 733437.0,
+      "eval_runtime": 68.185,
+      "eval_samples_per_second": 29.332,
+      "eval_steps_per_second": 0.469,
+      "step": 150
+    },
+    {
+      "entropy": 0.9311716175079345,
+      "epoch": 0.7,
+      "grad_norm": 0.3817085027694702,
+      "learning_rate": 0.00017945574966774376,
+      "loss": 0.9292,
+      "mean_token_accuracy": 0.8232095694541931,
+      "num_tokens": 855571.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.7,
+      "eval_entropy": 0.9240057598799467,
+      "eval_loss": 0.9190523028373718,
+      "eval_mean_token_accuracy": 0.8243635054677725,
+      "eval_num_tokens": 855571.0,
+      "eval_runtime": 68.1745,
+      "eval_samples_per_second": 29.336,
+      "eval_steps_per_second": 0.469,
+      "step": 175
+    },
+    {
+      "entropy": 0.9368235039710998,
+      "epoch": 0.8,
+      "grad_norm": 0.343488872051239,
+      "learning_rate": 0.00017244565609895074,
+      "loss": 0.9328,
+      "mean_token_accuracy": 0.822948260307312,
+      "num_tokens": 977886.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.8,
+      "eval_entropy": 0.9235651567578316,
+      "eval_loss": 0.9163441061973572,
+      "eval_mean_token_accuracy": 0.8248479198664427,
+      "eval_num_tokens": 977886.0,
+      "eval_runtime": 68.3524,
+      "eval_samples_per_second": 29.26,
+      "eval_steps_per_second": 0.468,
+      "step": 200
+    },
+    {
+      "entropy": 0.9266206288337707,
+      "epoch": 0.9,
+      "grad_norm": 0.34697458148002625,
+      "learning_rate": 0.00016459086570961594,
+      "loss": 0.9247,
+      "mean_token_accuracy": 0.8257838773727417,
+      "num_tokens": 1099649.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.9,
+      "eval_entropy": 0.9170300494879484,
+      "eval_loss": 0.9154583215713501,
+      "eval_mean_token_accuracy": 0.8250364065170288,
+      "eval_num_tokens": 1099649.0,
+      "eval_runtime": 67.9598,
+      "eval_samples_per_second": 29.429,
+      "eval_steps_per_second": 0.471,
+      "step": 225
+    },
+    {
+      "entropy": 0.9486314964294433,
+      "epoch": 1.0,
+      "grad_norm": 0.38791951537132263,
+      "learning_rate": 0.00015598296323822024,
+      "loss": 0.9457,
+      "mean_token_accuracy": 0.8199513030052185,
+      "num_tokens": 1222434.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.9278132077306509,
+      "eval_loss": 0.9133847951889038,
+      "eval_mean_token_accuracy": 0.8252693247050047,
+      "eval_num_tokens": 1222434.0,
+      "eval_runtime": 67.957,
+      "eval_samples_per_second": 29.43,
+      "eval_steps_per_second": 0.471,
+      "step": 250
+    },
+    {
+      "entropy": 0.8935548496246338,
+      "epoch": 1.1,
+      "grad_norm": 0.3913302421569824,
+      "learning_rate": 0.00014672231450710066,
+      "loss": 0.8794,
+      "mean_token_accuracy": 0.8301347184181214,
+      "num_tokens": 1344769.0,
+      "step": 275
+    },
+    {
+      "epoch": 1.1,
+      "eval_entropy": 0.8964261263608932,
+      "eval_loss": 0.918248176574707,
+      "eval_mean_token_accuracy": 0.8246872704476118,
+      "eval_num_tokens": 1344769.0,
+      "eval_runtime": 67.949,
+      "eval_samples_per_second": 29.434,
+      "eval_steps_per_second": 0.471,
+      "step": 275
+    },
+    {
+      "entropy": 0.8727394843101501,
+      "epoch": 1.2,
+      "grad_norm": 0.39644864201545715,
+      "learning_rate": 0.00013691689618401835,
+      "loss": 0.8669,
+      "mean_token_accuracy": 0.8310828638076783,
+      "num_tokens": 1466893.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.2,
+      "eval_entropy": 0.8782581854611635,
+      "eval_loss": 0.917015552520752,
+      "eval_mean_token_accuracy": 0.8250990845263004,
+      "eval_num_tokens": 1466893.0,
+      "eval_runtime": 67.8451,
+      "eval_samples_per_second": 29.479,
+      "eval_steps_per_second": 0.472,
+      "step": 300
+    },
+    {
+      "entropy": 0.8778977513313293,
+      "epoch": 1.3,
+      "grad_norm": 0.3395286500453949,
+      "learning_rate": 0.00012668103680332012,
+      "loss": 0.876,
+      "mean_token_accuracy": 0.8312993144989014,
+      "num_tokens": 1589094.0,
+      "step": 325
+    },
+    {
+      "epoch": 1.3,
+      "eval_entropy": 0.8799433764070272,
+      "eval_loss": 0.9174618124961853,
+      "eval_mean_token_accuracy": 0.8249436803162098,
+      "eval_num_tokens": 1589094.0,
+      "eval_runtime": 68.1596,
+      "eval_samples_per_second": 29.343,
+      "eval_steps_per_second": 0.469,
+      "step": 325
+    },
+    {
+      "entropy": 0.8876111268997192,
+      "epoch": 1.4,
+      "grad_norm": 0.364728182554245,
+      "learning_rate": 0.00011613408372604825,
+      "loss": 0.8773,
+      "mean_token_accuracy": 0.8295953154563904,
+      "num_tokens": 1711583.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.4,
+      "eval_entropy": 0.85817476734519,
+      "eval_loss": 0.9163104295730591,
+      "eval_mean_token_accuracy": 0.8252090867608786,
+      "eval_num_tokens": 1711583.0,
+      "eval_runtime": 68.1812,
+      "eval_samples_per_second": 29.334,
+      "eval_steps_per_second": 0.469,
+      "step": 350
+    },
+    {
+      "entropy": 0.88423011302948,
+      "epoch": 1.5,
+      "grad_norm": 0.38693588972091675,
+      "learning_rate": 0.00010539901158188398,
+      "loss": 0.883,
+      "mean_token_accuracy": 0.8286035037040711,
+      "num_tokens": 1834553.0,
+      "step": 375
+    },
+    {
+      "epoch": 1.5,
+      "eval_entropy": 0.873553803190589,
+      "eval_loss": 0.9151167273521423,
+      "eval_mean_token_accuracy": 0.8254394326359034,
+      "eval_num_tokens": 1834553.0,
+      "eval_runtime": 68.1992,
+      "eval_samples_per_second": 29.326,
+      "eval_steps_per_second": 0.469,
+      "step": 375
+    },
+    {
+      "entropy": 0.8715341877937317,
+      "epoch": 1.6,
+      "grad_norm": 0.3770897686481476,
+      "learning_rate": 9.460098841811601e-05,
+      "loss": 0.87,
+      "mean_token_accuracy": 0.8320170021057129,
+      "num_tokens": 1956574.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.6,
+      "eval_entropy": 0.87935302965343,
+      "eval_loss": 0.9151723980903625,
+      "eval_mean_token_accuracy": 0.8255144450813532,
+      "eval_num_tokens": 1956574.0,
+      "eval_runtime": 67.9177,
+      "eval_samples_per_second": 29.447,
+      "eval_steps_per_second": 0.471,
+      "step": 400
+    },
+    {
+      "entropy": 0.8710586881637573,
+      "epoch": 1.7,
+      "grad_norm": 0.3885301351547241,
+      "learning_rate": 8.386591627395173e-05,
+      "loss": 0.8672,
+      "mean_token_accuracy": 0.8299804759025574,
+      "num_tokens": 2078811.0,
+      "step": 425
+    },
+    {
+      "epoch": 1.7,
+      "eval_entropy": 0.8739563841372728,
+      "eval_loss": 0.9149895906448364,
+      "eval_mean_token_accuracy": 0.8253704849630594,
+      "eval_num_tokens": 2078811.0,
+      "eval_runtime": 66.7099,
+      "eval_samples_per_second": 29.981,
+      "eval_steps_per_second": 0.48,
+      "step": 425
+    },
+    {
+      "entropy": 0.8689111661911011,
+      "epoch": 1.8,
+      "grad_norm": 0.38322678208351135,
+      "learning_rate": 7.33189631966799e-05,
+      "loss": 0.865,
+      "mean_token_accuracy": 0.8322654938697815,
+      "num_tokens": 2200571.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.8,
+      "eval_entropy": 0.8741269316524267,
+      "eval_loss": 0.9147102236747742,
+      "eval_mean_token_accuracy": 0.8253954574465752,
+      "eval_num_tokens": 2200571.0,
+      "eval_runtime": 66.1144,
+      "eval_samples_per_second": 30.251,
+      "eval_steps_per_second": 0.484,
+      "step": 450
+    },
+    {
+      "entropy": 0.8786772465705872,
+      "epoch": 1.9,
+      "grad_norm": 0.3754963278770447,
+      "learning_rate": 6.308310381598168e-05,
+      "loss": 0.8755,
+      "mean_token_accuracy": 0.8297365355491638,
+      "num_tokens": 2322788.0,
+      "step": 475
+    },
+    {
+      "epoch": 1.9,
+      "eval_entropy": 0.8773031029850245,
+      "eval_loss": 0.9134438633918762,
+      "eval_mean_token_accuracy": 0.8253685813397169,
+      "eval_num_tokens": 2322788.0,
+      "eval_runtime": 66.1468,
+      "eval_samples_per_second": 30.236,
+      "eval_steps_per_second": 0.484,
+      "step": 475
+    },
+    {
+      "entropy": 0.8698205542564392,
+      "epoch": 2.0,
+      "grad_norm": 0.37209320068359375,
+      "learning_rate": 5.327768549289934e-05,
+      "loss": 0.8654,
+      "mean_token_accuracy": 0.8314353656768799,
+      "num_tokens": 2444868.0,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.874303799122572,
+      "eval_loss": 0.9136784076690674,
+      "eval_mean_token_accuracy": 0.8255054354667664,
+      "eval_num_tokens": 2444868.0,
+      "eval_runtime": 65.7882,
+      "eval_samples_per_second": 30.401,
+      "eval_steps_per_second": 0.486,
+      "step": 500
+    },
+    {
+      "entropy": 0.8443045258522034,
+      "epoch": 2.1,
+      "grad_norm": 0.3855106830596924,
+      "learning_rate": 4.4017036761779787e-05,
+      "loss": 0.8248,
+      "mean_token_accuracy": 0.8369424676895142,
+      "num_tokens": 2567342.0,
+      "step": 525
+    },
+    {
+      "epoch": 2.1,
+      "eval_entropy": 0.8267646413296461,
+      "eval_loss": 0.9248229265213013,
+      "eval_mean_token_accuracy": 0.8247568681836128,
+      "eval_num_tokens": 2567342.0,
+      "eval_runtime": 66.4418,
+      "eval_samples_per_second": 30.102,
+      "eval_steps_per_second": 0.482,
+      "step": 525
+    },
+    {
+      "entropy": 0.8175929665565491,
+      "epoch": 2.2,
+      "grad_norm": 0.3969684839248657,
+      "learning_rate": 3.540913429038407e-05,
+      "loss": 0.8159,
+      "mean_token_accuracy": 0.8389404201507569,
+      "num_tokens": 2689296.0,
+      "step": 550
+    },
+    {
+      "epoch": 2.2,
+      "eval_entropy": 0.8400543294847012,
+      "eval_loss": 0.9235786199569702,
+      "eval_mean_token_accuracy": 0.8250540643930435,
+      "eval_num_tokens": 2689296.0,
+      "eval_runtime": 66.682,
+      "eval_samples_per_second": 29.993,
+      "eval_steps_per_second": 0.48,
+      "step": 550
+    },
+    {
+      "entropy": 0.8221414375305176,
+      "epoch": 2.3,
+      "grad_norm": 0.4103279709815979,
+      "learning_rate": 2.7554343901049294e-05,
+      "loss": 0.8108,
+      "mean_token_accuracy": 0.8397244310379028,
+      "num_tokens": 2811102.0,
+      "step": 575
+    },
+    {
+      "epoch": 2.3,
+      "eval_entropy": 0.8320044614374638,
+      "eval_loss": 0.9250128269195557,
+      "eval_mean_token_accuracy": 0.8249792046844959,
+      "eval_num_tokens": 2811102.0,
+      "eval_runtime": 68.2399,
+      "eval_samples_per_second": 29.308,
+      "eval_steps_per_second": 0.469,
+      "step": 575
+    },
+    {
+      "entropy": 0.8239590454101563,
+      "epoch": 2.4,
+      "grad_norm": 0.4046800434589386,
+      "learning_rate": 2.0544250332256276e-05,
+      "loss": 0.8193,
+      "mean_token_accuracy": 0.8385440015792847,
+      "num_tokens": 2933467.0,
+      "step": 600
+    },
+    {
+      "epoch": 2.4,
+      "eval_entropy": 0.8278196454048157,
+      "eval_loss": 0.9243917465209961,
+      "eval_mean_token_accuracy": 0.82486542314291,
+      "eval_num_tokens": 2933467.0,
+      "eval_runtime": 68.1284,
+      "eval_samples_per_second": 29.356,
+      "eval_steps_per_second": 0.47,
+      "step": 600
+    },
+    {
+      "entropy": 0.8189333271980286,
+      "epoch": 2.5,
+      "grad_norm": 0.38442716002464294,
+      "learning_rate": 1.4460589385267842e-05,
+      "loss": 0.8178,
+      "mean_token_accuracy": 0.8380931878089904,
+      "num_tokens": 3055276.0,
+      "step": 625
+    },
+    {
+      "epoch": 2.5,
+      "eval_entropy": 0.8392351847141981,
+      "eval_loss": 0.9240784645080566,
+      "eval_mean_token_accuracy": 0.8248794414103031,
+      "eval_num_tokens": 3055276.0,
+      "eval_runtime": 68.2247,
+      "eval_samples_per_second": 29.315,
+      "eval_steps_per_second": 0.469,
+      "step": 625
+    },
+    {
+      "entropy": 0.8184775829315185,
+      "epoch": 2.6,
+      "grad_norm": 0.42365893721580505,
+      "learning_rate": 9.374294906720082e-06,
+      "loss": 0.8096,
+      "mean_token_accuracy": 0.8411558413505554,
+      "num_tokens": 3176654.0,
+      "step": 650
+    },
+    {
+      "epoch": 2.6,
+      "eval_entropy": 0.8347331862896681,
+      "eval_loss": 0.9245245456695557,
+      "eval_mean_token_accuracy": 0.8248291350901127,
+      "eval_num_tokens": 3176654.0,
+      "eval_runtime": 67.8139,
+      "eval_samples_per_second": 29.492,
+      "eval_steps_per_second": 0.472,
+      "step": 650
+    },
+    {
+      "entropy": 0.8422538375854492,
+      "epoch": 2.7,
+      "grad_norm": 0.410686194896698,
+      "learning_rate": 5.344671719092664e-06,
+      "loss": 0.8453,
+      "mean_token_accuracy": 0.832388162612915,
+      "num_tokens": 3299985.0,
+      "step": 675
+    },
+    {
+      "epoch": 2.7,
+      "eval_entropy": 0.8364100754261017,
+      "eval_loss": 0.9244425296783447,
+      "eval_mean_token_accuracy": 0.8246717043220997,
+      "eval_num_tokens": 3299985.0,
+      "eval_runtime": 67.9993,
+      "eval_samples_per_second": 29.412,
+      "eval_steps_per_second": 0.471,
+      "step": 675
+    },
+    {
+      "entropy": 0.8317058253288269,
+      "epoch": 2.8,
+      "grad_norm": 0.45394909381866455,
+      "learning_rate": 2.418704142465722e-06,
+      "loss": 0.8301,
+      "mean_token_accuracy": 0.8355569648742676,
+      "num_tokens": 3422725.0,
+      "step": 700
+    },
+    {
+      "epoch": 2.8,
+      "eval_entropy": 0.8373962622135878,
+      "eval_loss": 0.924216091632843,
+      "eval_mean_token_accuracy": 0.8247099295258522,
+      "eval_num_tokens": 3422725.0,
+      "eval_runtime": 67.6852,
+      "eval_samples_per_second": 29.549,
+      "eval_steps_per_second": 0.473,
+      "step": 700
+    },
+    {
+      "entropy": 0.8333729934692383,
+      "epoch": 2.9,
+      "grad_norm": 0.4409957230091095,
+      "learning_rate": 6.305081700136328e-07,
+      "loss": 0.8241,
+      "mean_token_accuracy": 0.83688227891922,
+      "num_tokens": 3545132.0,
+      "step": 725
+    },
+    {
+      "epoch": 2.9,
+      "eval_entropy": 0.8377762027084827,
+      "eval_loss": 0.924144446849823,
+      "eval_mean_token_accuracy": 0.824684476479888,
+      "eval_num_tokens": 3545132.0,
+      "eval_runtime": 68.0427,
+      "eval_samples_per_second": 29.393,
+      "eval_steps_per_second": 0.47,
+      "step": 725
+    },
+    {
+      "entropy": 0.8257460308074951,
+      "epoch": 3.0,
+      "grad_norm": 0.40077298879623413,
+      "learning_rate": 9.336847214269639e-10,
+      "loss": 0.8146,
+      "mean_token_accuracy": 0.8383808851242065,
+      "num_tokens": 3667302.0,
+      "step": 750
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.8377156592905521,
+      "eval_loss": 0.9241430759429932,
+      "eval_mean_token_accuracy": 0.8246781621128321,
+      "eval_num_tokens": 3667302.0,
+      "eval_runtime": 67.5858,
+      "eval_samples_per_second": 29.592,
+      "eval_steps_per_second": 0.473,
+      "step": 750
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.177111226528563e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c577c4230a20438cfda4e6e7dbc70fe516691639973ccf9eeab4f9b315f3712
+size 6353