upload fine tuning model

.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 +1,210 @@
+---
+base_model: ismaprasetiyadi/Biawak-8B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:ismaprasetiyadi/Biawak-8B-Base
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.18.0

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "ismaprasetiyadi/Biawak-8B-Base",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "down_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 sha256:1c40251ed9a8d51831e18e724bf3b732fabb118079ffa6cacba158719af22ea5
+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
+}

chat_template.jinja

@@ -0,0 +1,144 @@
+
+{%- if tools %}
+    {{- '<|im_start|>system
+' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '
+
+' }}
+    {%- endif %}
+    {{- "# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>" }}
+    {%- for tool in tools %}
+        {{- "
+" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{\"name\": <function-name>, \"arguments\": <args-json-object>}
+</tool_call><|im_end|>
+" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system
+' + messages[0].content + '<|im_end|>
+' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '
+' + message.content + '<|im_end|>' + '
+' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = (message.content.split('</think>')|last).lstrip('
+') %}
+                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('
+') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('
+') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '
+<think>
+' + reasoning_content.strip('
+') + '
+</think>
+
+' + content.lstrip('
+') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '
+' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '
+' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '
+' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>
+{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}
+</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>
+' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '
+<tool_response>
+' }}
+        {{- message.content }}
+        {{- '
+</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>
+' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant
+' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>
+
+</think>
+
+' }}
+    {%- endif %}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5edaa968405b8825456bf6b63287589c696fb791fe07966d4437732d11d54bc
+size 89251077

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a09a0dbe1b0dd4e8b12226739f335797927c1e94820312c55bdd16bbe59fdee
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea9dceb1aa198c4ab51767e3161cb5b5deeed4a28d0bd1c987687f08656919a
+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 +1,240 @@
+{
+  "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": 40960,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,637 @@
+{
+  "best_global_step": 540,
+  "best_metric": 0.6846529245376587,
+  "best_model_checkpoint": "./SFT-Biawak-8B-AGQ-9k-Unsloth/checkpoint-540",
+  "epoch": 1.0651851851851852,
+  "eval_steps": 20,
+  "global_step": 540,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019753086419753086,
+      "grad_norm": 0.12180884182453156,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 1.0077,
+      "step": 10
+    },
+    {
+      "epoch": 0.03950617283950617,
+      "grad_norm": 0.12343215197324753,
+      "learning_rate": 7.450980392156863e-06,
+      "loss": 1.0123,
+      "step": 20
+    },
+    {
+      "epoch": 0.03950617283950617,
+      "eval_loss": 1.008449673652649,
+      "eval_runtime": 693.1464,
+      "eval_samples_per_second": 1.298,
+      "eval_steps_per_second": 0.325,
+      "step": 20
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 0.10348870605230331,
+      "learning_rate": 1.1372549019607844e-05,
+      "loss": 1.0082,
+      "step": 30
+    },
+    {
+      "epoch": 0.07901234567901234,
+      "grad_norm": 0.07634297758340836,
+      "learning_rate": 1.5294117647058822e-05,
+      "loss": 1.0066,
+      "step": 40
+    },
+    {
+      "epoch": 0.07901234567901234,
+      "eval_loss": 0.981907844543457,
+      "eval_runtime": 692.8615,
+      "eval_samples_per_second": 1.299,
+      "eval_steps_per_second": 0.325,
+      "step": 40
+    },
+    {
+      "epoch": 0.09876543209876543,
+      "grad_norm": 0.08009450137615204,
+      "learning_rate": 1.9215686274509807e-05,
+      "loss": 0.9875,
+      "step": 50
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 0.07544852048158646,
+      "learning_rate": 1.983385254413292e-05,
+      "loss": 0.9598,
+      "step": 60
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "eval_loss": 0.942278265953064,
+      "eval_runtime": 692.9975,
+      "eval_samples_per_second": 1.299,
+      "eval_steps_per_second": 0.325,
+      "step": 60
+    },
+    {
+      "epoch": 0.1382716049382716,
+      "grad_norm": 0.07001063972711563,
+      "learning_rate": 1.9626168224299065e-05,
+      "loss": 0.9437,
+      "step": 70
+    },
+    {
+      "epoch": 0.1580246913580247,
+      "grad_norm": 0.071407251060009,
+      "learning_rate": 1.9418483904465214e-05,
+      "loss": 0.9285,
+      "step": 80
+    },
+    {
+      "epoch": 0.1580246913580247,
+      "eval_loss": 0.9138963222503662,
+      "eval_runtime": 692.9879,
+      "eval_samples_per_second": 1.299,
+      "eval_steps_per_second": 0.325,
+      "step": 80
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.07237081229686737,
+      "learning_rate": 1.9210799584631362e-05,
+      "loss": 0.9125,
+      "step": 90
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "grad_norm": 0.07662062346935272,
+      "learning_rate": 1.900311526479751e-05,
+      "loss": 0.9038,
+      "step": 100
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "eval_loss": 0.8946752548217773,
+      "eval_runtime": 691.8474,
+      "eval_samples_per_second": 1.301,
+      "eval_steps_per_second": 0.325,
+      "step": 100
+    },
+    {
+      "epoch": 0.21728395061728395,
+      "grad_norm": 0.08586585521697998,
+      "learning_rate": 1.8795430944963656e-05,
+      "loss": 0.897,
+      "step": 110
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 0.08783987909555435,
+      "learning_rate": 1.8587746625129804e-05,
+      "loss": 0.895,
+      "step": 120
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "eval_loss": 0.8792117238044739,
+      "eval_runtime": 692.2208,
+      "eval_samples_per_second": 1.3,
+      "eval_steps_per_second": 0.325,
+      "step": 120
+    },
+    {
+      "epoch": 0.25679012345679014,
+      "grad_norm": 0.09886828064918518,
+      "learning_rate": 1.8380062305295953e-05,
+      "loss": 0.9017,
+      "step": 130
+    },
+    {
+      "epoch": 0.2765432098765432,
+      "grad_norm": 0.09867409616708755,
+      "learning_rate": 1.81723779854621e-05,
+      "loss": 0.8908,
+      "step": 140
+    },
+    {
+      "epoch": 0.2765432098765432,
+      "eval_loss": 0.8661272525787354,
+      "eval_runtime": 691.9966,
+      "eval_samples_per_second": 1.301,
+      "eval_steps_per_second": 0.325,
+      "step": 140
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.10584826022386551,
+      "learning_rate": 1.7964693665628246e-05,
+      "loss": 0.8591,
+      "step": 150
+    },
+    {
+      "epoch": 0.3160493827160494,
+      "grad_norm": 0.11180440336465836,
+      "learning_rate": 1.7757009345794395e-05,
+      "loss": 0.8704,
+      "step": 160
+    },
+    {
+      "epoch": 0.3160493827160494,
+      "eval_loss": 0.853992760181427,
+      "eval_runtime": 691.8935,
+      "eval_samples_per_second": 1.301,
+      "eval_steps_per_second": 0.325,
+      "step": 160
+    },
+    {
+      "epoch": 0.3358024691358025,
+      "grad_norm": 0.10931171476840973,
+      "learning_rate": 1.7549325025960543e-05,
+      "loss": 0.8696,
+      "step": 170
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.1233023852109909,
+      "learning_rate": 1.734164070612669e-05,
+      "loss": 0.8648,
+      "step": 180
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 0.8424926996231079,
+      "eval_runtime": 691.9385,
+      "eval_samples_per_second": 1.301,
+      "eval_steps_per_second": 0.325,
+      "step": 180
+    },
+    {
+      "epoch": 0.37530864197530867,
+      "grad_norm": 0.12771755456924438,
+      "learning_rate": 1.7133956386292837e-05,
+      "loss": 0.8515,
+      "step": 190
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "grad_norm": 0.13220269978046417,
+      "learning_rate": 1.6926272066458985e-05,
+      "loss": 0.8463,
+      "step": 200
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "eval_loss": 0.8312501907348633,
+      "eval_runtime": 692.0848,
+      "eval_samples_per_second": 1.3,
+      "eval_steps_per_second": 0.325,
+      "step": 200
+    },
+    {
+      "epoch": 0.4148148148148148,
+      "grad_norm": 0.133916974067688,
+      "learning_rate": 1.671858774662513e-05,
+      "loss": 0.829,
+      "step": 210
+    },
+    {
+      "epoch": 0.4345679012345679,
+      "grad_norm": 0.15100638568401337,
+      "learning_rate": 1.651090342679128e-05,
+      "loss": 0.8313,
+      "step": 220
+    },
+    {
+      "epoch": 0.4345679012345679,
+      "eval_loss": 0.8192175030708313,
+      "eval_runtime": 692.3464,
+      "eval_samples_per_second": 1.3,
+      "eval_steps_per_second": 0.325,
+      "step": 220
+    },
+    {
+      "epoch": 0.454320987654321,
+      "grad_norm": 0.15603844821453094,
+      "learning_rate": 1.6303219106957427e-05,
+      "loss": 0.8194,
+      "step": 230
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 0.1611253321170807,
+      "learning_rate": 1.6095534787123576e-05,
+      "loss": 0.8229,
+      "step": 240
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "eval_loss": 0.8058387637138367,
+      "eval_runtime": 691.2488,
+      "eval_samples_per_second": 1.302,
+      "eval_steps_per_second": 0.325,
+      "step": 240
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.16903120279312134,
+      "learning_rate": 1.588785046728972e-05,
+      "loss": 0.8201,
+      "step": 250
+    },
+    {
+      "epoch": 0.5135802469135803,
+      "grad_norm": 0.19414032995700836,
+      "learning_rate": 1.568016614745587e-05,
+      "loss": 0.8225,
+      "step": 260
+    },
+    {
+      "epoch": 0.5135802469135803,
+      "eval_loss": 0.792759120464325,
+      "eval_runtime": 691.9927,
+      "eval_samples_per_second": 1.301,
+      "eval_steps_per_second": 0.325,
+      "step": 260
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.17173326015472412,
+      "learning_rate": 1.5472481827622018e-05,
+      "loss": 0.7943,
+      "step": 270
+    },
+    {
+      "epoch": 0.5530864197530864,
+      "grad_norm": 0.22506435215473175,
+      "learning_rate": 1.5264797507788163e-05,
+      "loss": 0.7864,
+      "step": 280
+    },
+    {
+      "epoch": 0.5530864197530864,
+      "eval_loss": 0.780030369758606,
+      "eval_runtime": 692.3772,
+      "eval_samples_per_second": 1.3,
+      "eval_steps_per_second": 0.325,
+      "step": 280
+    },
+    {
+      "epoch": 0.5728395061728395,
+      "grad_norm": 0.25333327054977417,
+      "learning_rate": 1.5057113187954311e-05,
+      "loss": 0.7867,
+      "step": 290
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.23071087896823883,
+      "learning_rate": 1.484942886812046e-05,
+      "loss": 0.7693,
+      "step": 300
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "eval_loss": 0.7666186690330505,
+      "eval_runtime": 692.4731,
+      "eval_samples_per_second": 1.3,
+      "eval_steps_per_second": 0.325,
+      "step": 300
+    },
+    {
+      "epoch": 0.6123456790123457,
+      "grad_norm": 0.20827655494213104,
+      "learning_rate": 1.4641744548286605e-05,
+      "loss": 0.7627,
+      "step": 310
+    },
+    {
+      "epoch": 0.6320987654320988,
+      "grad_norm": 0.21804091334342957,
+      "learning_rate": 1.4434060228452753e-05,
+      "loss": 0.779,
+      "step": 320
+    },
+    {
+      "epoch": 0.6320987654320988,
+      "eval_loss": 0.7543341517448425,
+      "eval_runtime": 691.6303,
+      "eval_samples_per_second": 1.301,
+      "eval_steps_per_second": 0.325,
+      "step": 320
+    },
+    {
+      "epoch": 0.6518518518518519,
+      "grad_norm": 0.2513262927532196,
+      "learning_rate": 1.4226375908618902e-05,
+      "loss": 0.7632,
+      "step": 330
+    },
+    {
+      "epoch": 0.671604938271605,
+      "grad_norm": 0.22374993562698364,
+      "learning_rate": 1.4018691588785047e-05,
+      "loss": 0.7493,
+      "step": 340
+    },
+    {
+      "epoch": 0.671604938271605,
+      "eval_loss": 0.7426387667655945,
+      "eval_runtime": 691.7042,
+      "eval_samples_per_second": 1.301,
+      "eval_steps_per_second": 0.325,
+      "step": 340
+    },
+    {
+      "epoch": 0.691358024691358,
+      "grad_norm": 0.2958984971046448,
+      "learning_rate": 1.3811007268951195e-05,
+      "loss": 0.7565,
+      "step": 350
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.2920616567134857,
+      "learning_rate": 1.3603322949117344e-05,
+      "loss": 0.7366,
+      "step": 360
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 0.7326313853263855,
+      "eval_runtime": 692.604,
+      "eval_samples_per_second": 1.299,
+      "eval_steps_per_second": 0.325,
+      "step": 360
+    },
+    {
+      "epoch": 0.7308641975308642,
+      "grad_norm": 0.2509481906890869,
+      "learning_rate": 1.3395638629283489e-05,
+      "loss": 0.74,
+      "step": 370
+    },
+    {
+      "epoch": 0.7506172839506173,
+      "grad_norm": 0.29313233494758606,
+      "learning_rate": 1.3187954309449637e-05,
+      "loss": 0.7237,
+      "step": 380
+    },
+    {
+      "epoch": 0.7506172839506173,
+      "eval_loss": 0.723445475101471,
+      "eval_runtime": 692.1563,
+      "eval_samples_per_second": 1.3,
+      "eval_steps_per_second": 0.325,
+      "step": 380
+    },
+    {
+      "epoch": 0.7703703703703704,
+      "grad_norm": 0.26945945620536804,
+      "learning_rate": 1.2980269989615786e-05,
+      "loss": 0.7278,
+      "step": 390
+    },
+    {
+      "epoch": 0.7901234567901234,
+      "grad_norm": 0.27647626399993896,
+      "learning_rate": 1.2772585669781932e-05,
+      "loss": 0.7245,
+      "step": 400
+    },
+    {
+      "epoch": 0.7901234567901234,
+      "eval_loss": 0.71584552526474,
+      "eval_runtime": 690.8883,
+      "eval_samples_per_second": 1.303,
+      "eval_steps_per_second": 0.326,
+      "step": 400
+    },
+    {
+      "epoch": 0.8098765432098766,
+      "grad_norm": 0.3796406090259552,
+      "learning_rate": 1.256490134994808e-05,
+      "loss": 0.7169,
+      "step": 410
+    },
+    {
+      "epoch": 0.8296296296296296,
+      "grad_norm": 0.3447484076023102,
+      "learning_rate": 1.2357217030114228e-05,
+      "loss": 0.7112,
+      "step": 420
+    },
+    {
+      "epoch": 0.8296296296296296,
+      "eval_loss": 0.7094859480857849,
+      "eval_runtime": 692.0984,
+      "eval_samples_per_second": 1.3,
+      "eval_steps_per_second": 0.325,
+      "step": 420
+    },
+    {
+      "epoch": 0.8493827160493828,
+      "grad_norm": 0.29176393151283264,
+      "learning_rate": 1.2149532710280374e-05,
+      "loss": 0.7167,
+      "step": 430
+    },
+    {
+      "epoch": 0.8691358024691358,
+      "grad_norm": 0.29126060009002686,
+      "learning_rate": 1.1941848390446523e-05,
+      "loss": 0.7202,
+      "step": 440
+    },
+    {
+      "epoch": 0.8691358024691358,
+      "eval_loss": 0.703975260257721,
+      "eval_runtime": 692.3797,
+      "eval_samples_per_second": 1.3,
+      "eval_steps_per_second": 0.325,
+      "step": 440
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.3009716272354126,
+      "learning_rate": 1.173416407061267e-05,
+      "loss": 0.7076,
+      "step": 450
+    },
+    {
+      "epoch": 0.908641975308642,
+      "grad_norm": 0.25401803851127625,
+      "learning_rate": 1.1526479750778816e-05,
+      "loss": 0.6981,
+      "step": 460
+    },
+    {
+      "epoch": 0.908641975308642,
+      "eval_loss": 0.6991094350814819,
+      "eval_runtime": 692.4866,
+      "eval_samples_per_second": 1.3,
+      "eval_steps_per_second": 0.325,
+      "step": 460
+    },
+    {
+      "epoch": 0.928395061728395,
+      "grad_norm": 0.2538835108280182,
+      "learning_rate": 1.1318795430944965e-05,
+      "loss": 0.7078,
+      "step": 470
+    },
+    {
+      "epoch": 0.9481481481481482,
+      "grad_norm": 0.26919299364089966,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.7081,
+      "step": 480
+    },
+    {
+      "epoch": 0.9481481481481482,
+      "eval_loss": 0.6949476003646851,
+      "eval_runtime": 692.5011,
+      "eval_samples_per_second": 1.3,
+      "eval_steps_per_second": 0.325,
+      "step": 480
+    },
+    {
+      "epoch": 0.9679012345679012,
+      "grad_norm": 0.28486502170562744,
+      "learning_rate": 1.0903426791277258e-05,
+      "loss": 0.7063,
+      "step": 490
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.2884429693222046,
+      "learning_rate": 1.0695742471443407e-05,
+      "loss": 0.7015,
+      "step": 500
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "eval_loss": 0.6906960606575012,
+      "eval_runtime": 692.568,
+      "eval_samples_per_second": 1.3,
+      "eval_steps_per_second": 0.325,
+      "step": 500
+    },
+    {
+      "epoch": 1.005925925925926,
+      "grad_norm": 0.2989191710948944,
+      "learning_rate": 1.0488058151609555e-05,
+      "loss": 0.7051,
+      "step": 510
+    },
+    {
+      "epoch": 1.025679012345679,
+      "grad_norm": 0.2781642973423004,
+      "learning_rate": 1.02803738317757e-05,
+      "loss": 0.6887,
+      "step": 520
+    },
+    {
+      "epoch": 1.025679012345679,
+      "eval_loss": 0.6878499388694763,
+      "eval_runtime": 691.8346,
+      "eval_samples_per_second": 1.301,
+      "eval_steps_per_second": 0.325,
+      "step": 520
+    },
+    {
+      "epoch": 1.0454320987654322,
+      "grad_norm": 0.27174291014671326,
+      "learning_rate": 1.0072689511941849e-05,
+      "loss": 0.6905,
+      "step": 530
+    },
+    {
+      "epoch": 1.0651851851851852,
+      "grad_norm": 0.28336238861083984,
+      "learning_rate": 9.865005192107997e-06,
+      "loss": 0.6933,
+      "step": 540
+    },
+    {
+      "epoch": 1.0651851851851852,
+      "eval_loss": 0.6846529245376587,
+      "eval_runtime": 691.686,
+      "eval_samples_per_second": 1.301,
+      "eval_steps_per_second": 0.325,
+      "step": 540
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1014,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3008860904594637e+18,
+  "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:dbf066235a28e7ce71c84c2164b22451100f86885df066960a369f787418554a
+size 6353