Upload task output zeus-gr-intercode-1780170064

.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: None
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/cache/models/Qwen--Qwen3-4B-Instruct-2507
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "up_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:ac4922b71d5f7f03e4a956f54dd9e9cc2d6272b667c897c61229dfe4b63c2802
+size 1057033224

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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 +1,61 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

loss.txt

@@ -0,0 +1 @@
+231,no_eval

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,448 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9978401727861771,
+  "eval_steps": 500,
+  "global_step": 231,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02159827213822894,
+      "grad_norm": 4.777818202972412,
+      "learning_rate": 1.1903333333333333e-05,
+      "loss": 1.7478,
+      "mean_token_accuracy": 0.673093843460083,
+      "num_tokens": 327041.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.04319654427645788,
+      "grad_norm": 1.6766164302825928,
+      "learning_rate": 2.6782500000000003e-05,
+      "loss": 1.1651,
+      "mean_token_accuracy": 0.7291636049747467,
+      "num_tokens": 654721.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.06479481641468683,
+      "grad_norm": 1.0733250379562378,
+      "learning_rate": 3.570453895221049e-05,
+      "loss": 0.6245,
+      "mean_token_accuracy": 0.8475371032953263,
+      "num_tokens": 981309.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.08639308855291576,
+      "grad_norm": 0.6415389180183411,
+      "learning_rate": 3.5643153305762796e-05,
+      "loss": 0.2271,
+      "mean_token_accuracy": 0.9391736060380935,
+      "num_tokens": 1307298.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.1079913606911447,
+      "grad_norm": 1.9687130451202393,
+      "learning_rate": 3.551386955429542e-05,
+      "loss": 0.1078,
+      "mean_token_accuracy": 0.9679672092199325,
+      "num_tokens": 1634102.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.12958963282937366,
+      "grad_norm": 0.43518000841140747,
+      "learning_rate": 3.531734649817135e-05,
+      "loss": 0.0894,
+      "mean_token_accuracy": 0.9722483873367309,
+      "num_tokens": 1960430.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.1511879049676026,
+      "grad_norm": 0.3164879381656647,
+      "learning_rate": 3.505458557383748e-05,
+      "loss": 0.0748,
+      "mean_token_accuracy": 0.9752993941307068,
+      "num_tokens": 2287205.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.17278617710583152,
+      "grad_norm": 12.315321922302246,
+      "learning_rate": 3.472692575073402e-05,
+      "loss": 0.0617,
+      "mean_token_accuracy": 0.9788013488054276,
+      "num_tokens": 2614608.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.19438444924406048,
+      "grad_norm": 0.18295283615589142,
+      "learning_rate": 3.4336036708213154e-05,
+      "loss": 0.0579,
+      "mean_token_accuracy": 0.9799674391746521,
+      "num_tokens": 2942049.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.2159827213822894,
+      "grad_norm": 0.10459253937005997,
+      "learning_rate": 3.3883910327235794e-05,
+      "loss": 0.0456,
+      "mean_token_accuracy": 0.9840161263942718,
+      "num_tokens": 3268494.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.23758099352051837,
+      "grad_norm": 0.12234116345643997,
+      "learning_rate": 3.337285054020275e-05,
+      "loss": 0.0476,
+      "mean_token_accuracy": 0.9830995976924897,
+      "num_tokens": 3595171.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.2591792656587473,
+      "grad_norm": 0.12831856310367584,
+      "learning_rate": 3.280546159064337e-05,
+      "loss": 0.0443,
+      "mean_token_accuracy": 0.9843576639890671,
+      "num_tokens": 3922203.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.28077753779697623,
+      "grad_norm": 0.16520845890045166,
+      "learning_rate": 3.218463476258741e-05,
+      "loss": 0.0414,
+      "mean_token_accuracy": 0.9853224068880081,
+      "num_tokens": 4249258.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.3023758099352052,
+      "grad_norm": 0.5860384702682495,
+      "learning_rate": 3.151353364724442e-05,
+      "loss": 0.044,
+      "mean_token_accuracy": 0.9839389264583588,
+      "num_tokens": 4576500.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.32397408207343414,
+      "grad_norm": 0.15807564556598663,
+      "learning_rate": 3.0795578022068034e-05,
+      "loss": 0.0436,
+      "mean_token_accuracy": 0.9843764930963517,
+      "num_tokens": 4903657.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.34557235421166305,
+      "grad_norm": 0.10453962534666061,
+      "learning_rate": 3.003442642435402e-05,
+      "loss": 0.04,
+      "mean_token_accuracy": 0.9854078710079193,
+      "num_tokens": 5230081.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.367170626349892,
+      "grad_norm": 0.11286672949790955,
+      "learning_rate": 2.923395750817275e-05,
+      "loss": 0.0398,
+      "mean_token_accuracy": 0.9855783194303512,
+      "num_tokens": 5556925.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.38876889848812096,
+      "grad_norm": 0.2122899740934372,
+      "learning_rate": 2.8398250279637206e-05,
+      "loss": 0.0372,
+      "mean_token_accuracy": 0.9866322726011276,
+      "num_tokens": 5883992.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.4103671706263499,
+      "grad_norm": 0.12236664444208145,
+      "learning_rate": 2.753156331122277e-05,
+      "loss": 0.0403,
+      "mean_token_accuracy": 0.9852587074041367,
+      "num_tokens": 6210605.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.4319654427645788,
+      "grad_norm": 0.09743868559598923,
+      "learning_rate": 2.6638313041058053e-05,
+      "loss": 0.0363,
+      "mean_token_accuracy": 0.9869196385145187,
+      "num_tokens": 6537632.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.4535637149028078,
+      "grad_norm": 0.12190241366624832,
+      "learning_rate": 2.5723051267768538e-05,
+      "loss": 0.0357,
+      "mean_token_accuracy": 0.9869883239269257,
+      "num_tokens": 6864705.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.47516198704103674,
+      "grad_norm": 0.08914244920015335,
+      "learning_rate": 2.4790441955554125e-05,
+      "loss": 0.0375,
+      "mean_token_accuracy": 0.9862172365188598,
+      "num_tokens": 7192178.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.49676025917926564,
+      "grad_norm": 0.09364324063062668,
+      "learning_rate": 2.3845237467696704e-05,
+      "loss": 0.042,
+      "mean_token_accuracy": 0.9846871644258499,
+      "num_tokens": 7518769.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.5183585313174947,
+      "grad_norm": 0.1068236380815506,
+      "learning_rate": 2.2892254349606132e-05,
+      "loss": 0.0376,
+      "mean_token_accuracy": 0.9862382262945175,
+      "num_tokens": 7845781.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.5399568034557235,
+      "grad_norm": 0.08777054399251938,
+      "learning_rate": 2.1936348784808918e-05,
+      "loss": 0.041,
+      "mean_token_accuracy": 0.9851777613162994,
+      "num_tokens": 8172882.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.5615550755939525,
+      "grad_norm": 0.10713644325733185,
+      "learning_rate": 2.0982391848950114e-05,
+      "loss": 0.0382,
+      "mean_token_accuracy": 0.9860901892185211,
+      "num_tokens": 8499891.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.5831533477321814,
+      "grad_norm": 0.09616448730230331,
+      "learning_rate": 2.0035244687908377e-05,
+      "loss": 0.0357,
+      "mean_token_accuracy": 0.9870383441448212,
+      "num_tokens": 8827333.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.6047516198704104,
+      "grad_norm": 0.11250793933868408,
+      "learning_rate": 1.9099733746510814e-05,
+      "loss": 0.0373,
+      "mean_token_accuracy": 0.9865201264619827,
+      "num_tokens": 9153215.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.6263498920086393,
+      "grad_norm": 0.07551588118076324,
+      "learning_rate": 1.818062617407649e-05,
+      "loss": 0.0367,
+      "mean_token_accuracy": 0.9866218030452728,
+      "num_tokens": 9480065.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.6479481641468683,
+      "grad_norm": 0.15281730890274048,
+      "learning_rate": 1.7282605532116228e-05,
+      "loss": 0.0357,
+      "mean_token_accuracy": 0.9870801359415055,
+      "num_tokens": 9806285.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.6695464362850972,
+      "grad_norm": 0.07491156458854675,
+      "learning_rate": 1.641024792797671e-05,
+      "loss": 0.0346,
+      "mean_token_accuracy": 0.9874009698629379,
+      "num_tokens": 10133128.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.6911447084233261,
+      "grad_norm": 0.08615657687187195,
+      "learning_rate": 1.5567998696046392e-05,
+      "loss": 0.0328,
+      "mean_token_accuracy": 0.9880871474742889,
+      "num_tokens": 10459417.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.712742980561555,
+      "grad_norm": 0.09050696343183517,
+      "learning_rate": 1.4760149745350381e-05,
+      "loss": 0.0359,
+      "mean_token_accuracy": 0.9867339074611664,
+      "num_tokens": 10786059.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.734341252699784,
+      "grad_norm": 0.21551507711410522,
+      "learning_rate": 1.3990817688965879e-05,
+      "loss": 0.0373,
+      "mean_token_accuracy": 0.9864282488822937,
+      "num_tokens": 11112457.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.755939524838013,
+      "grad_norm": 0.07269071042537689,
+      "learning_rate": 1.3263922866705542e-05,
+      "loss": 0.036,
+      "mean_token_accuracy": 0.9867516905069351,
+      "num_tokens": 11439674.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.7775377969762419,
+      "grad_norm": 0.12428650259971619,
+      "learning_rate": 1.2583169367964404e-05,
+      "loss": 0.0378,
+      "mean_token_accuracy": 0.9861906915903091,
+      "num_tokens": 11766139.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.7991360691144709,
+      "grad_norm": 0.0770215094089508,
+      "learning_rate": 1.1952026156529388e-05,
+      "loss": 0.0362,
+      "mean_token_accuracy": 0.986765107512474,
+      "num_tokens": 12092848.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.8207343412526998,
+      "grad_norm": 0.07880507409572601,
+      "learning_rate": 1.1373709393535004e-05,
+      "loss": 0.0341,
+      "mean_token_accuracy": 0.9875539094209671,
+      "num_tokens": 12420090.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.8423326133909287,
+      "grad_norm": 0.09498883038759232,
+      "learning_rate": 1.085116604864341e-05,
+      "loss": 0.0305,
+      "mean_token_accuracy": 0.988871157169342,
+      "num_tokens": 12747362.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.8639308855291576,
+      "grad_norm": 0.10424337536096573,
+      "learning_rate": 1.038705888296252e-05,
+      "loss": 0.0347,
+      "mean_token_accuracy": 0.987392121553421,
+      "num_tokens": 13074826.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.8855291576673866,
+      "grad_norm": 0.09163855761289597,
+      "learning_rate": 9.983752880225764e-06,
+      "loss": 0.0342,
+      "mean_token_accuracy": 0.9873875081539154,
+      "num_tokens": 13400958.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.9071274298056156,
+      "grad_norm": 0.13818813860416412,
+      "learning_rate": 9.643303195377083e-06,
+      "loss": 0.0391,
+      "mean_token_accuracy": 0.9855553776025772,
+      "num_tokens": 13727990.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.9287257019438445,
+      "grad_norm": 0.07480086386203766,
+      "learning_rate": 9.367444681972418e-06,
+      "loss": 0.0371,
+      "mean_token_accuracy": 0.9866992443799972,
+      "num_tokens": 14055037.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.9503239740820735,
+      "grad_norm": 0.07980502396821976,
+      "learning_rate": 9.157583051763647e-06,
+      "loss": 0.0338,
+      "mean_token_accuracy": 0.9877716153860092,
+      "num_tokens": 14382589.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.9719222462203023,
+      "grad_norm": 0.1249043345451355,
+      "learning_rate": 9.014787711513727e-06,
+      "loss": 0.0328,
+      "mean_token_accuracy": 0.9879971414804458,
+      "num_tokens": 14709624.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.9935205183585313,
+      "grad_norm": 0.10734046995639801,
+      "learning_rate": 8.939786313544953e-06,
+      "loss": 0.0352,
+      "mean_token_accuracy": 0.987159937620163,
+      "num_tokens": 15036472.0,
+      "step": 230
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 232,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.531691228313682e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e360a74ad56d2f7b7e5920cb90907270267e8fc56c9b0314e80b018404b13a2
+size 6545