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
+checkpoint-189/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-189/README.md

@@ -0,0 +1,208 @@
+---
+base_model: /home/msalimi/.cache/huggingface/hub/models--Qwen--Qwen3-8B/snapshots/b968826d9c46dd6066d109eabc6255188de91218
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/home/msalimi/.cache/huggingface/hub/models--Qwen--Qwen3-8B/snapshots/b968826d9c46dd6066d109eabc6255188de91218
+- lora
+- transformers
+- 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 0.16.0

checkpoint-189/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/msalimi/.cache/huggingface/hub/models--Qwen--Qwen3-8B/snapshots/b968826d9c46dd6066d109eabc6255188de91218",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoint-189/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bad7363231e167cbf4804c8b16cd1782d1f92665bf137f1400657f57cbbb280
+size 2834270800

checkpoint-189/added_tokens.json

@@ -0,0 +1,33 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|analysis|>": 151670,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|forecast|>": 151671,
+  "<|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,
+  "<|response|>": 151669,
+  "<|risks|>": 151672,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652,
+  "<|watch|>": 151673
+}

checkpoint-189/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 %}

checkpoint-189/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503f6a120536d53cd4ead6d2a5216cc120240c438d361a9db205e71ec4a11d47
+size 698777675

checkpoint-189/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+size 14645

checkpoint-189/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f6bef68f1a79850e9c094ae1ada2d209bb00bda2944425e211ef8d4b2d7e85
+size 1383

checkpoint-189/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e289d876d03c20b388f5f807a607e2db6f294bac252ce11dd04a61be779745
+size 1465

checkpoint-189/special_tokens_map.json

@@ -0,0 +1,53 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|analysis|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|forecast|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|risks|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|watch|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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
+  }
+}

checkpoint-189/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d762e8901f35e3021e2a14e7adbfd455d87accaf4462388e94a634dd2e9f7042
+size 11423593

checkpoint-189/tokenizer_config.json

@@ -0,0 +1,272 @@
+{
+  "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
+    },
+    "151669": {
+      "content": "<|response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|analysis|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<|forecast|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<|risks|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<|watch|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|response|>",
+    "<|analysis|>",
+    "<|forecast|>",
+    "<|risks|>",
+    "<|watch|>"
+  ],
+  "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
+}

checkpoint-189/trainer_state.json

@@ -0,0 +1,692 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 189,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.031914893617021274,
+      "grad_norm": 0.01057420950382948,
+      "learning_rate": 2e-05,
+      "loss": 44.1284,
+      "step": 2
+    },
+    {
+      "epoch": 0.06382978723404255,
+      "grad_norm": 0.00569568807259202,
+      "learning_rate": 6e-05,
+      "loss": 24.3059,
+      "step": 4
+    },
+    {
+      "epoch": 0.09574468085106383,
+      "grad_norm": 0.0002239234745502472,
+      "learning_rate": 0.0001,
+      "loss": 5.7057,
+      "step": 6
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "grad_norm": 0.00011368857667548582,
+      "learning_rate": 0.00014,
+      "loss": 2.7636,
+      "step": 8
+    },
+    {
+      "epoch": 0.1595744680851064,
+      "grad_norm": 7.678678957745433e-05,
+      "learning_rate": 0.00018,
+      "loss": 2.4238,
+      "step": 10
+    },
+    {
+      "epoch": 0.19148936170212766,
+      "grad_norm": 5.5640477512497455e-05,
+      "learning_rate": 0.00019998459887166634,
+      "loss": 2.2322,
+      "step": 12
+    },
+    {
+      "epoch": 0.22340425531914893,
+      "grad_norm": 5.7497938541928306e-05,
+      "learning_rate": 0.00019986141830690625,
+      "loss": 2.1314,
+      "step": 14
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "grad_norm": 5.0512484449427575e-05,
+      "learning_rate": 0.00019961520893527383,
+      "loss": 2.07,
+      "step": 16
+    },
+    {
+      "epoch": 0.2872340425531915,
+      "grad_norm": 4.325133340898901e-05,
+      "learning_rate": 0.00019924627408557963,
+      "loss": 1.9946,
+      "step": 18
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 3.306111830170266e-05,
+      "learning_rate": 0.00019875506828385722,
+      "loss": 1.9009,
+      "step": 20
+    },
+    {
+      "epoch": 0.35106382978723405,
+      "grad_norm": 3.122422640444711e-05,
+      "learning_rate": 0.00019814219669338928,
+      "loss": 1.8646,
+      "step": 22
+    },
+    {
+      "epoch": 0.3829787234042553,
+      "grad_norm": 3.1440973543794826e-05,
+      "learning_rate": 0.00019740841436914917,
+      "loss": 1.7765,
+      "step": 24
+    },
+    {
+      "epoch": 0.4148936170212766,
+      "grad_norm": 3.0649629479739815e-05,
+      "learning_rate": 0.00019655462532757676,
+      "loss": 1.7768,
+      "step": 26
+    },
+    {
+      "epoch": 0.44680851063829785,
+      "grad_norm": 3.085639400524087e-05,
+      "learning_rate": 0.00019558188143283426,
+      "loss": 1.7292,
+      "step": 28
+    },
+    {
+      "epoch": 0.4787234042553192,
+      "grad_norm": 3.063358599320054e-05,
+      "learning_rate": 0.00019449138110091445,
+      "loss": 1.6946,
+      "step": 30
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 3.059727168874815e-05,
+      "learning_rate": 0.00019328446782319772,
+      "loss": 1.6523,
+      "step": 32
+    },
+    {
+      "epoch": 0.5425531914893617,
+      "grad_norm": 2.677715201571118e-05,
+      "learning_rate": 0.00019196262851127693,
+      "loss": 1.5993,
+      "step": 34
+    },
+    {
+      "epoch": 0.574468085106383,
+      "grad_norm": 2.4694048988749273e-05,
+      "learning_rate": 0.00019052749166508908,
+      "loss": 1.5847,
+      "step": 36
+    },
+    {
+      "epoch": 0.6063829787234043,
+      "grad_norm": 2.3815042368369177e-05,
+      "learning_rate": 0.00018898082536661094,
+      "loss": 1.5459,
+      "step": 38
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 2.301201493537519e-05,
+      "learning_rate": 0.00018732453510159026,
+      "loss": 1.4705,
+      "step": 40
+    },
+    {
+      "epoch": 0.6702127659574468,
+      "grad_norm": 2.2661988623440266e-05,
+      "learning_rate": 0.000185560661411996,
+      "loss": 1.4791,
+      "step": 42
+    },
+    {
+      "epoch": 0.7021276595744681,
+      "grad_norm": 2.276069608342368e-05,
+      "learning_rate": 0.0001836913773820802,
+      "loss": 1.4257,
+      "step": 44
+    },
+    {
+      "epoch": 0.7340425531914894,
+      "grad_norm": 2.1834361177752726e-05,
+      "learning_rate": 0.00018171898596114805,
+      "loss": 1.3968,
+      "step": 46
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 2.1417945390567183e-05,
+      "learning_rate": 0.00017964591712633498,
+      "loss": 1.3475,
+      "step": 48
+    },
+    {
+      "epoch": 0.7978723404255319,
+      "grad_norm": 2.2434667698689736e-05,
+      "learning_rate": 0.00017747472488888622,
+      "loss": 1.3387,
+      "step": 50
+    },
+    {
+      "epoch": 0.8297872340425532,
+      "grad_norm": 2.094592673529405e-05,
+      "learning_rate": 0.00017520808414762641,
+      "loss": 1.2859,
+      "step": 52
+    },
+    {
+      "epoch": 0.8617021276595744,
+      "grad_norm": 2.0795474483747967e-05,
+      "learning_rate": 0.0001728487873934969,
+      "loss": 1.2813,
+      "step": 54
+    },
+    {
+      "epoch": 0.8936170212765957,
+      "grad_norm": 1.884896119008772e-05,
+      "learning_rate": 0.00017039974126921946,
+      "loss": 1.2709,
+      "step": 56
+    },
+    {
+      "epoch": 0.925531914893617,
+      "grad_norm": 1.857211100286804e-05,
+      "learning_rate": 0.00016786396298832624,
+      "loss": 1.2611,
+      "step": 58
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 2.0264646082068793e-05,
+      "learning_rate": 0.00016524457661796626,
+      "loss": 1.2927,
+      "step": 60
+    },
+    {
+      "epoch": 0.9893617021276596,
+      "grad_norm": 1.7549693438922986e-05,
+      "learning_rate": 0.00016254480923006925,
+      "loss": 1.24,
+      "step": 62
+    },
+    {
+      "epoch": 1.0159574468085106,
+      "grad_norm": 1.7233558537554927e-05,
+      "learning_rate": 0.00015976798692560795,
+      "loss": 1.221,
+      "step": 64
+    },
+    {
+      "epoch": 1.047872340425532,
+      "grad_norm": 1.619356407900341e-05,
+      "learning_rate": 0.00015691753073685693,
+      "loss": 1.2402,
+      "step": 66
+    },
+    {
+      "epoch": 1.0797872340425532,
+      "grad_norm": 1.7525637304061092e-05,
+      "learning_rate": 0.00015399695241269666,
+      "loss": 1.2386,
+      "step": 68
+    },
+    {
+      "epoch": 1.1117021276595744,
+      "grad_norm": 1.548230829939712e-05,
+      "learning_rate": 0.0001510098500921552,
+      "loss": 1.2308,
+      "step": 70
+    },
+    {
+      "epoch": 1.1436170212765957,
+      "grad_norm": 1.5968664229149e-05,
+      "learning_rate": 0.00014795990387151718,
+      "loss": 1.2075,
+      "step": 72
+    },
+    {
+      "epoch": 1.175531914893617,
+      "grad_norm": 1.6628053344902582e-05,
+      "learning_rate": 0.00014485087127046254,
+      "loss": 1.2014,
+      "step": 74
+    },
+    {
+      "epoch": 1.2074468085106382,
+      "grad_norm": 3.447881681495346e-05,
+      "learning_rate": 0.00014168658260281945,
+      "loss": 1.1938,
+      "step": 76
+    },
+    {
+      "epoch": 1.2393617021276595,
+      "grad_norm": 1.562910620123148e-05,
+      "learning_rate": 0.00013847093625763516,
+      "loss": 1.2349,
+      "step": 78
+    },
+    {
+      "epoch": 1.2712765957446808,
+      "grad_norm": 1.557634459459223e-05,
+      "learning_rate": 0.000135207893896379,
+      "loss": 1.1785,
+      "step": 80
+    },
+    {
+      "epoch": 1.3031914893617023,
+      "grad_norm": 1.7386775652994402e-05,
+      "learning_rate": 0.00013190147557219338,
+      "loss": 1.1821,
+      "step": 82
+    },
+    {
+      "epoch": 1.3351063829787235,
+      "grad_norm": 1.5759645975776948e-05,
+      "learning_rate": 0.0001285557547772072,
+      "loss": 1.1664,
+      "step": 84
+    },
+    {
+      "epoch": 1.3670212765957448,
+      "grad_norm": 1.842792335082777e-05,
+      "learning_rate": 0.00012517485342401202,
+      "loss": 1.172,
+      "step": 86
+    },
+    {
+      "epoch": 1.398936170212766,
+      "grad_norm": 1.647455974307377e-05,
+      "learning_rate": 0.00012176293676748493,
+      "loss": 1.1512,
+      "step": 88
+    },
+    {
+      "epoch": 1.4308510638297873,
+      "grad_norm": 1.5937717762426473e-05,
+      "learning_rate": 0.00011832420827321373,
+      "loss": 1.1777,
+      "step": 90
+    },
+    {
+      "epoch": 1.4627659574468086,
+      "grad_norm": 1.6279354895232245e-05,
+      "learning_rate": 0.00011486290443884666,
+      "loss": 1.1755,
+      "step": 92
+    },
+    {
+      "epoch": 1.4946808510638299,
+      "grad_norm": 1.845241968112532e-05,
+      "learning_rate": 0.00011138328957474691,
+      "loss": 1.1567,
+      "step": 94
+    },
+    {
+      "epoch": 1.5265957446808511,
+      "grad_norm": 1.5724048353149556e-05,
+      "learning_rate": 0.00010788965055038178,
+      "loss": 1.136,
+      "step": 96
+    },
+    {
+      "epoch": 1.5585106382978724,
+      "grad_norm": 1.5909397916402668e-05,
+      "learning_rate": 0.00010438629151291943,
+      "loss": 1.1322,
+      "step": 98
+    },
+    {
+      "epoch": 1.5904255319148937,
+      "grad_norm": 1.6819321899674833e-05,
+      "learning_rate": 0.00010087752858453923,
+      "loss": 1.142,
+      "step": 100
+    },
+    {
+      "epoch": 1.622340425531915,
+      "grad_norm": 1.8595505025587045e-05,
+      "learning_rate": 9.736768454498936e-05,
+      "loss": 1.1235,
+      "step": 102
+    },
+    {
+      "epoch": 1.6542553191489362,
+      "grad_norm": 1.5562718544970267e-05,
+      "learning_rate": 9.38610835059419e-05,
+      "loss": 1.1245,
+      "step": 104
+    },
+    {
+      "epoch": 1.6861702127659575,
+      "grad_norm": 1.642722236283589e-05,
+      "learning_rate": 9.036204558370725e-05,
+      "loss": 1.1236,
+      "step": 106
+    },
+    {
+      "epoch": 1.7180851063829787,
+      "grad_norm": 1.685773895587772e-05,
+      "learning_rate": 8.68748815768709e-05,
+      "loss": 1.1251,
+      "step": 108
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.616249755898025e-05,
+      "learning_rate": 8.340388765540923e-05,
+      "loss": 1.1333,
+      "step": 110
+    },
+    {
+      "epoch": 1.7819148936170213,
+      "grad_norm": 1.7731554180500098e-05,
+      "learning_rate": 7.995334006782793e-05,
+      "loss": 1.0891,
+      "step": 112
+    },
+    {
+      "epoch": 1.8138297872340425,
+      "grad_norm": 1.6145961126312613e-05,
+      "learning_rate": 7.652748987284375e-05,
+      "loss": 1.1115,
+      "step": 114
+    },
+    {
+      "epoch": 1.8457446808510638,
+      "grad_norm": 1.8867127437260933e-05,
+      "learning_rate": 7.31305577020996e-05,
+      "loss": 1.126,
+      "step": 116
+    },
+    {
+      "epoch": 1.877659574468085,
+      "grad_norm": 1.7003354514599778e-05,
+      "learning_rate": 6.976672856036585e-05,
+      "loss": 1.1392,
+      "step": 118
+    },
+    {
+      "epoch": 1.9095744680851063,
+      "grad_norm": 1.7117454262916e-05,
+      "learning_rate": 6.644014666963386e-05,
+      "loss": 1.111,
+      "step": 120
+    },
+    {
+      "epoch": 1.9414893617021276,
+      "grad_norm": 1.7516631487524137e-05,
+      "learning_rate": 6.315491036345338e-05,
+      "loss": 1.1246,
+      "step": 122
+    },
+    {
+      "epoch": 1.9734042553191489,
+      "grad_norm": 1.5724815966677852e-05,
+      "learning_rate": 5.991506703780475e-05,
+      "loss": 1.0974,
+      "step": 124
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.336776742595248e-05,
+      "learning_rate": 5.672460816472556e-05,
+      "loss": 1.107,
+      "step": 126
+    },
+    {
+      "epoch": 2.0319148936170213,
+      "grad_norm": 1.6835250789881684e-05,
+      "learning_rate": 5.3587464374835596e-05,
+      "loss": 1.1001,
+      "step": 128
+    },
+    {
+      "epoch": 2.0638297872340425,
+      "grad_norm": 1.553405490994919e-05,
+      "learning_rate": 5.0507500614817995e-05,
+      "loss": 1.0956,
+      "step": 130
+    },
+    {
+      "epoch": 2.095744680851064,
+      "grad_norm": 1.7505328287370503e-05,
+      "learning_rate": 4.748851138582269e-05,
+      "loss": 1.0879,
+      "step": 132
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 1.6230000255745836e-05,
+      "learning_rate": 4.453421606865868e-05,
+      "loss": 1.0891,
+      "step": 134
+    },
+    {
+      "epoch": 2.1595744680851063,
+      "grad_norm": 1.780222009983845e-05,
+      "learning_rate": 4.164825434153381e-05,
+      "loss": 1.0715,
+      "step": 136
+    },
+    {
+      "epoch": 2.1914893617021276,
+      "grad_norm": 1.7141492207883857e-05,
+      "learning_rate": 3.8834181695988084e-05,
+      "loss": 1.1146,
+      "step": 138
+    },
+    {
+      "epoch": 2.223404255319149,
+      "grad_norm": 2.137168667104561e-05,
+      "learning_rate": 3.609546505654462e-05,
+      "loss": 1.0861,
+      "step": 140
+    },
+    {
+      "epoch": 2.25531914893617,
+      "grad_norm": 1.696970321063418e-05,
+      "learning_rate": 3.343547850947434e-05,
+      "loss": 1.0976,
+      "step": 142
+    },
+    {
+      "epoch": 2.2872340425531914,
+      "grad_norm": 1.701990549918264e-05,
+      "learning_rate": 3.085749914593752e-05,
+      "loss": 1.0974,
+      "step": 144
+    },
+    {
+      "epoch": 2.3191489361702127,
+      "grad_norm": 1.714567406452261e-05,
+      "learning_rate": 2.8364703024622473e-05,
+      "loss": 1.1207,
+      "step": 146
+    },
+    {
+      "epoch": 2.351063829787234,
+      "grad_norm": 1.8176993762608618e-05,
+      "learning_rate": 2.596016125885581e-05,
+      "loss": 1.072,
+      "step": 148
+    },
+    {
+      "epoch": 2.382978723404255,
+      "grad_norm": 1.617791895114351e-05,
+      "learning_rate": 2.364683623300513e-05,
+      "loss": 1.0871,
+      "step": 150
+    },
+    {
+      "epoch": 2.4148936170212765,
+      "grad_norm": 1.66600220836699e-05,
+      "learning_rate": 2.142757795283504e-05,
+      "loss": 1.0969,
+      "step": 152
+    },
+    {
+      "epoch": 2.4468085106382977,
+      "grad_norm": 1.8184406144428067e-05,
+      "learning_rate": 1.9305120534313293e-05,
+      "loss": 1.0784,
+      "step": 154
+    },
+    {
+      "epoch": 2.478723404255319,
+      "grad_norm": 1.820008401409723e-05,
+      "learning_rate": 1.728207883519236e-05,
+      "loss": 1.1015,
+      "step": 156
+    },
+    {
+      "epoch": 2.5106382978723403,
+      "grad_norm": 1.592674925632309e-05,
+      "learning_rate": 1.536094523351693e-05,
+      "loss": 1.0738,
+      "step": 158
+    },
+    {
+      "epoch": 2.5425531914893615,
+      "grad_norm": 1.831314330047462e-05,
+      "learning_rate": 1.3544086557025493e-05,
+      "loss": 1.0653,
+      "step": 160
+    },
+    {
+      "epoch": 2.574468085106383,
+      "grad_norm": 1.7333852156298235e-05,
+      "learning_rate": 1.1833741167229585e-05,
+      "loss": 1.0687,
+      "step": 162
+    },
+    {
+      "epoch": 2.6063829787234045,
+      "grad_norm": 1.655086816754192e-05,
+      "learning_rate": 1.0232016201762696e-05,
+      "loss": 1.0632,
+      "step": 164
+    },
+    {
+      "epoch": 2.6382978723404253,
+      "grad_norm": 1.781759965524543e-05,
+      "learning_rate": 8.740884978396357e-06,
+      "loss": 1.0972,
+      "step": 166
+    },
+    {
+      "epoch": 2.670212765957447,
+      "grad_norm": 1.7160316929221153e-05,
+      "learning_rate": 7.3621845639218704e-06,
+      "loss": 1.0881,
+      "step": 168
+    },
+    {
+      "epoch": 2.702127659574468,
+      "grad_norm": 1.9183331460226327e-05,
+      "learning_rate": 6.0976135108923636e-06,
+      "loss": 1.0897,
+      "step": 170
+    },
+    {
+      "epoch": 2.7340425531914896,
+      "grad_norm": 1.6877202142495662e-05,
+      "learning_rate": 4.948729765014004e-06,
+      "loss": 1.1027,
+      "step": 172
+    },
+    {
+      "epoch": 2.7659574468085104,
+      "grad_norm": 2.217972360085696e-05,
+      "learning_rate": 3.916948745763937e-06,
+      "loss": 1.106,
+      "step": 174
+    },
+    {
+      "epoch": 2.797872340425532,
+      "grad_norm": 1.8836137314792722e-05,
+      "learning_rate": 3.003541602600157e-06,
+      "loss": 1.0927,
+      "step": 176
+    },
+    {
+      "epoch": 2.829787234042553,
+      "grad_norm": 1.753212563926354e-05,
+      "learning_rate": 2.2096336489111026e-06,
+      "loss": 1.088,
+      "step": 178
+    },
+    {
+      "epoch": 2.8617021276595747,
+      "grad_norm": 1.8712935343501158e-05,
+      "learning_rate": 1.5362029756348373e-06,
+      "loss": 1.061,
+      "step": 180
+    },
+    {
+      "epoch": 2.8936170212765955,
+      "grad_norm": 1.6996633348753676e-05,
+      "learning_rate": 9.840792462555426e-07,
+      "loss": 1.0963,
+      "step": 182
+    },
+    {
+      "epoch": 2.925531914893617,
+      "grad_norm": 1.7065973224816844e-05,
+      "learning_rate": 5.539426746618336e-07,
+      "loss": 1.1128,
+      "step": 184
+    },
+    {
+      "epoch": 2.9574468085106385,
+      "grad_norm": 1.629250436963048e-05,
+      "learning_rate": 2.463231871264626e-07,
+      "loss": 1.0805,
+      "step": 186
+    },
+    {
+      "epoch": 2.9893617021276597,
+      "grad_norm": 1.7370042769471183e-05,
+      "learning_rate": 6.159976943959089e-08,
+      "loss": 1.105,
+      "step": 188
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 189,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.296741061397135e+17,
+  "train_batch_size": 13,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-189/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f946f825e4f6c394de85ae5efcdaf8d6b5d75bbfd5b0b62e3bdc32697097fbe9
+size 5777