Upload Qwen2-VL weather satellite AdaLoRA adapter

.gitattributes

@@ -33,3 +33,14 @@ 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-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-80/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-7B-Instruct
+library_name: peft
+model_name: adalora_weather_model
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for adalora_weather_model
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-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
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/azdinsahir11-university-mohamed-v/qwen2vl-adalora-weather/runs/6q7w54jc) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.16.0
+- TRL: 0.19.1
+- Transformers: 4.53.2
+- Pytorch: 2.6.0+cu124
+- Datasets: 4.0.0
+- Tokenizers: 0.21.2
+
+## 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 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-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": 24,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 12,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "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 sha256:2dcab183f9a9603d3cc21b369b2058993b02b28454ed14ad28f2309c884bbf58
+size 30310976

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-120/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-7B-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 0.16.0

checkpoint-120/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-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": 24,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 12,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-120/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5b6fac98fc971c2c6b22d9b68222a1fb75595051451c06ae6688b98264080c9
+size 30310976

checkpoint-120/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-120/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-120/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf9bbd69f2fd2466f04760490900de0a929e09714c9f6501029d6e85ae59cc96
+size 60743290

checkpoint-120/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5c0756aedd487492bad1b35d43af521df515858b7c745fc7d6d1a0d10e46966
+size 14244

checkpoint-120/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fade00f111acdd833f7b0d851d6af49db2dd6691910453c9ee7b286f7574ebc4
+size 1064

checkpoint-120/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-120/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

checkpoint-120/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-120/trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_global_step": 120,
+  "best_metric": 0.2297067493200302,
+  "best_model_checkpoint": "./adalora_weather_model/checkpoint-120",
+  "epoch": 1.2262210796915167,
+  "eval_steps": 20,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 3.2930359840393066,
+      "learning_rate": 6.75e-05,
+      "loss": 16.7516,
+      "mean_token_accuracy": 0.5331788018345833,
+      "num_tokens": 171254.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 5.34633731842041,
+      "learning_rate": 0.0001425,
+      "loss": 14.2345,
+      "mean_token_accuracy": 0.5723872803151607,
+      "num_tokens": 342816.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "eval_loss": 1.4267879724502563,
+      "eval_mean_token_accuracy": 0.6206505249708126,
+      "eval_num_tokens": 342816.0,
+      "eval_runtime": 103.2151,
+      "eval_samples_per_second": 1.889,
+      "eval_steps_per_second": 1.889,
+      "step": 20
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 8.451922416687012,
+      "learning_rate": 0.00021749999999999997,
+      "loss": 8.4633,
+      "mean_token_accuracy": 0.7056376278400421,
+      "num_tokens": 514067.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 3.2435312271118164,
+      "learning_rate": 0.00029249999999999995,
+      "loss": 3.6174,
+      "mean_token_accuracy": 0.8711350880563259,
+      "num_tokens": 685570.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "eval_loss": 0.34826213121414185,
+      "eval_mean_token_accuracy": 0.8939384683584556,
+      "eval_num_tokens": 685570.0,
+      "eval_runtime": 103.283,
+      "eval_samples_per_second": 1.888,
+      "eval_steps_per_second": 1.888,
+      "step": 40
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 3.4071648120880127,
+      "learning_rate": 0.0002995163544683256,
+      "loss": 2.9181,
+      "mean_token_accuracy": 0.8942699111998081,
+      "num_tokens": 856740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 2.6412267684936523,
+      "learning_rate": 0.00029784849709745616,
+      "loss": 2.638,
+      "mean_token_accuracy": 0.9004527874290943,
+      "num_tokens": 1028000.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "eval_loss": 0.29210129380226135,
+      "eval_mean_token_accuracy": 0.9071287249907469,
+      "eval_num_tokens": 1028000.0,
+      "eval_runtime": 103.2512,
+      "eval_samples_per_second": 1.889,
+      "eval_steps_per_second": 1.889,
+      "step": 60
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 10.460367202758789,
+      "learning_rate": 0.0002950037303267096,
+      "loss": 2.2428,
+      "mean_token_accuracy": 0.9117808744311333,
+      "num_tokens": 1199650.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 5.442368984222412,
+      "learning_rate": 0.0002910046991800035,
+      "loss": 2.0227,
+      "mean_token_accuracy": 0.9168093383312226,
+      "num_tokens": 1370524.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "eval_loss": 0.2537098526954651,
+      "eval_mean_token_accuracy": 0.9172265719144772,
+      "eval_num_tokens": 1370524.0,
+      "eval_runtime": 103.2432,
+      "eval_samples_per_second": 1.889,
+      "eval_steps_per_second": 1.889,
+      "step": 80
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 2.3143043518066406,
+      "learning_rate": 0.00028588323690176954,
+      "loss": 1.9486,
+      "mean_token_accuracy": 0.9203169830143452,
+      "num_tokens": 1542159.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 2.387840986251831,
+      "learning_rate": 0.0002796801115567139,
+      "loss": 1.7171,
+      "mean_token_accuracy": 0.9238405316262632,
+      "num_tokens": 1700574.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "eval_loss": 0.237007275223732,
+      "eval_mean_token_accuracy": 0.9215406671548501,
+      "eval_num_tokens": 1700574.0,
+      "eval_runtime": 102.9604,
+      "eval_samples_per_second": 1.894,
+      "eval_steps_per_second": 1.894,
+      "step": 100
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 2.3169972896575928,
+      "learning_rate": 0.0002724447015062708,
+      "loss": 1.7776,
+      "mean_token_accuracy": 0.925829317420721,
+      "num_tokens": 1871783.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 2.366626262664795,
+      "learning_rate": 0.0002642346023450357,
+      "loss": 1.7638,
+      "mean_token_accuracy": 0.9251113034784794,
+      "num_tokens": 2043203.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "eval_loss": 0.2297067493200302,
+      "eval_mean_token_accuracy": 0.9240646191132375,
+      "eval_num_tokens": 2043203.0,
+      "eval_runtime": 103.0662,
+      "eval_samples_per_second": 1.892,
+      "eval_steps_per_second": 1.892,
+      "step": 120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 392,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.505733457741926e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-120/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ef167df2c1b603606608ab0230b213acbe27e0c1433603800a4bb1e7d7f687
+size 5752

checkpoint-160/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-7B-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 0.16.0

checkpoint-160/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-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": 24,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 12,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-160/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43200de8ef24785e0daa8e76a30866639c95489a27cf7991b36a3ea5051c5c5e
+size 30310976

checkpoint-160/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-160/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-160/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c9c6fcc0d93ed94cc95dbe6ee2fb73184e2eff3acdf3d35a10c76c7fb2de12
+size 60743290

checkpoint-160/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d817ecfe2a411deb1f606ac81facbdf5c0b59545ea5c76e24c4d2933747348
+size 14244

checkpoint-160/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4078e2a7c02601d5e0eeb618902a971f3d69ca4bff8d896454ff2d0d00f255c8
+size 1064

checkpoint-160/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-160/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

checkpoint-160/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-160/trainer_state.json

@@ -0,0 +1,258 @@
+{
+  "best_global_step": 160,
+  "best_metric": 0.21823178231716156,
+  "best_model_checkpoint": "./adalora_weather_model/checkpoint-160",
+  "epoch": 1.6375321336760926,
+  "eval_steps": 20,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 3.2930359840393066,
+      "learning_rate": 6.75e-05,
+      "loss": 16.7516,
+      "mean_token_accuracy": 0.5331788018345833,
+      "num_tokens": 171254.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 5.34633731842041,
+      "learning_rate": 0.0001425,
+      "loss": 14.2345,
+      "mean_token_accuracy": 0.5723872803151607,
+      "num_tokens": 342816.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "eval_loss": 1.4267879724502563,
+      "eval_mean_token_accuracy": 0.6206505249708126,
+      "eval_num_tokens": 342816.0,
+      "eval_runtime": 103.2151,
+      "eval_samples_per_second": 1.889,
+      "eval_steps_per_second": 1.889,
+      "step": 20
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 8.451922416687012,
+      "learning_rate": 0.00021749999999999997,
+      "loss": 8.4633,
+      "mean_token_accuracy": 0.7056376278400421,
+      "num_tokens": 514067.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 3.2435312271118164,
+      "learning_rate": 0.00029249999999999995,
+      "loss": 3.6174,
+      "mean_token_accuracy": 0.8711350880563259,
+      "num_tokens": 685570.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "eval_loss": 0.34826213121414185,
+      "eval_mean_token_accuracy": 0.8939384683584556,
+      "eval_num_tokens": 685570.0,
+      "eval_runtime": 103.283,
+      "eval_samples_per_second": 1.888,
+      "eval_steps_per_second": 1.888,
+      "step": 40
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 3.4071648120880127,
+      "learning_rate": 0.0002995163544683256,
+      "loss": 2.9181,
+      "mean_token_accuracy": 0.8942699111998081,
+      "num_tokens": 856740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 2.6412267684936523,
+      "learning_rate": 0.00029784849709745616,
+      "loss": 2.638,
+      "mean_token_accuracy": 0.9004527874290943,
+      "num_tokens": 1028000.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "eval_loss": 0.29210129380226135,
+      "eval_mean_token_accuracy": 0.9071287249907469,
+      "eval_num_tokens": 1028000.0,
+      "eval_runtime": 103.2512,
+      "eval_samples_per_second": 1.889,
+      "eval_steps_per_second": 1.889,
+      "step": 60
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 10.460367202758789,
+      "learning_rate": 0.0002950037303267096,
+      "loss": 2.2428,
+      "mean_token_accuracy": 0.9117808744311333,
+      "num_tokens": 1199650.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 5.442368984222412,
+      "learning_rate": 0.0002910046991800035,
+      "loss": 2.0227,
+      "mean_token_accuracy": 0.9168093383312226,
+      "num_tokens": 1370524.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "eval_loss": 0.2537098526954651,
+      "eval_mean_token_accuracy": 0.9172265719144772,
+      "eval_num_tokens": 1370524.0,
+      "eval_runtime": 103.2432,
+      "eval_samples_per_second": 1.889,
+      "eval_steps_per_second": 1.889,
+      "step": 80
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 2.3143043518066406,
+      "learning_rate": 0.00028588323690176954,
+      "loss": 1.9486,
+      "mean_token_accuracy": 0.9203169830143452,
+      "num_tokens": 1542159.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 2.387840986251831,
+      "learning_rate": 0.0002796801115567139,
+      "loss": 1.7171,
+      "mean_token_accuracy": 0.9238405316262632,
+      "num_tokens": 1700574.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "eval_loss": 0.237007275223732,
+      "eval_mean_token_accuracy": 0.9215406671548501,
+      "eval_num_tokens": 1700574.0,
+      "eval_runtime": 102.9604,
+      "eval_samples_per_second": 1.894,
+      "eval_steps_per_second": 1.894,
+      "step": 100
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 2.3169972896575928,
+      "learning_rate": 0.0002724447015062708,
+      "loss": 1.7776,
+      "mean_token_accuracy": 0.925829317420721,
+      "num_tokens": 1871783.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 2.366626262664795,
+      "learning_rate": 0.0002642346023450357,
+      "loss": 1.7638,
+      "mean_token_accuracy": 0.9251113034784794,
+      "num_tokens": 2043203.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "eval_loss": 0.2297067493200302,
+      "eval_mean_token_accuracy": 0.9240646191132375,
+      "eval_num_tokens": 2043203.0,
+      "eval_runtime": 103.0662,
+      "eval_samples_per_second": 1.892,
+      "eval_steps_per_second": 1.892,
+      "step": 120
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 2.324875593185425,
+      "learning_rate": 0.0002551151684260553,
+      "loss": 1.7129,
+      "mean_token_accuracy": 0.9276402719318867,
+      "num_tokens": 2214867.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 2.4916014671325684,
+      "learning_rate": 0.0002451589926245468,
+      "loss": 1.6328,
+      "mean_token_accuracy": 0.9298155799508094,
+      "num_tokens": 2385981.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "eval_loss": 0.22466857731342316,
+      "eval_mean_token_accuracy": 0.9257748848352677,
+      "eval_num_tokens": 2385981.0,
+      "eval_runtime": 103.2959,
+      "eval_samples_per_second": 1.888,
+      "eval_steps_per_second": 1.888,
+      "step": 140
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 2.331782341003418,
+      "learning_rate": 0.00023444532848124715,
+      "loss": 1.6382,
+      "mean_token_accuracy": 0.9296720393002034,
+      "num_tokens": 2557432.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "grad_norm": 2.2701163291931152,
+      "learning_rate": 0.00022305945932527308,
+      "loss": 1.6396,
+      "mean_token_accuracy": 0.9298155024647713,
+      "num_tokens": 2729083.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "eval_loss": 0.21823178231716156,
+      "eval_mean_token_accuracy": 0.92809411745805,
+      "eval_num_tokens": 2729083.0,
+      "eval_runtime": 103.3054,
+      "eval_samples_per_second": 1.888,
+      "eval_steps_per_second": 1.888,
+      "step": 160
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 392,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.269670002542807e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-160/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ef167df2c1b603606608ab0230b213acbe27e0c1433603800a4bb1e7d7f687
+size 5752

checkpoint-200/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-7B-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 0.16.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-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": 24,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 12,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aebc51df76ccb2c08e1052ffacfceb30d649f17bc567af73e62c3164ec3481a6
+size 30310976

checkpoint-200/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-200/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-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd0bb207e0059cfa57f468254032fd110aeb2cdb2da5a251dcf9b7335205e67
+size 60743290

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d9c0eced34865636bbbde9c8b8e66233c183eb1678743888d0b307a1c1a1e97
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466a3e032ea2a04b4fd1ef71f9841bdf4f29fc0770db16c430c9234351b79982
+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 sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

checkpoint-200/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-200/trainer_state.json

@@ -0,0 +1,314 @@
+{
+  "best_global_step": 200,
+  "best_metric": 0.2087530493736267,
+  "best_model_checkpoint": "./adalora_weather_model/checkpoint-200",
+  "epoch": 2.0411311053984575,
+  "eval_steps": 20,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 3.2930359840393066,
+      "learning_rate": 6.75e-05,
+      "loss": 16.7516,
+      "mean_token_accuracy": 0.5331788018345833,
+      "num_tokens": 171254.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 5.34633731842041,
+      "learning_rate": 0.0001425,
+      "loss": 14.2345,
+      "mean_token_accuracy": 0.5723872803151607,
+      "num_tokens": 342816.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "eval_loss": 1.4267879724502563,
+      "eval_mean_token_accuracy": 0.6206505249708126,
+      "eval_num_tokens": 342816.0,
+      "eval_runtime": 103.2151,
+      "eval_samples_per_second": 1.889,
+      "eval_steps_per_second": 1.889,
+      "step": 20
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 8.451922416687012,
+      "learning_rate": 0.00021749999999999997,
+      "loss": 8.4633,
+      "mean_token_accuracy": 0.7056376278400421,
+      "num_tokens": 514067.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 3.2435312271118164,
+      "learning_rate": 0.00029249999999999995,
+      "loss": 3.6174,
+      "mean_token_accuracy": 0.8711350880563259,
+      "num_tokens": 685570.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "eval_loss": 0.34826213121414185,
+      "eval_mean_token_accuracy": 0.8939384683584556,
+      "eval_num_tokens": 685570.0,
+      "eval_runtime": 103.283,
+      "eval_samples_per_second": 1.888,
+      "eval_steps_per_second": 1.888,
+      "step": 40
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 3.4071648120880127,
+      "learning_rate": 0.0002995163544683256,
+      "loss": 2.9181,
+      "mean_token_accuracy": 0.8942699111998081,
+      "num_tokens": 856740.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 2.6412267684936523,
+      "learning_rate": 0.00029784849709745616,
+      "loss": 2.638,
+      "mean_token_accuracy": 0.9004527874290943,
+      "num_tokens": 1028000.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "eval_loss": 0.29210129380226135,
+      "eval_mean_token_accuracy": 0.9071287249907469,
+      "eval_num_tokens": 1028000.0,
+      "eval_runtime": 103.2512,
+      "eval_samples_per_second": 1.889,
+      "eval_steps_per_second": 1.889,
+      "step": 60
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 10.460367202758789,
+      "learning_rate": 0.0002950037303267096,
+      "loss": 2.2428,
+      "mean_token_accuracy": 0.9117808744311333,
+      "num_tokens": 1199650.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 5.442368984222412,
+      "learning_rate": 0.0002910046991800035,
+      "loss": 2.0227,
+      "mean_token_accuracy": 0.9168093383312226,
+      "num_tokens": 1370524.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "eval_loss": 0.2537098526954651,
+      "eval_mean_token_accuracy": 0.9172265719144772,
+      "eval_num_tokens": 1370524.0,
+      "eval_runtime": 103.2432,
+      "eval_samples_per_second": 1.889,
+      "eval_steps_per_second": 1.889,
+      "step": 80
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 2.3143043518066406,
+      "learning_rate": 0.00028588323690176954,
+      "loss": 1.9486,
+      "mean_token_accuracy": 0.9203169830143452,
+      "num_tokens": 1542159.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 2.387840986251831,
+      "learning_rate": 0.0002796801115567139,
+      "loss": 1.7171,
+      "mean_token_accuracy": 0.9238405316262632,
+      "num_tokens": 1700574.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "eval_loss": 0.237007275223732,
+      "eval_mean_token_accuracy": 0.9215406671548501,
+      "eval_num_tokens": 1700574.0,
+      "eval_runtime": 102.9604,
+      "eval_samples_per_second": 1.894,
+      "eval_steps_per_second": 1.894,
+      "step": 100
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 2.3169972896575928,
+      "learning_rate": 0.0002724447015062708,
+      "loss": 1.7776,
+      "mean_token_accuracy": 0.925829317420721,
+      "num_tokens": 1871783.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 2.366626262664795,
+      "learning_rate": 0.0002642346023450357,
+      "loss": 1.7638,
+      "mean_token_accuracy": 0.9251113034784794,
+      "num_tokens": 2043203.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "eval_loss": 0.2297067493200302,
+      "eval_mean_token_accuracy": 0.9240646191132375,
+      "eval_num_tokens": 2043203.0,
+      "eval_runtime": 103.0662,
+      "eval_samples_per_second": 1.892,
+      "eval_steps_per_second": 1.892,
+      "step": 120
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 2.324875593185425,
+      "learning_rate": 0.0002551151684260553,
+      "loss": 1.7129,
+      "mean_token_accuracy": 0.9276402719318867,
+      "num_tokens": 2214867.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 2.4916014671325684,
+      "learning_rate": 0.0002451589926245468,
+      "loss": 1.6328,
+      "mean_token_accuracy": 0.9298155799508094,
+      "num_tokens": 2385981.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "eval_loss": 0.22466857731342316,
+      "eval_mean_token_accuracy": 0.9257748848352677,
+      "eval_num_tokens": 2385981.0,
+      "eval_runtime": 103.2959,
+      "eval_samples_per_second": 1.888,
+      "eval_steps_per_second": 1.888,
+      "step": 140
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 2.331782341003418,
+      "learning_rate": 0.00023444532848124715,
+      "loss": 1.6382,
+      "mean_token_accuracy": 0.9296720393002034,
+      "num_tokens": 2557432.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "grad_norm": 2.2701163291931152,
+      "learning_rate": 0.00022305945932527308,
+      "loss": 1.6396,
+      "mean_token_accuracy": 0.9298155024647713,
+      "num_tokens": 2729083.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "eval_loss": 0.21823178231716156,
+      "eval_mean_token_accuracy": 0.92809411745805,
+      "eval_num_tokens": 2729083.0,
+      "eval_runtime": 103.3054,
+      "eval_samples_per_second": 1.888,
+      "eval_steps_per_second": 1.888,
+      "step": 160
+    },
+    {
+      "epoch": 1.7403598971722365,
+      "grad_norm": 2.184347629547119,
+      "learning_rate": 0.0002110920193984228,
+      "loss": 1.667,
+      "mean_token_accuracy": 0.928074149042368,
+      "num_tokens": 2900445.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.8431876606683804,
+      "grad_norm": 2.0277137756347656,
+      "learning_rate": 0.00019863827238493308,
+      "loss": 1.5743,
+      "mean_token_accuracy": 0.9325967490673065,
+      "num_tokens": 3072258.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.8431876606683804,
+      "eval_loss": 0.2095421850681305,
+      "eval_mean_token_accuracy": 0.9297601647866078,
+      "eval_num_tokens": 3072258.0,
+      "eval_runtime": 103.4026,
+      "eval_samples_per_second": 1.886,
+      "eval_steps_per_second": 1.886,
+      "step": 180
+    },
+    {
+      "epoch": 1.9460154241645244,
+      "grad_norm": 2.0166707038879395,
+      "learning_rate": 0.00018579735308976727,
+      "loss": 1.5818,
+      "mean_token_accuracy": 0.9324821837246418,
+      "num_tokens": 3242706.0,
+      "step": 190
+    },
+    {
+      "epoch": 2.0411311053984575,
+      "grad_norm": 2.155334949493408,
+      "learning_rate": 0.00017267147830185608,
+      "loss": 1.4363,
+      "mean_token_accuracy": 0.9325833642804945,
+      "num_tokens": 3401061.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.0411311053984575,
+      "eval_loss": 0.2087530493736267,
+      "eval_mean_token_accuracy": 0.9303424829091781,
+      "eval_num_tokens": 3401061.0,
+      "eval_runtime": 103.3012,
+      "eval_samples_per_second": 1.888,
+      "eval_steps_per_second": 1.888,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 392,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5822989364992717e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ef167df2c1b603606608ab0230b213acbe27e0c1433603800a4bb1e7d7f687
+size 5752