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

@@ -1,3 +1,209 @@
----
-license: apache-2.0
----
+---
+base_model: aitfindonesia/Bakti-8B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:aitfindonesia/Bakti-8B-Base
+- 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 0.17.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "aitfindonesia/Bakti-8B-Base",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "q_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 sha256:305bb4752e2e564be1438fe780dc3083cd0d5652bcc591078f23f9615d96fe87
+size 174655536

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
+}

additional_chat_templates/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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 %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- 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" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32166c9ca24e179ca13977c4c416d13c54c2b2ac5bfaca469a51e31d64fdf502
+size 349601867

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b64cdc88d9d46723a8c9c597d76b977831329c40c0f00f7277f4e8f134cad89
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d41284aa86e9a28ce75f484326acf4e27303a5e7fd4713525ca5b18b65ec03a4
+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: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": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,322 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.516535433070866,
+  "eval_steps": 50,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.9739606760442256,
+      "epoch": 0.12598425196850394,
+      "grad_norm": 0.968841016292572,
+      "learning_rate": 7.6e-05,
+      "loss": 2.2682,
+      "mean_token_accuracy": 0.5962976351380348,
+      "num_tokens": 99995.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.9236388027667999,
+      "epoch": 0.25196850393700787,
+      "grad_norm": 0.30187129974365234,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.9381,
+      "mean_token_accuracy": 0.7860403966158629,
+      "num_tokens": 200771.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.31496062992125984,
+      "eval_entropy": 0.7079527728587577,
+      "eval_loss": 0.6960555911064148,
+      "eval_mean_token_accuracy": 0.8306159124059497,
+      "eval_num_tokens": 251130.0,
+      "eval_runtime": 45.7017,
+      "eval_samples_per_second": 13.894,
+      "eval_steps_per_second": 6.958,
+      "step": 50
+    },
+    {
+      "entropy": 0.7168553218245506,
+      "epoch": 0.3779527559055118,
+      "grad_norm": 0.28825637698173523,
+      "learning_rate": 0.0001997808505782075,
+      "loss": 0.7182,
+      "mean_token_accuracy": 0.8267303571105004,
+      "num_tokens": 300943.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.647084547393024,
+      "epoch": 0.5039370078740157,
+      "grad_norm": 0.3307661712169647,
+      "learning_rate": 0.00019773242425416768,
+      "loss": 0.6472,
+      "mean_token_accuracy": 0.8401378501206637,
+      "num_tokens": 401448.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.6049567876383662,
+      "epoch": 0.6299212598425197,
+      "grad_norm": 0.3357570469379425,
+      "learning_rate": 0.00019357168190404936,
+      "loss": 0.6097,
+      "mean_token_accuracy": 0.8464727878570557,
+      "num_tokens": 501464.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.6299212598425197,
+      "eval_entropy": 0.60639403676087,
+      "eval_loss": 0.5814101696014404,
+      "eval_mean_token_accuracy": 0.8527061408795651,
+      "eval_num_tokens": 501464.0,
+      "eval_runtime": 45.6184,
+      "eval_samples_per_second": 13.92,
+      "eval_steps_per_second": 6.971,
+      "step": 100
+    },
+    {
+      "entropy": 0.580510495044291,
+      "epoch": 0.7559055118110236,
+      "grad_norm": 0.35506585240364075,
+      "learning_rate": 0.0001873885507225743,
+      "loss": 0.5852,
+      "mean_token_accuracy": 0.8522923283278943,
+      "num_tokens": 602072.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.5525572836399079,
+      "epoch": 0.8818897637795275,
+      "grad_norm": 0.3671925663948059,
+      "learning_rate": 0.00017931666831451536,
+      "loss": 0.5538,
+      "mean_token_accuracy": 0.8564509227871895,
+      "num_tokens": 701808.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.9448818897637795,
+      "eval_entropy": 0.5495308028452052,
+      "eval_loss": 0.5309950113296509,
+      "eval_mean_token_accuracy": 0.8605339890755948,
+      "eval_num_tokens": 751756.0,
+      "eval_runtime": 46.259,
+      "eval_samples_per_second": 13.727,
+      "eval_steps_per_second": 6.874,
+      "step": 150
+    },
+    {
+      "entropy": 0.5359916405964501,
+      "epoch": 1.0062992125984251,
+      "grad_norm": 0.3443862497806549,
+      "learning_rate": 0.0001695304943507677,
+      "loss": 0.5351,
+      "mean_token_accuracy": 0.8600816813450826,
+      "num_tokens": 800169.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.47207170017063615,
+      "epoch": 1.132283464566929,
+      "grad_norm": 0.4181714951992035,
+      "learning_rate": 0.0001582415399266036,
+      "loss": 0.4724,
+      "mean_token_accuracy": 0.8726930443197489,
+      "num_tokens": 899852.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.4565439449623227,
+      "epoch": 1.258267716535433,
+      "grad_norm": 0.45549947023391724,
+      "learning_rate": 0.00014569379611796137,
+      "loss": 0.4599,
+      "mean_token_accuracy": 0.875334644690156,
+      "num_tokens": 999653.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.258267716535433,
+      "eval_entropy": 0.4601464904141876,
+      "eval_loss": 0.5056809782981873,
+      "eval_mean_token_accuracy": 0.8665201171014294,
+      "eval_num_tokens": 999653.0,
+      "eval_runtime": 45.7221,
+      "eval_samples_per_second": 13.888,
+      "eval_steps_per_second": 6.955,
+      "step": 200
+    },
+    {
+      "entropy": 0.4486727064475417,
+      "epoch": 1.384251968503937,
+      "grad_norm": 0.4510684311389923,
+      "learning_rate": 0.00013215846053955683,
+      "loss": 0.4513,
+      "mean_token_accuracy": 0.878431486710906,
+      "num_tokens": 1100570.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.4511976413428783,
+      "epoch": 1.510236220472441,
+      "grad_norm": 0.44284847378730774,
+      "learning_rate": 0.00011792807588107357,
+      "loss": 0.4521,
+      "mean_token_accuracy": 0.8780730802565813,
+      "num_tokens": 1201178.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.573228346456693,
+      "eval_entropy": 0.46230017211077346,
+      "eval_loss": 0.4856663942337036,
+      "eval_mean_token_accuracy": 0.8700332990232503,
+      "eval_num_tokens": 1251074.0,
+      "eval_runtime": 45.5388,
+      "eval_samples_per_second": 13.944,
+      "eval_steps_per_second": 6.983,
+      "step": 250
+    },
+    {
+      "entropy": 0.451329773850739,
+      "epoch": 1.6362204724409448,
+      "grad_norm": 0.4431185722351074,
+      "learning_rate": 0.00010331020710675729,
+      "loss": 0.4531,
+      "mean_token_accuracy": 0.8772743601351977,
+      "num_tokens": 1301346.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.42816779650747777,
+      "epoch": 1.762204724409449,
+      "grad_norm": 0.45769160985946655,
+      "learning_rate": 8.862079397472553e-05,
+      "loss": 0.4285,
+      "mean_token_accuracy": 0.8827753882855177,
+      "num_tokens": 1401547.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.4320015098899603,
+      "epoch": 1.8881889763779527,
+      "grad_norm": 0.44558027386665344,
+      "learning_rate": 7.417732254970317e-05,
+      "loss": 0.4326,
+      "mean_token_accuracy": 0.8826998364180326,
+      "num_tokens": 1502107.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.8881889763779527,
+      "eval_entropy": 0.42231335453454805,
+      "eval_loss": 0.4666292071342468,
+      "eval_mean_token_accuracy": 0.875962255885766,
+      "eval_num_tokens": 1502107.0,
+      "eval_runtime": 46.1255,
+      "eval_samples_per_second": 13.767,
+      "eval_steps_per_second": 6.894,
+      "step": 300
+    },
+    {
+      "entropy": 0.4177426643009427,
+      "epoch": 2.0125984251968503,
+      "grad_norm": 0.42371708154678345,
+      "learning_rate": 6.0291963295035484e-05,
+      "loss": 0.4157,
+      "mean_token_accuracy": 0.8861905902246886,
+      "num_tokens": 1600674.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.3515403226017952,
+      "epoch": 2.1385826771653544,
+      "grad_norm": 0.5003436803817749,
+      "learning_rate": 4.726482405216125e-05,
+      "loss": 0.3405,
+      "mean_token_accuracy": 0.9042681198567152,
+      "num_tokens": 1700569.0,
+      "step": 340
+    },
+    {
+      "epoch": 2.2015748031496063,
+      "eval_entropy": 0.3585739609955242,
+      "eval_loss": 0.46917417645454407,
+      "eval_mean_token_accuracy": 0.8779247264442204,
+      "eval_num_tokens": 1750522.0,
+      "eval_runtime": 46.0421,
+      "eval_samples_per_second": 13.792,
+      "eval_steps_per_second": 6.907,
+      "step": 350
+    },
+    {
+      "entropy": 0.33075640462338923,
+      "epoch": 2.264566929133858,
+      "grad_norm": 0.5350939035415649,
+      "learning_rate": 3.537746373263589e-05,
+      "loss": 0.3258,
+      "mean_token_accuracy": 0.9079407677054405,
+      "num_tokens": 1800230.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.3440810150466859,
+      "epoch": 2.3905511811023623,
+      "grad_norm": 0.5540388822555542,
+      "learning_rate": 2.4886806912948035e-05,
+      "loss": 0.3391,
+      "mean_token_accuracy": 0.9038707241415977,
+      "num_tokens": 1900074.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.3350882642902434,
+      "epoch": 2.516535433070866,
+      "grad_norm": 0.630711019039154,
+      "learning_rate": 1.601959085755641e-05,
+      "loss": 0.3338,
+      "mean_token_accuracy": 0.9055462963879108,
+      "num_tokens": 2000844.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.516535433070866,
+      "eval_entropy": 0.3513495825559088,
+      "eval_loss": 0.46354979276657104,
+      "eval_mean_token_accuracy": 0.8799726563804554,
+      "eval_num_tokens": 2000844.0,
+      "eval_runtime": 45.6998,
+      "eval_samples_per_second": 13.895,
+      "eval_steps_per_second": 6.958,
+      "step": 400
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 477,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0208648418588672e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea544ee4df5535dc903400da197be4f25e71813f7ebf5ad99e56e85d71855cd
+size 6161