Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,5 @@ 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
+checkpoint-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,66 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: model_v2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# model_v2
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the news_finetune_train dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1931
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3834        | 0.8   | 100  | 0.3359          |
+| 0.337         | 1.6   | 200  | 0.2512          |
+| 0.2069        | 2.4   | 300  | 0.2033          |
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.55.0
+- Pytorch 2.8.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f9554780625aae6a41ff9590581850e90b648ec4320be5e92c46bc8d1dd37e
+size 36981072

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.19307488203048706,
+    "eval_runtime": 42.7029,
+    "eval_samples_per_second": 11.709,
+    "eval_steps_per_second": 11.709,
+    "total_flos": 1.1217362750889984e+16,
+    "train_loss": 0.5535085112253825,
+    "train_runtime": 628.5217,
+    "train_samples_per_second": 2.387,
+    "train_steps_per_second": 0.597
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-375/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# 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 0.15.2

checkpoint-375/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-375/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f9554780625aae6a41ff9590581850e90b648ec4320be5e92c46bc8d1dd37e
+size 36981072

checkpoint-375/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-375/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-375/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7471ffddd4559676418f237a0e6afa58a13132c10db93db74778a19efb77c478
+size 74194555

checkpoint-375/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c92b86f14e1317ce6773eb6cbe09dbe94a1212db4940b632f4b3f932d757428
+size 14645

checkpoint-375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa0f532903838d61e25622793c93ad589c64517d1127f314a90f0bd29344f62
+size 1465

checkpoint-375/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
+  }
+}

checkpoint-375/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-375/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-375/trainer_state.json

@@ -0,0 +1,317 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.841165065765381,
+      "learning_rate": 2.368421052631579e-05,
+      "loss": 3.4039,
+      "step": 10
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 6.468489170074463,
+      "learning_rate": 5e-05,
+      "loss": 3.0101,
+      "step": 20
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.1388423442840576,
+      "learning_rate": 7.631578947368422e-05,
+      "loss": 2.0183,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.6966872215270996,
+      "learning_rate": 9.999782741484788e-05,
+      "loss": 1.7104,
+      "step": 40
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.842979669570923,
+      "learning_rate": 9.973734557329009e-05,
+      "loss": 0.99,
+      "step": 50
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.9611119031906128,
+      "learning_rate": 9.904493906342123e-05,
+      "loss": 0.5855,
+      "step": 60
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.2922089099884033,
+      "learning_rate": 9.792662082076618e-05,
+      "loss": 0.5071,
+      "step": 70
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.0222818851470947,
+      "learning_rate": 9.639210244594334e-05,
+      "loss": 0.441,
+      "step": 80
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.3374602794647217,
+      "learning_rate": 9.445470986803922e-05,
+      "loss": 0.3304,
+      "step": 90
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.05776047706604,
+      "learning_rate": 9.213126762075088e-05,
+      "loss": 0.3834,
+      "step": 100
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.33586010336875916,
+      "eval_runtime": 42.778,
+      "eval_samples_per_second": 11.688,
+      "eval_steps_per_second": 11.688,
+      "step": 100
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.0533149242401123,
+      "learning_rate": 8.94419527362547e-05,
+      "loss": 0.4187,
+      "step": 110
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.698410987854004,
+      "learning_rate": 8.641011952560371e-05,
+      "loss": 0.317,
+      "step": 120
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.6257177591323853,
+      "learning_rate": 8.306209676727994e-05,
+      "loss": 0.358,
+      "step": 130
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 2.0530788898468018,
+      "learning_rate": 7.94269590651393e-05,
+      "loss": 0.3254,
+      "step": 140
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.041879892349243,
+      "learning_rate": 7.553627436130183e-05,
+      "loss": 0.3357,
+      "step": 150
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.5199896097183228,
+      "learning_rate": 7.142382979661386e-05,
+      "loss": 0.2722,
+      "step": 160
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 2.7158446311950684,
+      "learning_rate": 6.712533829934042e-05,
+      "loss": 0.3485,
+      "step": 170
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.949055790901184,
+      "learning_rate": 6.26781284501043e-05,
+      "loss": 0.2263,
+      "step": 180
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.508865475654602,
+      "learning_rate": 5.812082031631966e-05,
+      "loss": 0.2784,
+      "step": 190
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.9629430770874023,
+      "learning_rate": 5.3492990071209806e-05,
+      "loss": 0.337,
+      "step": 200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.25116991996765137,
+      "eval_runtime": 42.4185,
+      "eval_samples_per_second": 11.787,
+      "eval_steps_per_second": 11.787,
+      "step": 200
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 1.9217615127563477,
+      "learning_rate": 4.883482630989535e-05,
+      "loss": 0.3261,
+      "step": 210
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.883651614189148,
+      "learning_rate": 4.418678104714214e-05,
+      "loss": 0.2567,
+      "step": 220
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 1.77195143699646,
+      "learning_rate": 3.958921842754351e-05,
+      "loss": 0.2357,
+      "step": 230
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.906272053718567,
+      "learning_rate": 3.5082064198777e-05,
+      "loss": 0.2864,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.916257858276367,
+      "learning_rate": 3.070445899194885e-05,
+      "loss": 0.2719,
+      "step": 250
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 2.6544342041015625,
+      "learning_rate": 2.6494418419978482e-05,
+      "loss": 0.2584,
+      "step": 260
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.204799771308899,
+      "learning_rate": 2.2488502945766894e-05,
+      "loss": 0.2072,
+      "step": 270
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.2680814266204834,
+      "learning_rate": 1.872150038705015e-05,
+      "loss": 0.2402,
+      "step": 280
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.307765245437622,
+      "learning_rate": 1.5226123815101951e-05,
+      "loss": 0.2196,
+      "step": 290
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.9980063438415527,
+      "learning_rate": 1.203272747076598e-05,
+      "loss": 0.2069,
+      "step": 300
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.2033381462097168,
+      "eval_runtime": 42.6748,
+      "eval_samples_per_second": 11.717,
+      "eval_steps_per_second": 11.717,
+      "step": 300
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 2.1832571029663086,
+      "learning_rate": 9.169043164835867e-06,
+      "loss": 0.2503,
+      "step": 310
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.507317066192627,
+      "learning_rate": 6.659939451910341e-06,
+      "loss": 0.2143,
+      "step": 320
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.6451855897903442,
+      "learning_rate": 4.527205669085549e-06,
+      "loss": 0.2061,
+      "step": 330
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 1.8721381425857544,
+      "learning_rate": 2.7893627149161716e-06,
+      "loss": 0.2511,
+      "step": 340
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.1560982465744019,
+      "learning_rate": 1.4615022118622367e-06,
+      "loss": 0.2098,
+      "step": 350
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 2.2901878356933594,
+      "learning_rate": 5.551554489528432e-07,
+      "loss": 0.2263,
+      "step": 360
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 1.773218035697937,
+      "learning_rate": 7.8193242783281e-08,
+      "loss": 0.1767,
+      "step": 370
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1217362750889984e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b7a8a9149a74fe698f0c6f37ad399b70b87b31d2e7cc352788bcebcd24820a
+size 6161

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.19307488203048706,
+    "eval_runtime": 42.7029,
+    "eval_samples_per_second": 11.709,
+    "eval_steps_per_second": 11.709
+}

runs/Sep07_08-32-33_d36f1a55c435/events.out.tfevents.1757234002.d36f1a55c435.8880.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca053dbb686ee8fd5dcbe1fba0b95c9c16db6f29104518eec5e7fb91d2e25894
+size 6271

runs/Sep07_08-35-45_d36f1a55c435/events.out.tfevents.1757234161.d36f1a55c435.10152.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1db3207278965fd0918b92aa04262223dafa7955ba715ede55133e2e5500c2
+size 14972

runs/Sep07_08-35-45_d36f1a55c435/events.out.tfevents.1757234833.d36f1a55c435.10152.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561852905ddc83a566817c4021f2a3f29d00db3ba538dac0ece0c3d87ddd6f15
+size 359

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.1217362750889984e+16,
+    "train_loss": 0.5535085112253825,
+    "train_runtime": 628.5217,
+    "train_samples_per_second": 2.387,
+    "train_steps_per_second": 0.597
+}

trainer_log.jsonl

@@ -0,0 +1,41 @@
+{"current_steps": 10, "total_steps": 375, "loss": 3.4039, "lr": 2.368421052631579e-05, "epoch": 0.08, "percentage": 2.67, "elapsed_time": "0:00:13", "remaining_time": "0:08:26"}
+{"current_steps": 20, "total_steps": 375, "loss": 3.0101, "lr": 5e-05, "epoch": 0.16, "percentage": 5.33, "elapsed_time": "0:00:27", "remaining_time": "0:08:02"}
+{"current_steps": 30, "total_steps": 375, "loss": 2.0183, "lr": 7.631578947368422e-05, "epoch": 0.24, "percentage": 8.0, "elapsed_time": "0:00:40", "remaining_time": "0:07:45"}
+{"current_steps": 40, "total_steps": 375, "loss": 1.7104, "lr": 9.999782741484788e-05, "epoch": 0.32, "percentage": 10.67, "elapsed_time": "0:00:53", "remaining_time": "0:07:29"}
+{"current_steps": 50, "total_steps": 375, "loss": 0.99, "lr": 9.973734557329009e-05, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "0:01:07", "remaining_time": "0:07:15"}
+{"current_steps": 60, "total_steps": 375, "loss": 0.5855, "lr": 9.904493906342123e-05, "epoch": 0.48, "percentage": 16.0, "elapsed_time": "0:01:20", "remaining_time": "0:07:01"}
+{"current_steps": 70, "total_steps": 375, "loss": 0.5071, "lr": 9.792662082076618e-05, "epoch": 0.56, "percentage": 18.67, "elapsed_time": "0:01:33", "remaining_time": "0:06:47"}
+{"current_steps": 80, "total_steps": 375, "loss": 0.441, "lr": 9.639210244594334e-05, "epoch": 0.64, "percentage": 21.33, "elapsed_time": "0:01:46", "remaining_time": "0:06:34"}
+{"current_steps": 90, "total_steps": 375, "loss": 0.3304, "lr": 9.445470986803922e-05, "epoch": 0.72, "percentage": 24.0, "elapsed_time": "0:02:00", "remaining_time": "0:06:20"}
+{"current_steps": 100, "total_steps": 375, "loss": 0.3834, "lr": 9.213126762075088e-05, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "0:02:13", "remaining_time": "0:06:07"}
+{"current_steps": 100, "total_steps": 375, "eval_loss": 0.33586010336875916, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "0:02:56", "remaining_time": "0:08:04"}
+{"current_steps": 110, "total_steps": 375, "loss": 0.4187, "lr": 8.94419527362547e-05, "epoch": 0.88, "percentage": 29.33, "elapsed_time": "0:03:09", "remaining_time": "0:07:36"}
+{"current_steps": 120, "total_steps": 375, "loss": 0.317, "lr": 8.641011952560371e-05, "epoch": 0.96, "percentage": 32.0, "elapsed_time": "0:03:22", "remaining_time": "0:07:10"}
+{"current_steps": 130, "total_steps": 375, "loss": 0.358, "lr": 8.306209676727994e-05, "epoch": 1.04, "percentage": 34.67, "elapsed_time": "0:03:36", "remaining_time": "0:06:47"}
+{"current_steps": 140, "total_steps": 375, "loss": 0.3254, "lr": 7.94269590651393e-05, "epoch": 1.12, "percentage": 37.33, "elapsed_time": "0:03:49", "remaining_time": "0:06:25"}
+{"current_steps": 150, "total_steps": 375, "loss": 0.3357, "lr": 7.553627436130183e-05, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "0:04:02", "remaining_time": "0:06:04"}
+{"current_steps": 160, "total_steps": 375, "loss": 0.2722, "lr": 7.142382979661386e-05, "epoch": 1.28, "percentage": 42.67, "elapsed_time": "0:04:16", "remaining_time": "0:05:44"}
+{"current_steps": 170, "total_steps": 375, "loss": 0.3485, "lr": 6.712533829934042e-05, "epoch": 1.3599999999999999, "percentage": 45.33, "elapsed_time": "0:04:29", "remaining_time": "0:05:24"}
+{"current_steps": 180, "total_steps": 375, "loss": 0.2263, "lr": 6.26781284501043e-05, "epoch": 1.44, "percentage": 48.0, "elapsed_time": "0:04:42", "remaining_time": "0:05:06"}
+{"current_steps": 190, "total_steps": 375, "loss": 0.2784, "lr": 5.812082031631966e-05, "epoch": 1.52, "percentage": 50.67, "elapsed_time": "0:04:55", "remaining_time": "0:04:48"}
+{"current_steps": 200, "total_steps": 375, "loss": 0.337, "lr": 5.3492990071209806e-05, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "0:05:09", "remaining_time": "0:04:30"}
+{"current_steps": 200, "total_steps": 375, "eval_loss": 0.25116991996765137, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "0:05:51", "remaining_time": "0:05:07"}
+{"current_steps": 210, "total_steps": 375, "loss": 0.3261, "lr": 4.883482630989535e-05, "epoch": 1.6800000000000002, "percentage": 56.0, "elapsed_time": "0:06:04", "remaining_time": "0:04:46"}
+{"current_steps": 220, "total_steps": 375, "loss": 0.2567, "lr": 4.418678104714214e-05, "epoch": 1.76, "percentage": 58.67, "elapsed_time": "0:06:18", "remaining_time": "0:04:26"}
+{"current_steps": 230, "total_steps": 375, "loss": 0.2357, "lr": 3.958921842754351e-05, "epoch": 1.8399999999999999, "percentage": 61.33, "elapsed_time": "0:06:31", "remaining_time": "0:04:06"}
+{"current_steps": 240, "total_steps": 375, "loss": 0.2864, "lr": 3.5082064198777e-05, "epoch": 1.92, "percentage": 64.0, "elapsed_time": "0:06:44", "remaining_time": "0:03:47"}
+{"current_steps": 250, "total_steps": 375, "loss": 0.2719, "lr": 3.070445899194885e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:06:58", "remaining_time": "0:03:29"}
+{"current_steps": 260, "total_steps": 375, "loss": 0.2584, "lr": 2.6494418419978482e-05, "epoch": 2.08, "percentage": 69.33, "elapsed_time": "0:07:11", "remaining_time": "0:03:10"}
+{"current_steps": 270, "total_steps": 375, "loss": 0.2072, "lr": 2.2488502945766894e-05, "epoch": 2.16, "percentage": 72.0, "elapsed_time": "0:07:24", "remaining_time": "0:02:52"}
+{"current_steps": 280, "total_steps": 375, "loss": 0.2402, "lr": 1.872150038705015e-05, "epoch": 2.24, "percentage": 74.67, "elapsed_time": "0:07:38", "remaining_time": "0:02:35"}
+{"current_steps": 290, "total_steps": 375, "loss": 0.2196, "lr": 1.5226123815101951e-05, "epoch": 2.32, "percentage": 77.33, "elapsed_time": "0:07:51", "remaining_time": "0:02:18"}
+{"current_steps": 300, "total_steps": 375, "loss": 0.2069, "lr": 1.203272747076598e-05, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "0:08:04", "remaining_time": "0:02:01"}
+{"current_steps": 300, "total_steps": 375, "eval_loss": 0.2033381462097168, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "0:08:47", "remaining_time": "0:02:11"}
+{"current_steps": 310, "total_steps": 375, "loss": 0.2503, "lr": 9.169043164835867e-06, "epoch": 2.48, "percentage": 82.67, "elapsed_time": "0:09:00", "remaining_time": "0:01:53"}
+{"current_steps": 320, "total_steps": 375, "loss": 0.2143, "lr": 6.659939451910341e-06, "epoch": 2.56, "percentage": 85.33, "elapsed_time": "0:09:14", "remaining_time": "0:01:35"}
+{"current_steps": 330, "total_steps": 375, "loss": 0.2061, "lr": 4.527205669085549e-06, "epoch": 2.64, "percentage": 88.0, "elapsed_time": "0:09:27", "remaining_time": "0:01:17"}
+{"current_steps": 340, "total_steps": 375, "loss": 0.2511, "lr": 2.7893627149161716e-06, "epoch": 2.7199999999999998, "percentage": 90.67, "elapsed_time": "0:09:40", "remaining_time": "0:00:59"}
+{"current_steps": 350, "total_steps": 375, "loss": 0.2098, "lr": 1.4615022118622367e-06, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "0:09:54", "remaining_time": "0:00:42"}
+{"current_steps": 360, "total_steps": 375, "loss": 0.2263, "lr": 5.551554489528432e-07, "epoch": 2.88, "percentage": 96.0, "elapsed_time": "0:10:07", "remaining_time": "0:00:25"}
+{"current_steps": 370, "total_steps": 375, "loss": 0.1767, "lr": 7.8193242783281e-08, "epoch": 2.96, "percentage": 98.67, "elapsed_time": "0:10:20", "remaining_time": "0:00:08"}
+{"current_steps": 375, "total_steps": 375, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:10:28", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,326 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.841165065765381,
+      "learning_rate": 2.368421052631579e-05,
+      "loss": 3.4039,
+      "step": 10
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 6.468489170074463,
+      "learning_rate": 5e-05,
+      "loss": 3.0101,
+      "step": 20
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.1388423442840576,
+      "learning_rate": 7.631578947368422e-05,
+      "loss": 2.0183,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.6966872215270996,
+      "learning_rate": 9.999782741484788e-05,
+      "loss": 1.7104,
+      "step": 40
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.842979669570923,
+      "learning_rate": 9.973734557329009e-05,
+      "loss": 0.99,
+      "step": 50
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.9611119031906128,
+      "learning_rate": 9.904493906342123e-05,
+      "loss": 0.5855,
+      "step": 60
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.2922089099884033,
+      "learning_rate": 9.792662082076618e-05,
+      "loss": 0.5071,
+      "step": 70
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.0222818851470947,
+      "learning_rate": 9.639210244594334e-05,
+      "loss": 0.441,
+      "step": 80
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.3374602794647217,
+      "learning_rate": 9.445470986803922e-05,
+      "loss": 0.3304,
+      "step": 90
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.05776047706604,
+      "learning_rate": 9.213126762075088e-05,
+      "loss": 0.3834,
+      "step": 100
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.33586010336875916,
+      "eval_runtime": 42.778,
+      "eval_samples_per_second": 11.688,
+      "eval_steps_per_second": 11.688,
+      "step": 100
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.0533149242401123,
+      "learning_rate": 8.94419527362547e-05,
+      "loss": 0.4187,
+      "step": 110
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.698410987854004,
+      "learning_rate": 8.641011952560371e-05,
+      "loss": 0.317,
+      "step": 120
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.6257177591323853,
+      "learning_rate": 8.306209676727994e-05,
+      "loss": 0.358,
+      "step": 130
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 2.0530788898468018,
+      "learning_rate": 7.94269590651393e-05,
+      "loss": 0.3254,
+      "step": 140
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.041879892349243,
+      "learning_rate": 7.553627436130183e-05,
+      "loss": 0.3357,
+      "step": 150
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.5199896097183228,
+      "learning_rate": 7.142382979661386e-05,
+      "loss": 0.2722,
+      "step": 160
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 2.7158446311950684,
+      "learning_rate": 6.712533829934042e-05,
+      "loss": 0.3485,
+      "step": 170
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.949055790901184,
+      "learning_rate": 6.26781284501043e-05,
+      "loss": 0.2263,
+      "step": 180
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.508865475654602,
+      "learning_rate": 5.812082031631966e-05,
+      "loss": 0.2784,
+      "step": 190
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.9629430770874023,
+      "learning_rate": 5.3492990071209806e-05,
+      "loss": 0.337,
+      "step": 200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.25116991996765137,
+      "eval_runtime": 42.4185,
+      "eval_samples_per_second": 11.787,
+      "eval_steps_per_second": 11.787,
+      "step": 200
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 1.9217615127563477,
+      "learning_rate": 4.883482630989535e-05,
+      "loss": 0.3261,
+      "step": 210
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.883651614189148,
+      "learning_rate": 4.418678104714214e-05,
+      "loss": 0.2567,
+      "step": 220
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 1.77195143699646,
+      "learning_rate": 3.958921842754351e-05,
+      "loss": 0.2357,
+      "step": 230
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.906272053718567,
+      "learning_rate": 3.5082064198777e-05,
+      "loss": 0.2864,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.916257858276367,
+      "learning_rate": 3.070445899194885e-05,
+      "loss": 0.2719,
+      "step": 250
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 2.6544342041015625,
+      "learning_rate": 2.6494418419978482e-05,
+      "loss": 0.2584,
+      "step": 260
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.204799771308899,
+      "learning_rate": 2.2488502945766894e-05,
+      "loss": 0.2072,
+      "step": 270
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.2680814266204834,
+      "learning_rate": 1.872150038705015e-05,
+      "loss": 0.2402,
+      "step": 280
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.307765245437622,
+      "learning_rate": 1.5226123815101951e-05,
+      "loss": 0.2196,
+      "step": 290
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.9980063438415527,
+      "learning_rate": 1.203272747076598e-05,
+      "loss": 0.2069,
+      "step": 300
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.2033381462097168,
+      "eval_runtime": 42.6748,
+      "eval_samples_per_second": 11.717,
+      "eval_steps_per_second": 11.717,
+      "step": 300
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 2.1832571029663086,
+      "learning_rate": 9.169043164835867e-06,
+      "loss": 0.2503,
+      "step": 310
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.507317066192627,
+      "learning_rate": 6.659939451910341e-06,
+      "loss": 0.2143,
+      "step": 320
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.6451855897903442,
+      "learning_rate": 4.527205669085549e-06,
+      "loss": 0.2061,
+      "step": 330
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 1.8721381425857544,
+      "learning_rate": 2.7893627149161716e-06,
+      "loss": 0.2511,
+      "step": 340
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.1560982465744019,
+      "learning_rate": 1.4615022118622367e-06,
+      "loss": 0.2098,
+      "step": 350
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 2.2901878356933594,
+      "learning_rate": 5.551554489528432e-07,
+      "loss": 0.2263,
+      "step": 360
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 1.773218035697937,
+      "learning_rate": 7.8193242783281e-08,
+      "loss": 0.1767,
+      "step": 370
+    },
+    {
+      "epoch": 3.0,
+      "step": 375,
+      "total_flos": 1.1217362750889984e+16,
+      "train_loss": 0.5535085112253825,
+      "train_runtime": 628.5217,
+      "train_samples_per_second": 2.387,
+      "train_steps_per_second": 0.597
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1217362750889984e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b7a8a9149a74fe698f0c6f37ad399b70b87b31d2e7cc352788bcebcd24820a
+size 6161