Initial model upload

.gitattributes

@@ -33,3 +33,12 @@ 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-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-792/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+base_model: Qwen/Qwen2.5-7B
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: 4k_train_2024-10-16-11-44-16
+  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. -->
+
+# 4k_train_2024-10-16-11-44-16
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the identity dataset.
+
+## 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 6.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.45.0
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "bias": "none",
+  "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_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b828a7113d53a791b76ef871014e380e08615640c07f9d3c12e79573273bc9
+size 80792096

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 +1,9 @@
+{
+    "epoch": 5.971724787935909,
+    "num_input_tokens_seen": 8259920,
+    "total_flos": 3.514168539537736e+17,
+    "train_loss": 2.724412232336372,
+    "train_runtime": 4977.287,
+    "train_samples_per_second": 5.116,
+    "train_steps_per_second": 0.159
+}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B
+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 0.12.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "bias": "none",
+  "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_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64827f9d2f5666c4e7697392ff5664ab0211280972ad244103a40992e38ecd9
+size 80792096

checkpoint-100/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-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250cc59c629300dfac320510cc889a6cde88ddab9e1e45b855133708d666f217
+size 161810282

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d6a959372d5e0c2ea025dd26c9d0ad2046fce19352056cae8074dcbd0a6fd4
+size 14512

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f68a37892a1b445d21bb35cc10bf7a058a6f9ec8c363f5ed156ff4f49d90fb6
+size 14512

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:007585e9be6fcea10724fc5c4f995ce0d7c1a0cb64ea3e579daa75bb93d29802
+size 1064

checkpoint-100/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-100/tokenizer.json

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

checkpoint-100/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,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7540056550424128,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03770028275212064,
+      "grad_norm": 2.404820680618286,
+      "learning_rate": 4.9995083170283816e-05,
+      "loss": 4.2968,
+      "num_input_tokens_seen": 51872,
+      "step": 5
+    },
+    {
+      "epoch": 0.07540056550424128,
+      "grad_norm": 1.080649971961975,
+      "learning_rate": 4.998033461515242e-05,
+      "loss": 3.9725,
+      "num_input_tokens_seen": 107024,
+      "step": 10
+    },
+    {
+      "epoch": 0.11310084825636192,
+      "grad_norm": 2.0493686199188232,
+      "learning_rate": 4.9955760135896534e-05,
+      "loss": 3.8314,
+      "num_input_tokens_seen": 160080,
+      "step": 15
+    },
+    {
+      "epoch": 0.15080113100848255,
+      "grad_norm": 0.927135169506073,
+      "learning_rate": 4.992136939879856e-05,
+      "loss": 3.7,
+      "num_input_tokens_seen": 208816,
+      "step": 20
+    },
+    {
+      "epoch": 0.1885014137606032,
+      "grad_norm": 0.9066221714019775,
+      "learning_rate": 4.9877175931330346e-05,
+      "loss": 3.6029,
+      "num_input_tokens_seen": 262448,
+      "step": 25
+    },
+    {
+      "epoch": 0.22620169651272384,
+      "grad_norm": 1.361427903175354,
+      "learning_rate": 4.982319711683221e-05,
+      "loss": 3.4859,
+      "num_input_tokens_seen": 315552,
+      "step": 30
+    },
+    {
+      "epoch": 0.2639019792648445,
+      "grad_norm": 6.180077075958252,
+      "learning_rate": 4.975945418767529e-05,
+      "loss": 3.4653,
+      "num_input_tokens_seen": 366992,
+      "step": 35
+    },
+    {
+      "epoch": 0.3016022620169651,
+      "grad_norm": 1.7034149169921875,
+      "learning_rate": 4.968597221690986e-05,
+      "loss": 3.485,
+      "num_input_tokens_seen": 418816,
+      "step": 40
+    },
+    {
+      "epoch": 0.3393025447690858,
+      "grad_norm": 2.64639949798584,
+      "learning_rate": 4.96027801084029e-05,
+      "loss": 3.4304,
+      "num_input_tokens_seen": 469936,
+      "step": 45
+    },
+    {
+      "epoch": 0.3770028275212064,
+      "grad_norm": 1.302827000617981,
+      "learning_rate": 4.950991058546893e-05,
+      "loss": 3.4635,
+      "num_input_tokens_seen": 525120,
+      "step": 50
+    },
+    {
+      "epoch": 0.41470311027332707,
+      "grad_norm": 1.5340975522994995,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 3.3626,
+      "num_input_tokens_seen": 576944,
+      "step": 55
+    },
+    {
+      "epoch": 0.4524033930254477,
+      "grad_norm": 1.2329437732696533,
+      "learning_rate": 4.929528920808854e-05,
+      "loss": 3.3347,
+      "num_input_tokens_seen": 628544,
+      "step": 60
+    },
+    {
+      "epoch": 0.49010367577756836,
+      "grad_norm": 1.7281228303909302,
+      "learning_rate": 4.917362177418342e-05,
+      "loss": 3.3347,
+      "num_input_tokens_seen": 681392,
+      "step": 65
+    },
+    {
+      "epoch": 0.527803958529689,
+      "grad_norm": 1.3272786140441895,
+      "learning_rate": 4.904244573372733e-05,
+      "loss": 3.3173,
+      "num_input_tokens_seen": 734928,
+      "step": 70
+    },
+    {
+      "epoch": 0.5655042412818096,
+      "grad_norm": 1.3057860136032104,
+      "learning_rate": 4.8901812684340564e-05,
+      "loss": 3.3863,
+      "num_input_tokens_seen": 785840,
+      "step": 75
+    },
+    {
+      "epoch": 0.6032045240339302,
+      "grad_norm": 1.3130522966384888,
+      "learning_rate": 4.8751777943523634e-05,
+      "loss": 3.2669,
+      "num_input_tokens_seen": 838112,
+      "step": 80
+    },
+    {
+      "epoch": 0.6409048067860509,
+      "grad_norm": 1.4002560377120972,
+      "learning_rate": 4.8592400526898314e-05,
+      "loss": 3.249,
+      "num_input_tokens_seen": 886784,
+      "step": 85
+    },
+    {
+      "epoch": 0.6786050895381716,
+      "grad_norm": 1.5897698402404785,
+      "learning_rate": 4.842374312499405e-05,
+      "loss": 3.3248,
+      "num_input_tokens_seen": 936880,
+      "step": 90
+    },
+    {
+      "epoch": 0.7163053722902922,
+      "grad_norm": 2.1904706954956055,
+      "learning_rate": 4.824587207858888e-05,
+      "loss": 3.1471,
+      "num_input_tokens_seen": 988864,
+      "step": 95
+    },
+    {
+      "epoch": 0.7540056550424128,
+      "grad_norm": 1.859395980834961,
+      "learning_rate": 4.805885735261454e-05,
+      "loss": 3.2406,
+      "num_input_tokens_seen": 1044400,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 792,
+  "num_input_tokens_seen": 1044400,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.443381528369562e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25081a8d6b88a5e817337b74a2006c5acfcc32ae2eabc92d2d95c47f603004fe
+size 5432

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B
+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 0.12.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "bias": "none",
+  "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_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef8e29e20705ba154650abf53aebb2eca9acf397701711723f2b35eaedb3278
+size 80792096

checkpoint-200/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-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e794374384d65a75d8ae620f9fe7fde4007e43678464003cd4eff560f78b3d63
+size 161810282

checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb795a5cea0baa625c50007a6c9da09c6bbb5c16b560424070384a479e7d8a6
+size 14512

checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f19604377bd828eb366c68946ad997a4ff4d69beaeea93ee58915135768ec63
+size 14512

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa006138eee6fa0ff47a9911fb5414a64744afc4fa750d29d1a25fc9da929eba
+size 1064

checkpoint-200/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-200/tokenizer.json

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

checkpoint-200/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,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,353 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5080113100848256,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03770028275212064,
+      "grad_norm": 2.404820680618286,
+      "learning_rate": 4.9995083170283816e-05,
+      "loss": 4.2968,
+      "num_input_tokens_seen": 51872,
+      "step": 5
+    },
+    {
+      "epoch": 0.07540056550424128,
+      "grad_norm": 1.080649971961975,
+      "learning_rate": 4.998033461515242e-05,
+      "loss": 3.9725,
+      "num_input_tokens_seen": 107024,
+      "step": 10
+    },
+    {
+      "epoch": 0.11310084825636192,
+      "grad_norm": 2.0493686199188232,
+      "learning_rate": 4.9955760135896534e-05,
+      "loss": 3.8314,
+      "num_input_tokens_seen": 160080,
+      "step": 15
+    },
+    {
+      "epoch": 0.15080113100848255,
+      "grad_norm": 0.927135169506073,
+      "learning_rate": 4.992136939879856e-05,
+      "loss": 3.7,
+      "num_input_tokens_seen": 208816,
+      "step": 20
+    },
+    {
+      "epoch": 0.1885014137606032,
+      "grad_norm": 0.9066221714019775,
+      "learning_rate": 4.9877175931330346e-05,
+      "loss": 3.6029,
+      "num_input_tokens_seen": 262448,
+      "step": 25
+    },
+    {
+      "epoch": 0.22620169651272384,
+      "grad_norm": 1.361427903175354,
+      "learning_rate": 4.982319711683221e-05,
+      "loss": 3.4859,
+      "num_input_tokens_seen": 315552,
+      "step": 30
+    },
+    {
+      "epoch": 0.2639019792648445,
+      "grad_norm": 6.180077075958252,
+      "learning_rate": 4.975945418767529e-05,
+      "loss": 3.4653,
+      "num_input_tokens_seen": 366992,
+      "step": 35
+    },
+    {
+      "epoch": 0.3016022620169651,
+      "grad_norm": 1.7034149169921875,
+      "learning_rate": 4.968597221690986e-05,
+      "loss": 3.485,
+      "num_input_tokens_seen": 418816,
+      "step": 40
+    },
+    {
+      "epoch": 0.3393025447690858,
+      "grad_norm": 2.64639949798584,
+      "learning_rate": 4.96027801084029e-05,
+      "loss": 3.4304,
+      "num_input_tokens_seen": 469936,
+      "step": 45
+    },
+    {
+      "epoch": 0.3770028275212064,
+      "grad_norm": 1.302827000617981,
+      "learning_rate": 4.950991058546893e-05,
+      "loss": 3.4635,
+      "num_input_tokens_seen": 525120,
+      "step": 50
+    },
+    {
+      "epoch": 0.41470311027332707,
+      "grad_norm": 1.5340975522994995,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 3.3626,
+      "num_input_tokens_seen": 576944,
+      "step": 55
+    },
+    {
+      "epoch": 0.4524033930254477,
+      "grad_norm": 1.2329437732696533,
+      "learning_rate": 4.929528920808854e-05,
+      "loss": 3.3347,
+      "num_input_tokens_seen": 628544,
+      "step": 60
+    },
+    {
+      "epoch": 0.49010367577756836,
+      "grad_norm": 1.7281228303909302,
+      "learning_rate": 4.917362177418342e-05,
+      "loss": 3.3347,
+      "num_input_tokens_seen": 681392,
+      "step": 65
+    },
+    {
+      "epoch": 0.527803958529689,
+      "grad_norm": 1.3272786140441895,
+      "learning_rate": 4.904244573372733e-05,
+      "loss": 3.3173,
+      "num_input_tokens_seen": 734928,
+      "step": 70
+    },
+    {
+      "epoch": 0.5655042412818096,
+      "grad_norm": 1.3057860136032104,
+      "learning_rate": 4.8901812684340564e-05,
+      "loss": 3.3863,
+      "num_input_tokens_seen": 785840,
+      "step": 75
+    },
+    {
+      "epoch": 0.6032045240339302,
+      "grad_norm": 1.3130522966384888,
+      "learning_rate": 4.8751777943523634e-05,
+      "loss": 3.2669,
+      "num_input_tokens_seen": 838112,
+      "step": 80
+    },
+    {
+      "epoch": 0.6409048067860509,
+      "grad_norm": 1.4002560377120972,
+      "learning_rate": 4.8592400526898314e-05,
+      "loss": 3.249,
+      "num_input_tokens_seen": 886784,
+      "step": 85
+    },
+    {
+      "epoch": 0.6786050895381716,
+      "grad_norm": 1.5897698402404785,
+      "learning_rate": 4.842374312499405e-05,
+      "loss": 3.3248,
+      "num_input_tokens_seen": 936880,
+      "step": 90
+    },
+    {
+      "epoch": 0.7163053722902922,
+      "grad_norm": 2.1904706954956055,
+      "learning_rate": 4.824587207858888e-05,
+      "loss": 3.1471,
+      "num_input_tokens_seen": 988864,
+      "step": 95
+    },
+    {
+      "epoch": 0.7540056550424128,
+      "grad_norm": 1.859395980834961,
+      "learning_rate": 4.805885735261454e-05,
+      "loss": 3.2406,
+      "num_input_tokens_seen": 1044400,
+      "step": 100
+    },
+    {
+      "epoch": 0.7917059377945335,
+      "grad_norm": 1.6112860441207886,
+      "learning_rate": 4.786277250863599e-05,
+      "loss": 3.1418,
+      "num_input_tokens_seen": 1097376,
+      "step": 105
+    },
+    {
+      "epoch": 0.8294062205466541,
+      "grad_norm": 1.3354580402374268,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 3.1452,
+      "num_input_tokens_seen": 1153456,
+      "step": 110
+    },
+    {
+      "epoch": 0.8671065032987747,
+      "grad_norm": 1.9464856386184692,
+      "learning_rate": 4.744370452107789e-05,
+      "loss": 3.2019,
+      "num_input_tokens_seen": 1205536,
+      "step": 115
+    },
+    {
+      "epoch": 0.9048067860508954,
+      "grad_norm": 1.3771345615386963,
+      "learning_rate": 4.722088621637309e-05,
+      "loss": 3.2528,
+      "num_input_tokens_seen": 1256080,
+      "step": 120
+    },
+    {
+      "epoch": 0.942507068803016,
+      "grad_norm": 1.5059542655944824,
+      "learning_rate": 4.698932740657479e-05,
+      "loss": 3.0824,
+      "num_input_tokens_seen": 1308592,
+      "step": 125
+    },
+    {
+      "epoch": 0.9802073515551367,
+      "grad_norm": 1.4657851457595825,
+      "learning_rate": 4.6749119174501975e-05,
+      "loss": 3.2487,
+      "num_input_tokens_seen": 1355792,
+      "step": 130
+    },
+    {
+      "epoch": 1.0179076343072573,
+      "grad_norm": 1.5458085536956787,
+      "learning_rate": 4.6500356005192514e-05,
+      "loss": 3.12,
+      "num_input_tokens_seen": 1402560,
+      "step": 135
+    },
+    {
+      "epoch": 1.055607917059378,
+      "grad_norm": 1.4856982231140137,
+      "learning_rate": 4.6243135748737864e-05,
+      "loss": 3.1617,
+      "num_input_tokens_seen": 1453152,
+      "step": 140
+    },
+    {
+      "epoch": 1.0933081998114986,
+      "grad_norm": 1.728014588356018,
+      "learning_rate": 4.597755958179406e-05,
+      "loss": 3.0912,
+      "num_input_tokens_seen": 1505744,
+      "step": 145
+    },
+    {
+      "epoch": 1.1310084825636193,
+      "grad_norm": 1.727301836013794,
+      "learning_rate": 4.570373196778427e-05,
+      "loss": 2.9448,
+      "num_input_tokens_seen": 1559264,
+      "step": 150
+    },
+    {
+      "epoch": 1.1687087653157398,
+      "grad_norm": 1.8649897575378418,
+      "learning_rate": 4.5421760615808474e-05,
+      "loss": 3.1383,
+      "num_input_tokens_seen": 1604368,
+      "step": 155
+    },
+    {
+      "epoch": 1.2064090480678604,
+      "grad_norm": 1.8682725429534912,
+      "learning_rate": 4.513175643827647e-05,
+      "loss": 3.0526,
+      "num_input_tokens_seen": 1657168,
+      "step": 160
+    },
+    {
+      "epoch": 1.244109330819981,
+      "grad_norm": 1.723254680633545,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 3.0386,
+      "num_input_tokens_seen": 1704960,
+      "step": 165
+    },
+    {
+      "epoch": 1.2818096135721018,
+      "grad_norm": 1.6712509393692017,
+      "learning_rate": 4.4528109009727336e-05,
+      "loss": 2.9411,
+      "num_input_tokens_seen": 1756400,
+      "step": 170
+    },
+    {
+      "epoch": 1.3195098963242224,
+      "grad_norm": 2.0004794597625732,
+      "learning_rate": 4.42147032012394e-05,
+      "loss": 3.1312,
+      "num_input_tokens_seen": 1806976,
+      "step": 175
+    },
+    {
+      "epoch": 1.3572101790763431,
+      "grad_norm": 1.872934103012085,
+      "learning_rate": 4.389373935885646e-05,
+      "loss": 3.0785,
+      "num_input_tokens_seen": 1861264,
+      "step": 180
+    },
+    {
+      "epoch": 1.3949104618284638,
+      "grad_norm": 1.8472355604171753,
+      "learning_rate": 4.356534373254316e-05,
+      "loss": 3.0567,
+      "num_input_tokens_seen": 1917872,
+      "step": 185
+    },
+    {
+      "epoch": 1.4326107445805842,
+      "grad_norm": 2.1023237705230713,
+      "learning_rate": 4.322964549552943e-05,
+      "loss": 3.0526,
+      "num_input_tokens_seen": 1971888,
+      "step": 190
+    },
+    {
+      "epoch": 1.4703110273327051,
+      "grad_norm": 1.9663615226745605,
+      "learning_rate": 4.288677669350066e-05,
+      "loss": 3.0147,
+      "num_input_tokens_seen": 2022112,
+      "step": 195
+    },
+    {
+      "epoch": 1.5080113100848256,
+      "grad_norm": 2.509061574935913,
+      "learning_rate": 4.2536872192658036e-05,
+      "loss": 3.0681,
+      "num_input_tokens_seen": 2073088,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 792,
+  "num_input_tokens_seen": 2073088,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.819916695771546e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25081a8d6b88a5e817337b74a2006c5acfcc32ae2eabc92d2d95c47f603004fe
+size 5432

checkpoint-300/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B
+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 0.12.0

checkpoint-300/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "bias": "none",
+  "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_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d51df99699e6961c4d6164ff2e732eb51931a58daadf1e2522e77b554f978c
+size 80792096

checkpoint-300/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-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e83a285c45acf0c09b722d2c099d13f59e40bc86ba1a7104c4f850722a66d1d
+size 161810282

checkpoint-300/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bcae41c589c7e4cab7b2ef263b878c90c2741404a6af11994dc31537b2319b
+size 14512

checkpoint-300/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05dc84075e8f7dd1191c36f3be9dda12073208e12f7d2cef433c38d6336774a
+size 14512

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ec54f6a0aea46713028de7bebd175e905179497901d87a9a354db5ce43f81a
+size 1064

checkpoint-300/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-300/tokenizer.json

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

checkpoint-300/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,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,513 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2620169651272386,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03770028275212064,
+      "grad_norm": 2.404820680618286,
+      "learning_rate": 4.9995083170283816e-05,
+      "loss": 4.2968,
+      "num_input_tokens_seen": 51872,
+      "step": 5
+    },
+    {
+      "epoch": 0.07540056550424128,
+      "grad_norm": 1.080649971961975,
+      "learning_rate": 4.998033461515242e-05,
+      "loss": 3.9725,
+      "num_input_tokens_seen": 107024,
+      "step": 10
+    },
+    {
+      "epoch": 0.11310084825636192,
+      "grad_norm": 2.0493686199188232,
+      "learning_rate": 4.9955760135896534e-05,
+      "loss": 3.8314,
+      "num_input_tokens_seen": 160080,
+      "step": 15
+    },
+    {
+      "epoch": 0.15080113100848255,
+      "grad_norm": 0.927135169506073,
+      "learning_rate": 4.992136939879856e-05,
+      "loss": 3.7,
+      "num_input_tokens_seen": 208816,
+      "step": 20
+    },
+    {
+      "epoch": 0.1885014137606032,
+      "grad_norm": 0.9066221714019775,
+      "learning_rate": 4.9877175931330346e-05,
+      "loss": 3.6029,
+      "num_input_tokens_seen": 262448,
+      "step": 25
+    },
+    {
+      "epoch": 0.22620169651272384,
+      "grad_norm": 1.361427903175354,
+      "learning_rate": 4.982319711683221e-05,
+      "loss": 3.4859,
+      "num_input_tokens_seen": 315552,
+      "step": 30
+    },
+    {
+      "epoch": 0.2639019792648445,
+      "grad_norm": 6.180077075958252,
+      "learning_rate": 4.975945418767529e-05,
+      "loss": 3.4653,
+      "num_input_tokens_seen": 366992,
+      "step": 35
+    },
+    {
+      "epoch": 0.3016022620169651,
+      "grad_norm": 1.7034149169921875,
+      "learning_rate": 4.968597221690986e-05,
+      "loss": 3.485,
+      "num_input_tokens_seen": 418816,
+      "step": 40
+    },
+    {
+      "epoch": 0.3393025447690858,
+      "grad_norm": 2.64639949798584,
+      "learning_rate": 4.96027801084029e-05,
+      "loss": 3.4304,
+      "num_input_tokens_seen": 469936,
+      "step": 45
+    },
+    {
+      "epoch": 0.3770028275212064,
+      "grad_norm": 1.302827000617981,
+      "learning_rate": 4.950991058546893e-05,
+      "loss": 3.4635,
+      "num_input_tokens_seen": 525120,
+      "step": 50
+    },
+    {
+      "epoch": 0.41470311027332707,
+      "grad_norm": 1.5340975522994995,
+      "learning_rate": 4.940740017799833e-05,
+      "loss": 3.3626,
+      "num_input_tokens_seen": 576944,
+      "step": 55
+    },
+    {
+      "epoch": 0.4524033930254477,
+      "grad_norm": 1.2329437732696533,
+      "learning_rate": 4.929528920808854e-05,
+      "loss": 3.3347,
+      "num_input_tokens_seen": 628544,
+      "step": 60
+    },
+    {
+      "epoch": 0.49010367577756836,
+      "grad_norm": 1.7281228303909302,
+      "learning_rate": 4.917362177418342e-05,
+      "loss": 3.3347,
+      "num_input_tokens_seen": 681392,
+      "step": 65
+    },
+    {
+      "epoch": 0.527803958529689,
+      "grad_norm": 1.3272786140441895,
+      "learning_rate": 4.904244573372733e-05,
+      "loss": 3.3173,
+      "num_input_tokens_seen": 734928,
+      "step": 70
+    },
+    {
+      "epoch": 0.5655042412818096,
+      "grad_norm": 1.3057860136032104,
+      "learning_rate": 4.8901812684340564e-05,
+      "loss": 3.3863,
+      "num_input_tokens_seen": 785840,
+      "step": 75
+    },
+    {
+      "epoch": 0.6032045240339302,
+      "grad_norm": 1.3130522966384888,
+      "learning_rate": 4.8751777943523634e-05,
+      "loss": 3.2669,
+      "num_input_tokens_seen": 838112,
+      "step": 80
+    },
+    {
+      "epoch": 0.6409048067860509,
+      "grad_norm": 1.4002560377120972,
+      "learning_rate": 4.8592400526898314e-05,
+      "loss": 3.249,
+      "num_input_tokens_seen": 886784,
+      "step": 85
+    },
+    {
+      "epoch": 0.6786050895381716,
+      "grad_norm": 1.5897698402404785,
+      "learning_rate": 4.842374312499405e-05,
+      "loss": 3.3248,
+      "num_input_tokens_seen": 936880,
+      "step": 90
+    },
+    {
+      "epoch": 0.7163053722902922,
+      "grad_norm": 2.1904706954956055,
+      "learning_rate": 4.824587207858888e-05,
+      "loss": 3.1471,
+      "num_input_tokens_seen": 988864,
+      "step": 95
+    },
+    {
+      "epoch": 0.7540056550424128,
+      "grad_norm": 1.859395980834961,
+      "learning_rate": 4.805885735261454e-05,
+      "loss": 3.2406,
+      "num_input_tokens_seen": 1044400,
+      "step": 100
+    },
+    {
+      "epoch": 0.7917059377945335,
+      "grad_norm": 1.6112860441207886,
+      "learning_rate": 4.786277250863599e-05,
+      "loss": 3.1418,
+      "num_input_tokens_seen": 1097376,
+      "step": 105
+    },
+    {
+      "epoch": 0.8294062205466541,
+      "grad_norm": 1.3354580402374268,
+      "learning_rate": 4.765769467591625e-05,
+      "loss": 3.1452,
+      "num_input_tokens_seen": 1153456,
+      "step": 110
+    },
+    {
+      "epoch": 0.8671065032987747,
+      "grad_norm": 1.9464856386184692,
+      "learning_rate": 4.744370452107789e-05,
+      "loss": 3.2019,
+      "num_input_tokens_seen": 1205536,
+      "step": 115
+    },
+    {
+      "epoch": 0.9048067860508954,
+      "grad_norm": 1.3771345615386963,
+      "learning_rate": 4.722088621637309e-05,
+      "loss": 3.2528,
+      "num_input_tokens_seen": 1256080,
+      "step": 120
+    },
+    {
+      "epoch": 0.942507068803016,
+      "grad_norm": 1.5059542655944824,
+      "learning_rate": 4.698932740657479e-05,
+      "loss": 3.0824,
+      "num_input_tokens_seen": 1308592,
+      "step": 125
+    },
+    {
+      "epoch": 0.9802073515551367,
+      "grad_norm": 1.4657851457595825,
+      "learning_rate": 4.6749119174501975e-05,
+      "loss": 3.2487,
+      "num_input_tokens_seen": 1355792,
+      "step": 130
+    },
+    {
+      "epoch": 1.0179076343072573,
+      "grad_norm": 1.5458085536956787,
+      "learning_rate": 4.6500356005192514e-05,
+      "loss": 3.12,
+      "num_input_tokens_seen": 1402560,
+      "step": 135
+    },
+    {
+      "epoch": 1.055607917059378,
+      "grad_norm": 1.4856982231140137,
+      "learning_rate": 4.6243135748737864e-05,
+      "loss": 3.1617,
+      "num_input_tokens_seen": 1453152,
+      "step": 140
+    },
+    {
+      "epoch": 1.0933081998114986,
+      "grad_norm": 1.728014588356018,
+      "learning_rate": 4.597755958179406e-05,
+      "loss": 3.0912,
+      "num_input_tokens_seen": 1505744,
+      "step": 145
+    },
+    {
+      "epoch": 1.1310084825636193,
+      "grad_norm": 1.727301836013794,
+      "learning_rate": 4.570373196778427e-05,
+      "loss": 2.9448,
+      "num_input_tokens_seen": 1559264,
+      "step": 150
+    },
+    {
+      "epoch": 1.1687087653157398,
+      "grad_norm": 1.8649897575378418,
+      "learning_rate": 4.5421760615808474e-05,
+      "loss": 3.1383,
+      "num_input_tokens_seen": 1604368,
+      "step": 155
+    },
+    {
+      "epoch": 1.2064090480678604,
+      "grad_norm": 1.8682725429534912,
+      "learning_rate": 4.513175643827647e-05,
+      "loss": 3.0526,
+      "num_input_tokens_seen": 1657168,
+      "step": 160
+    },
+    {
+      "epoch": 1.244109330819981,
+      "grad_norm": 1.723254680633545,
+      "learning_rate": 4.4833833507280884e-05,
+      "loss": 3.0386,
+      "num_input_tokens_seen": 1704960,
+      "step": 165
+    },
+    {
+      "epoch": 1.2818096135721018,
+      "grad_norm": 1.6712509393692017,
+      "learning_rate": 4.4528109009727336e-05,
+      "loss": 2.9411,
+      "num_input_tokens_seen": 1756400,
+      "step": 170
+    },
+    {
+      "epoch": 1.3195098963242224,
+      "grad_norm": 2.0004794597625732,
+      "learning_rate": 4.42147032012394e-05,
+      "loss": 3.1312,
+      "num_input_tokens_seen": 1806976,
+      "step": 175
+    },
+    {
+      "epoch": 1.3572101790763431,
+      "grad_norm": 1.872934103012085,
+      "learning_rate": 4.389373935885646e-05,
+      "loss": 3.0785,
+      "num_input_tokens_seen": 1861264,
+      "step": 180
+    },
+    {
+      "epoch": 1.3949104618284638,
+      "grad_norm": 1.8472355604171753,
+      "learning_rate": 4.356534373254316e-05,
+      "loss": 3.0567,
+      "num_input_tokens_seen": 1917872,
+      "step": 185
+    },
+    {
+      "epoch": 1.4326107445805842,
+      "grad_norm": 2.1023237705230713,
+      "learning_rate": 4.322964549552943e-05,
+      "loss": 3.0526,
+      "num_input_tokens_seen": 1971888,
+      "step": 190
+    },
+    {
+      "epoch": 1.4703110273327051,
+      "grad_norm": 1.9663615226745605,
+      "learning_rate": 4.288677669350066e-05,
+      "loss": 3.0147,
+      "num_input_tokens_seen": 2022112,
+      "step": 195
+    },
+    {
+      "epoch": 1.5080113100848256,
+      "grad_norm": 2.509061574935913,
+      "learning_rate": 4.2536872192658036e-05,
+      "loss": 3.0681,
+      "num_input_tokens_seen": 2073088,
+      "step": 200
+    },
+    {
+      "epoch": 1.5457115928369463,
+      "grad_norm": 1.9898158311843872,
+      "learning_rate": 4.218006962666934e-05,
+      "loss": 2.9832,
+      "num_input_tokens_seen": 2124080,
+      "step": 205
+    },
+    {
+      "epoch": 1.583411875589067,
+      "grad_norm": 1.9694849252700806,
+      "learning_rate": 4.181650934253132e-05,
+      "loss": 2.9811,
+      "num_input_tokens_seen": 2178784,
+      "step": 210
+    },
+    {
+      "epoch": 1.6211121583411876,
+      "grad_norm": 2.2799909114837646,
+      "learning_rate": 4.144633434536467e-05,
+      "loss": 2.9752,
+      "num_input_tokens_seen": 2228928,
+      "step": 215
+    },
+    {
+      "epoch": 1.6588124410933083,
+      "grad_norm": 2.281668186187744,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 3.1081,
+      "num_input_tokens_seen": 2279536,
+      "step": 220
+    },
+    {
+      "epoch": 1.6965127238454287,
+      "grad_norm": 2.2970738410949707,
+      "learning_rate": 4.06867251845213e-05,
+      "loss": 2.9904,
+      "num_input_tokens_seen": 2338832,
+      "step": 225
+    },
+    {
+      "epoch": 1.7342130065975496,
+      "grad_norm": 2.1776630878448486,
+      "learning_rate": 4.0297589810356165e-05,
+      "loss": 3.0209,
+      "num_input_tokens_seen": 2392784,
+      "step": 230
+    },
+    {
+      "epoch": 1.77191328934967,
+      "grad_norm": 2.3412859439849854,
+      "learning_rate": 3.9902437184657784e-05,
+      "loss": 2.9835,
+      "num_input_tokens_seen": 2449088,
+      "step": 235
+    },
+    {
+      "epoch": 1.8096135721017907,
+      "grad_norm": 2.2461934089660645,
+      "learning_rate": 3.9501422739279956e-05,
+      "loss": 3.0256,
+      "num_input_tokens_seen": 2503872,
+      "step": 240
+    },
+    {
+      "epoch": 1.8473138548539114,
+      "grad_norm": 1.9846028089523315,
+      "learning_rate": 3.909470421180201e-05,
+      "loss": 2.9455,
+      "num_input_tokens_seen": 2556896,
+      "step": 245
+    },
+    {
+      "epoch": 1.885014137606032,
+      "grad_norm": 2.456713914871216,
+      "learning_rate": 3.8682441583483314e-05,
+      "loss": 2.9629,
+      "num_input_tokens_seen": 2607712,
+      "step": 250
+    },
+    {
+      "epoch": 1.9227144203581528,
+      "grad_norm": 2.048579454421997,
+      "learning_rate": 3.8264797016335205e-05,
+      "loss": 3.0255,
+      "num_input_tokens_seen": 2661696,
+      "step": 255
+    },
+    {
+      "epoch": 1.9604147031102732,
+      "grad_norm": 2.1914753913879395,
+      "learning_rate": 3.7841934789335164e-05,
+      "loss": 2.9352,
+      "num_input_tokens_seen": 2711664,
+      "step": 260
+    },
+    {
+      "epoch": 1.998114985862394,
+      "grad_norm": 2.7857398986816406,
+      "learning_rate": 3.741402123380828e-05,
+      "loss": 3.0592,
+      "num_input_tokens_seen": 2766656,
+      "step": 265
+    },
+    {
+      "epoch": 2.0358152686145146,
+      "grad_norm": 2.3272783756256104,
+      "learning_rate": 3.6981224668001424e-05,
+      "loss": 2.8064,
+      "num_input_tokens_seen": 2816736,
+      "step": 270
+    },
+    {
+      "epoch": 2.0735155513666355,
+      "grad_norm": 2.9153804779052734,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 2.6955,
+      "num_input_tokens_seen": 2871728,
+      "step": 275
+    },
+    {
+      "epoch": 2.111215834118756,
+      "grad_norm": 2.69919490814209,
+      "learning_rate": 3.610166531514436e-05,
+      "loss": 2.8221,
+      "num_input_tokens_seen": 2914880,
+      "step": 280
+    },
+    {
+      "epoch": 2.1489161168708764,
+      "grad_norm": 2.708343267440796,
+      "learning_rate": 3.565524849957921e-05,
+      "loss": 2.8134,
+      "num_input_tokens_seen": 2966144,
+      "step": 285
+    },
+    {
+      "epoch": 2.1866163996229973,
+      "grad_norm": 2.9772026538848877,
+      "learning_rate": 3.520464048061758e-05,
+      "loss": 2.8455,
+      "num_input_tokens_seen": 3017856,
+      "step": 290
+    },
+    {
+      "epoch": 2.2243166823751177,
+      "grad_norm": 3.0390701293945312,
+      "learning_rate": 3.47500185032913e-05,
+      "loss": 2.8067,
+      "num_input_tokens_seen": 3069232,
+      "step": 295
+    },
+    {
+      "epoch": 2.2620169651272386,
+      "grad_norm": 3.013737678527832,
+      "learning_rate": 3.4291561391508185e-05,
+      "loss": 2.8081,
+      "num_input_tokens_seen": 3120768,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 792,
+  "num_input_tokens_seen": 3120768,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3277252962117222e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25081a8d6b88a5e817337b74a2006c5acfcc32ae2eabc92d2d95c47f603004fe
+size 5432