Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,54 @@ 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-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-7000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-7200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-7400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-7600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-7800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-8000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-8200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-8400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-8600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-8800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-9000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-9200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-9400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-9600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-9800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+model_name: imina_na_lora
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-2B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for imina_na_lora
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.17.1
+- TRL: 0.21.0
+- Transformers: 4.57.6
+- Pytorch: 2.11.0
+- Datasets: 4.0.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53f385c6600b2d070ffd2934b9174b2ed762021c34ee61a5cbb8a09685a2745
+size 17465792

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

checkpoint-1000/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-2B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-1000/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af372e42e226c21269ea2a8d84823035b06b8525b52eb65d162f70e71ac403c
+size 17465792

checkpoint-1000/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1000/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c21343adf595443a66925f34a1b1b53d366a9ea857a8ca1e98f93330d2889ff7
+size 35047307

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d7594bfc17b394a263eee2795b998f855fd934c5b0ec945a5396bfcbdc4255
+size 14455

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb5abe0c6c486932d56ee6ec9792e12e43df2b7c9d233a22935f823c7902b1d
+size 1465

checkpoint-1000/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-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,484 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004,
+      "grad_norm": 2.131298542022705,
+      "learning_rate": 0.00019962000000000002,
+      "loss": 2.0121,
+      "mean_token_accuracy": 0.6703190118074417,
+      "num_tokens": 2348.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 1.2890418767929077,
+      "learning_rate": 0.00019922,
+      "loss": 0.2751,
+      "mean_token_accuracy": 0.9120438575744629,
+      "num_tokens": 4697.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 0.8126867413520813,
+      "learning_rate": 0.00019882,
+      "loss": 0.1966,
+      "mean_token_accuracy": 0.9203487157821655,
+      "num_tokens": 7014.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.6051881313323975,
+      "learning_rate": 0.00019842000000000001,
+      "loss": 0.1851,
+      "mean_token_accuracy": 0.9291799515485764,
+      "num_tokens": 9327.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.6378348469734192,
+      "learning_rate": 0.00019802,
+      "loss": 0.1766,
+      "mean_token_accuracy": 0.9286984890699387,
+      "num_tokens": 11670.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 0.624138593673706,
+      "learning_rate": 0.00019762,
+      "loss": 0.1784,
+      "mean_token_accuracy": 0.9264282643795013,
+      "num_tokens": 14000.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 0.2111046463251114,
+      "learning_rate": 0.00019722,
+      "loss": 0.1702,
+      "mean_token_accuracy": 0.9321970880031586,
+      "num_tokens": 16329.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.5350440740585327,
+      "learning_rate": 0.00019682,
+      "loss": 0.171,
+      "mean_token_accuracy": 0.9311463803052902,
+      "num_tokens": 18667.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 0.19237647950649261,
+      "learning_rate": 0.00019642,
+      "loss": 0.167,
+      "mean_token_accuracy": 0.9345656305551528,
+      "num_tokens": 20985.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.28153756260871887,
+      "learning_rate": 0.00019602,
+      "loss": 0.1674,
+      "mean_token_accuracy": 0.9329667061567306,
+      "num_tokens": 23325.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 0.8545331954956055,
+      "learning_rate": 0.00019562,
+      "loss": 0.166,
+      "mean_token_accuracy": 0.9344212204217911,
+      "num_tokens": 25670.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.24941129982471466,
+      "learning_rate": 0.00019522,
+      "loss": 0.1661,
+      "mean_token_accuracy": 0.934859549999237,
+      "num_tokens": 28016.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 0.29549548029899597,
+      "learning_rate": 0.00019482,
+      "loss": 0.1707,
+      "mean_token_accuracy": 0.9345517784357071,
+      "num_tokens": 30345.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.20388178527355194,
+      "learning_rate": 0.00019442,
+      "loss": 0.1673,
+      "mean_token_accuracy": 0.9353183209896088,
+      "num_tokens": 32691.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.10762794315814972,
+      "learning_rate": 0.00019402,
+      "loss": 0.1642,
+      "mean_token_accuracy": 0.9325390756130219,
+      "num_tokens": 35030.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.07676753401756287,
+      "learning_rate": 0.00019362,
+      "loss": 0.1633,
+      "mean_token_accuracy": 0.9348760217428207,
+      "num_tokens": 37359.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 0.06781225651502609,
+      "learning_rate": 0.00019322,
+      "loss": 0.1589,
+      "mean_token_accuracy": 0.936154904961586,
+      "num_tokens": 39707.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.10010460019111633,
+      "learning_rate": 0.00019282000000000001,
+      "loss": 0.1583,
+      "mean_token_accuracy": 0.9410124599933625,
+      "num_tokens": 42071.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 0.07932794839143753,
+      "learning_rate": 0.00019242,
+      "loss": 0.1608,
+      "mean_token_accuracy": 0.9380002528429031,
+      "num_tokens": 44404.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.06678586453199387,
+      "learning_rate": 0.00019202,
+      "loss": 0.1633,
+      "mean_token_accuracy": 0.9347729980945587,
+      "num_tokens": 46715.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.05118393525481224,
+      "learning_rate": 0.00019162,
+      "loss": 0.1621,
+      "mean_token_accuracy": 0.9356200367212295,
+      "num_tokens": 49030.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.07563836127519608,
+      "learning_rate": 0.00019122,
+      "loss": 0.1603,
+      "mean_token_accuracy": 0.9362942427396774,
+      "num_tokens": 51366.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.053388580679893494,
+      "learning_rate": 0.00019082,
+      "loss": 0.1585,
+      "mean_token_accuracy": 0.9377258807420731,
+      "num_tokens": 53706.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.05659119412302971,
+      "learning_rate": 0.00019042,
+      "loss": 0.1575,
+      "mean_token_accuracy": 0.937972965836525,
+      "num_tokens": 56052.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.04934714362025261,
+      "learning_rate": 0.00019002,
+      "loss": 0.1606,
+      "mean_token_accuracy": 0.9356311202049256,
+      "num_tokens": 58374.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.05647804215550423,
+      "learning_rate": 0.00018962000000000002,
+      "loss": 0.1587,
+      "mean_token_accuracy": 0.9353525519371033,
+      "num_tokens": 60706.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 0.058523017913103104,
+      "learning_rate": 0.00018922,
+      "loss": 0.1595,
+      "mean_token_accuracy": 0.9371987581253052,
+      "num_tokens": 63021.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.03793497756123543,
+      "learning_rate": 0.00018882000000000003,
+      "loss": 0.1584,
+      "mean_token_accuracy": 0.9341553807258606,
+      "num_tokens": 65369.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 0.04743633046746254,
+      "learning_rate": 0.00018842000000000002,
+      "loss": 0.1586,
+      "mean_token_accuracy": 0.936157900094986,
+      "num_tokens": 67700.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.05463261529803276,
+      "learning_rate": 0.00018802,
+      "loss": 0.1578,
+      "mean_token_accuracy": 0.937694975733757,
+      "num_tokens": 70038.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 0.11279874294996262,
+      "learning_rate": 0.00018762000000000002,
+      "loss": 0.1584,
+      "mean_token_accuracy": 0.9382745862007141,
+      "num_tokens": 72367.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.050823234021663666,
+      "learning_rate": 0.00018722,
+      "loss": 0.1602,
+      "mean_token_accuracy": 0.9388011395931244,
+      "num_tokens": 74677.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 0.04983159899711609,
+      "learning_rate": 0.00018682000000000003,
+      "loss": 0.1584,
+      "mean_token_accuracy": 0.9374112606048584,
+      "num_tokens": 77014.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.05084273964166641,
+      "learning_rate": 0.00018642000000000002,
+      "loss": 0.1591,
+      "mean_token_accuracy": 0.9387890577316285,
+      "num_tokens": 79339.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.04936506226658821,
+      "learning_rate": 0.00018602,
+      "loss": 0.157,
+      "mean_token_accuracy": 0.9359721839427948,
+      "num_tokens": 81688.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.04119481146335602,
+      "learning_rate": 0.00018562000000000003,
+      "loss": 0.1584,
+      "mean_token_accuracy": 0.9359663873910904,
+      "num_tokens": 84025.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 0.03988514095544815,
+      "learning_rate": 0.00018522000000000002,
+      "loss": 0.1595,
+      "mean_token_accuracy": 0.9372004926204681,
+      "num_tokens": 86341.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.04381653666496277,
+      "learning_rate": 0.00018482,
+      "loss": 0.1591,
+      "mean_token_accuracy": 0.9373360633850097,
+      "num_tokens": 88665.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 0.03504428267478943,
+      "learning_rate": 0.00018442000000000003,
+      "loss": 0.1579,
+      "mean_token_accuracy": 0.9403579801321029,
+      "num_tokens": 90997.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.03745226562023163,
+      "learning_rate": 0.00018402000000000002,
+      "loss": 0.1584,
+      "mean_token_accuracy": 0.9388439536094666,
+      "num_tokens": 93322.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 0.033838506788015366,
+      "learning_rate": 0.00018362,
+      "loss": 0.1562,
+      "mean_token_accuracy": 0.9360319077968597,
+      "num_tokens": 95688.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.0314440056681633,
+      "learning_rate": 0.00018322000000000002,
+      "loss": 0.1596,
+      "mean_token_accuracy": 0.9349893003702163,
+      "num_tokens": 98005.0,
+      "step": 840
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 0.06577116250991821,
+      "learning_rate": 0.00018282000000000001,
+      "loss": 0.1589,
+      "mean_token_accuracy": 0.9364802747964859,
+      "num_tokens": 100327.0,
+      "step": 860
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.029735982418060303,
+      "learning_rate": 0.00018242,
+      "loss": 0.1576,
+      "mean_token_accuracy": 0.9365677893161773,
+      "num_tokens": 102671.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.03155644237995148,
+      "learning_rate": 0.00018202000000000002,
+      "loss": 0.1587,
+      "mean_token_accuracy": 0.9387517213821411,
+      "num_tokens": 104996.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.027411427348852158,
+      "learning_rate": 0.00018162,
+      "loss": 0.1581,
+      "mean_token_accuracy": 0.9342827945947647,
+      "num_tokens": 107337.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 0.024014495313167572,
+      "learning_rate": 0.00018122,
+      "loss": 0.1583,
+      "mean_token_accuracy": 0.9355534523725509,
+      "num_tokens": 109674.0,
+      "step": 940
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.02990046516060829,
+      "learning_rate": 0.00018082000000000002,
+      "loss": 0.1577,
+      "mean_token_accuracy": 0.9373938798904419,
+      "num_tokens": 112015.0,
+      "step": 960
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 0.020676879212260246,
+      "learning_rate": 0.00018042,
+      "loss": 0.1582,
+      "mean_token_accuracy": 0.9363098949193954,
+      "num_tokens": 114349.0,
+      "step": 980
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.024556942284107208,
+      "learning_rate": 0.00018002,
+      "loss": 0.159,
+      "mean_token_accuracy": 0.9355833351612091,
+      "num_tokens": 116672.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1412368074399744.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c5ae63f5ecd2b63b9e730d8c4e9bd14c8065d94e890b963ef26d9d377b00df
+size 6161

checkpoint-10000/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-2B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-10000/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-10000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53f385c6600b2d070ffd2934b9174b2ed762021c34ee61a5cbb8a09685a2745
+size 17465792

checkpoint-10000/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-10000/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d371585b94eb7ec6c3babab6bb0279251252c30f921987264b29c1752f7935a4
+size 35047307

checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b36f9ab185c91cea00b0da87fa81eb74aec5d9f4fa71e80f8c32124a0dfe159
+size 14455

checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9f154b1359afdda4d3ed65870a0e8dc4d46259d77c6ba1858bc2095aee8d67
+size 1465

checkpoint-10000/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-10000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

checkpoint-10000/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c5ae63f5ecd2b63b9e730d8c4e9bd14c8065d94e890b963ef26d9d377b00df
+size 6161

checkpoint-1200/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-2B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-1200/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33eb62455eb0e4ebc4faa49b400e4541cb7077d607ec322fdbdd86ac9c7665b
+size 17465792

checkpoint-1200/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-1200/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e3872256c4b67f400c3dfe14585031ce24f6c9bd827c0520a682ee1944e2bc
+size 35047307

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15177edf9ebfb5ad50d36052fe51a713a6872c0cf28e4a5ad6266ec66e41b5aa
+size 14455

checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:395e220ed3170149372bddba65060a46bad10758a1f0f81e9afc2b3b84112f90
+size 1465

checkpoint-1200/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-1200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

checkpoint-1200/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1200/trainer_state.json

@@ -0,0 +1,574 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.24,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004,
+      "grad_norm": 2.131298542022705,
+      "learning_rate": 0.00019962000000000002,
+      "loss": 2.0121,
+      "mean_token_accuracy": 0.6703190118074417,
+      "num_tokens": 2348.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 1.2890418767929077,
+      "learning_rate": 0.00019922,
+      "loss": 0.2751,
+      "mean_token_accuracy": 0.9120438575744629,
+      "num_tokens": 4697.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 0.8126867413520813,
+      "learning_rate": 0.00019882,
+      "loss": 0.1966,
+      "mean_token_accuracy": 0.9203487157821655,
+      "num_tokens": 7014.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.6051881313323975,
+      "learning_rate": 0.00019842000000000001,
+      "loss": 0.1851,
+      "mean_token_accuracy": 0.9291799515485764,
+      "num_tokens": 9327.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.6378348469734192,
+      "learning_rate": 0.00019802,
+      "loss": 0.1766,
+      "mean_token_accuracy": 0.9286984890699387,
+      "num_tokens": 11670.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 0.624138593673706,
+      "learning_rate": 0.00019762,
+      "loss": 0.1784,
+      "mean_token_accuracy": 0.9264282643795013,
+      "num_tokens": 14000.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 0.2111046463251114,
+      "learning_rate": 0.00019722,
+      "loss": 0.1702,
+      "mean_token_accuracy": 0.9321970880031586,
+      "num_tokens": 16329.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.5350440740585327,
+      "learning_rate": 0.00019682,
+      "loss": 0.171,
+      "mean_token_accuracy": 0.9311463803052902,
+      "num_tokens": 18667.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 0.19237647950649261,
+      "learning_rate": 0.00019642,
+      "loss": 0.167,
+      "mean_token_accuracy": 0.9345656305551528,
+      "num_tokens": 20985.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.28153756260871887,
+      "learning_rate": 0.00019602,
+      "loss": 0.1674,
+      "mean_token_accuracy": 0.9329667061567306,
+      "num_tokens": 23325.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 0.8545331954956055,
+      "learning_rate": 0.00019562,
+      "loss": 0.166,
+      "mean_token_accuracy": 0.9344212204217911,
+      "num_tokens": 25670.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.24941129982471466,
+      "learning_rate": 0.00019522,
+      "loss": 0.1661,
+      "mean_token_accuracy": 0.934859549999237,
+      "num_tokens": 28016.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 0.29549548029899597,
+      "learning_rate": 0.00019482,
+      "loss": 0.1707,
+      "mean_token_accuracy": 0.9345517784357071,
+      "num_tokens": 30345.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.20388178527355194,
+      "learning_rate": 0.00019442,
+      "loss": 0.1673,
+      "mean_token_accuracy": 0.9353183209896088,
+      "num_tokens": 32691.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.10762794315814972,
+      "learning_rate": 0.00019402,
+      "loss": 0.1642,
+      "mean_token_accuracy": 0.9325390756130219,
+      "num_tokens": 35030.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.07676753401756287,
+      "learning_rate": 0.00019362,
+      "loss": 0.1633,
+      "mean_token_accuracy": 0.9348760217428207,
+      "num_tokens": 37359.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 0.06781225651502609,
+      "learning_rate": 0.00019322,
+      "loss": 0.1589,
+      "mean_token_accuracy": 0.936154904961586,
+      "num_tokens": 39707.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.10010460019111633,
+      "learning_rate": 0.00019282000000000001,
+      "loss": 0.1583,
+      "mean_token_accuracy": 0.9410124599933625,
+      "num_tokens": 42071.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 0.07932794839143753,
+      "learning_rate": 0.00019242,
+      "loss": 0.1608,
+      "mean_token_accuracy": 0.9380002528429031,
+      "num_tokens": 44404.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.06678586453199387,
+      "learning_rate": 0.00019202,
+      "loss": 0.1633,
+      "mean_token_accuracy": 0.9347729980945587,
+      "num_tokens": 46715.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.05118393525481224,
+      "learning_rate": 0.00019162,
+      "loss": 0.1621,
+      "mean_token_accuracy": 0.9356200367212295,
+      "num_tokens": 49030.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.07563836127519608,
+      "learning_rate": 0.00019122,
+      "loss": 0.1603,
+      "mean_token_accuracy": 0.9362942427396774,
+      "num_tokens": 51366.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.053388580679893494,
+      "learning_rate": 0.00019082,
+      "loss": 0.1585,
+      "mean_token_accuracy": 0.9377258807420731,
+      "num_tokens": 53706.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.05659119412302971,
+      "learning_rate": 0.00019042,
+      "loss": 0.1575,
+      "mean_token_accuracy": 0.937972965836525,
+      "num_tokens": 56052.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.04934714362025261,
+      "learning_rate": 0.00019002,
+      "loss": 0.1606,
+      "mean_token_accuracy": 0.9356311202049256,
+      "num_tokens": 58374.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.05647804215550423,
+      "learning_rate": 0.00018962000000000002,
+      "loss": 0.1587,
+      "mean_token_accuracy": 0.9353525519371033,
+      "num_tokens": 60706.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 0.058523017913103104,
+      "learning_rate": 0.00018922,
+      "loss": 0.1595,
+      "mean_token_accuracy": 0.9371987581253052,
+      "num_tokens": 63021.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.03793497756123543,
+      "learning_rate": 0.00018882000000000003,
+      "loss": 0.1584,
+      "mean_token_accuracy": 0.9341553807258606,
+      "num_tokens": 65369.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 0.04743633046746254,
+      "learning_rate": 0.00018842000000000002,
+      "loss": 0.1586,
+      "mean_token_accuracy": 0.936157900094986,
+      "num_tokens": 67700.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.05463261529803276,
+      "learning_rate": 0.00018802,
+      "loss": 0.1578,
+      "mean_token_accuracy": 0.937694975733757,
+      "num_tokens": 70038.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 0.11279874294996262,
+      "learning_rate": 0.00018762000000000002,
+      "loss": 0.1584,
+      "mean_token_accuracy": 0.9382745862007141,
+      "num_tokens": 72367.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.050823234021663666,
+      "learning_rate": 0.00018722,
+      "loss": 0.1602,
+      "mean_token_accuracy": 0.9388011395931244,
+      "num_tokens": 74677.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 0.04983159899711609,
+      "learning_rate": 0.00018682000000000003,
+      "loss": 0.1584,
+      "mean_token_accuracy": 0.9374112606048584,
+      "num_tokens": 77014.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 0.05084273964166641,
+      "learning_rate": 0.00018642000000000002,
+      "loss": 0.1591,
+      "mean_token_accuracy": 0.9387890577316285,
+      "num_tokens": 79339.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.04936506226658821,
+      "learning_rate": 0.00018602,
+      "loss": 0.157,
+      "mean_token_accuracy": 0.9359721839427948,
+      "num_tokens": 81688.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 0.04119481146335602,
+      "learning_rate": 0.00018562000000000003,
+      "loss": 0.1584,
+      "mean_token_accuracy": 0.9359663873910904,
+      "num_tokens": 84025.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 0.03988514095544815,
+      "learning_rate": 0.00018522000000000002,
+      "loss": 0.1595,
+      "mean_token_accuracy": 0.9372004926204681,
+      "num_tokens": 86341.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 0.04381653666496277,
+      "learning_rate": 0.00018482,
+      "loss": 0.1591,
+      "mean_token_accuracy": 0.9373360633850097,
+      "num_tokens": 88665.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 0.03504428267478943,
+      "learning_rate": 0.00018442000000000003,
+      "loss": 0.1579,
+      "mean_token_accuracy": 0.9403579801321029,
+      "num_tokens": 90997.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.03745226562023163,
+      "learning_rate": 0.00018402000000000002,
+      "loss": 0.1584,
+      "mean_token_accuracy": 0.9388439536094666,
+      "num_tokens": 93322.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 0.033838506788015366,
+      "learning_rate": 0.00018362,
+      "loss": 0.1562,
+      "mean_token_accuracy": 0.9360319077968597,
+      "num_tokens": 95688.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.0314440056681633,
+      "learning_rate": 0.00018322000000000002,
+      "loss": 0.1596,
+      "mean_token_accuracy": 0.9349893003702163,
+      "num_tokens": 98005.0,
+      "step": 840
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 0.06577116250991821,
+      "learning_rate": 0.00018282000000000001,
+      "loss": 0.1589,
+      "mean_token_accuracy": 0.9364802747964859,
+      "num_tokens": 100327.0,
+      "step": 860
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.029735982418060303,
+      "learning_rate": 0.00018242,
+      "loss": 0.1576,
+      "mean_token_accuracy": 0.9365677893161773,
+      "num_tokens": 102671.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.03155644237995148,
+      "learning_rate": 0.00018202000000000002,
+      "loss": 0.1587,
+      "mean_token_accuracy": 0.9387517213821411,
+      "num_tokens": 104996.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.027411427348852158,
+      "learning_rate": 0.00018162,
+      "loss": 0.1581,
+      "mean_token_accuracy": 0.9342827945947647,
+      "num_tokens": 107337.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 0.024014495313167572,
+      "learning_rate": 0.00018122,
+      "loss": 0.1583,
+      "mean_token_accuracy": 0.9355534523725509,
+      "num_tokens": 109674.0,
+      "step": 940
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.02990046516060829,
+      "learning_rate": 0.00018082000000000002,
+      "loss": 0.1577,
+      "mean_token_accuracy": 0.9373938798904419,
+      "num_tokens": 112015.0,
+      "step": 960
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 0.020676879212260246,
+      "learning_rate": 0.00018042,
+      "loss": 0.1582,
+      "mean_token_accuracy": 0.9363098949193954,
+      "num_tokens": 114349.0,
+      "step": 980
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.024556942284107208,
+      "learning_rate": 0.00018002,
+      "loss": 0.159,
+      "mean_token_accuracy": 0.9355833351612091,
+      "num_tokens": 116672.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 0.22343556582927704,
+      "learning_rate": 0.00017962000000000002,
+      "loss": 0.157,
+      "mean_token_accuracy": 0.9363467574119568,
+      "num_tokens": 119023.0,
+      "step": 1020
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.515048623085022,
+      "learning_rate": 0.00017922,
+      "loss": 0.1585,
+      "mean_token_accuracy": 0.9374267637729645,
+      "num_tokens": 121366.0,
+      "step": 1040
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 0.2672664225101471,
+      "learning_rate": 0.00017882,
+      "loss": 0.1704,
+      "mean_token_accuracy": 0.938492265343666,
+      "num_tokens": 123719.0,
+      "step": 1060
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.11909265071153641,
+      "learning_rate": 0.00017842000000000002,
+      "loss": 0.1752,
+      "mean_token_accuracy": 0.9297878712415695,
+      "num_tokens": 126053.0,
+      "step": 1080
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.11977271735668182,
+      "learning_rate": 0.00017802,
+      "loss": 0.1652,
+      "mean_token_accuracy": 0.9360411554574967,
+      "num_tokens": 128379.0,
+      "step": 1100
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.17722292244434357,
+      "learning_rate": 0.00017762,
+      "loss": 0.1697,
+      "mean_token_accuracy": 0.9314894318580628,
+      "num_tokens": 130700.0,
+      "step": 1120
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 0.8375388979911804,
+      "learning_rate": 0.00017722000000000001,
+      "loss": 0.1895,
+      "mean_token_accuracy": 0.9316652357578278,
+      "num_tokens": 133026.0,
+      "step": 1140
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.10569056123495102,
+      "learning_rate": 0.00017682,
+      "loss": 0.1679,
+      "mean_token_accuracy": 0.9333775132894516,
+      "num_tokens": 135371.0,
+      "step": 1160
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 0.07626856118440628,
+      "learning_rate": 0.00017642,
+      "loss": 0.1613,
+      "mean_token_accuracy": 0.9380175620317459,
+      "num_tokens": 137695.0,
+      "step": 1180
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.06852507591247559,
+      "learning_rate": 0.00017602,
+      "loss": 0.1693,
+      "mean_token_accuracy": 0.9329774439334869,
+      "num_tokens": 140007.0,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1694276209833984.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c5ae63f5ecd2b63b9e730d8c4e9bd14c8065d94e890b963ef26d9d377b00df
+size 6161