Kaggle retrain: refresh ECG LoRA adapter

README.md

@@ -1,6 +1,11 @@
 ---
-library_name: transformers
-tags: []
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-2B-Instruct
+- lora
+- transformers
 ---
 
 # Model Card for Model ID
@@ -15,7 +20,7 @@ tags: []
 
 <!-- Provide a longer summary of what this model is. -->
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
 
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +201,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

adapter_config.json

@@ -2,10 +2,7 @@
   "alora_invocation_tokens": null,
   "alpha_pattern": {},
   "arrow_config": null,
-  "auto_mapping": {
-    "base_model_class": "Qwen2VLForConditionalGeneration",
-    "parent_library": "transformers.models.qwen2_vl.modeling_qwen2_vl"
-  },
+  "auto_mapping": null,
   "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
   "bias": "none",
   "corda_config": null,
@@ -32,13 +29,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "v_proj",
-    "q_proj",
-    "o_proj"
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj"
   ],
   "target_parameters": null,
-  "task_type": null,
+  "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
   "use_qalora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da5cff03bcd9622a55aac322e5ebeefc2d840664673df9a7d45af9d79c964a43
-size 17465792
+oid sha256:58bf6ff9a49c18127e9e1b5d2d920690a4abe7d9fd5c08b6fbc78f289bc70194
+size 73916992

checkpoint-375/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-2B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoint-375/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "gate_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-375/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffd66772d2d67d46838602e8b9f7df1cd0dd32232bbad4974851d86514d6c300
+size 73916992

checkpoint-375/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea125e48b49c373f7089c89b5a57c982f5fd8fddacc3269e7baeb7af93966b8
+size 37974661

checkpoint-375/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-375/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399f4aaededab8174282d2a4c4bcf01bd75c5d6918859368fda3d74f94455968
+size 1383

checkpoint-375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8cb48116a0c352779fa847a6ff5c6d8dc19bb02af6354b3c93f3afef3a58de
+size 1465

checkpoint-375/trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.09229224175214767,
+      "learning_rate": 0.00019546666666666668,
+      "loss": 7.443636322021485,
+      "step": 20
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.03113839030265808,
+      "learning_rate": 0.00019013333333333334,
+      "loss": 4.766106414794922,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.023965956643223763,
+      "learning_rate": 0.00018480000000000002,
+      "loss": 4.672945022583008,
+      "step": 60
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.04270876571536064,
+      "learning_rate": 0.00017946666666666667,
+      "loss": 4.6693061828613285,
+      "step": 80
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.007624867372214794,
+      "learning_rate": 0.00017413333333333336,
+      "loss": 4.666190338134766,
+      "step": 100
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.005640557501465082,
+      "learning_rate": 0.0001688,
+      "loss": 4.658547973632812,
+      "step": 120
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.005010648630559444,
+      "learning_rate": 0.0001634666666666667,
+      "loss": 4.665555191040039,
+      "step": 140
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.010227741673588753,
+      "learning_rate": 0.00015813333333333335,
+      "loss": 4.662850952148437,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.027864055708050728,
+      "learning_rate": 0.0001528,
+      "loss": 4.663832473754883,
+      "step": 180
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.005860226694494486,
+      "learning_rate": 0.00014746666666666666,
+      "loss": 4.6652687072753904,
+      "step": 200
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.004596560262143612,
+      "learning_rate": 0.00014213333333333334,
+      "loss": 4.672823333740235,
+      "step": 220
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.00873731728643179,
+      "learning_rate": 0.00013680000000000002,
+      "loss": 4.66284065246582,
+      "step": 240
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.01795760542154312,
+      "learning_rate": 0.00013146666666666667,
+      "loss": 4.663800430297852,
+      "step": 260
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.017787013202905655,
+      "learning_rate": 0.00012613333333333335,
+      "loss": 4.658986282348633,
+      "step": 280
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.037507686764001846,
+      "learning_rate": 0.0001208,
+      "loss": 4.65656852722168,
+      "step": 300
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.015351720154285431,
+      "learning_rate": 0.00011546666666666668,
+      "loss": 4.6595008850097654,
+      "step": 320
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.012529321946203709,
+      "learning_rate": 0.00011013333333333333,
+      "loss": 4.6615745544433596,
+      "step": 340
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.01247857604175806,
+      "learning_rate": 0.00010480000000000001,
+      "loss": 4.665129089355469,
+      "step": 360
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5036654810750976.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94007b14b916aeb2fb2fd86c81ba83caa6e64d6db54e98bd315b252e8bbcead8
+size 5201

checkpoint-750/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2-VL-2B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoint-750/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "gate_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-750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58bf6ff9a49c18127e9e1b5d2d920690a4abe7d9fd5c08b6fbc78f289bc70194
+size 73916992

checkpoint-750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5289a2c45aa965669936d8265bcf982e678663cc1e6be266712a55f842a0dead
+size 37974661

checkpoint-750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-750/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c8449f044dc7bc8b739be9d29a57045cc2127d73d54289dce54b6b63ff0e8f
+size 1383

checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a8ae186d646d92c42acb78a59b77d63d1d83998edc100de18cc809b9262387
+size 1465

checkpoint-750/trainer_state.json

@@ -0,0 +1,293 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.09229224175214767,
+      "learning_rate": 0.00019546666666666668,
+      "loss": 7.443636322021485,
+      "step": 20
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.03113839030265808,
+      "learning_rate": 0.00019013333333333334,
+      "loss": 4.766106414794922,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.023965956643223763,
+      "learning_rate": 0.00018480000000000002,
+      "loss": 4.672945022583008,
+      "step": 60
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.04270876571536064,
+      "learning_rate": 0.00017946666666666667,
+      "loss": 4.6693061828613285,
+      "step": 80
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.007624867372214794,
+      "learning_rate": 0.00017413333333333336,
+      "loss": 4.666190338134766,
+      "step": 100
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.005640557501465082,
+      "learning_rate": 0.0001688,
+      "loss": 4.658547973632812,
+      "step": 120
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.005010648630559444,
+      "learning_rate": 0.0001634666666666667,
+      "loss": 4.665555191040039,
+      "step": 140
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.010227741673588753,
+      "learning_rate": 0.00015813333333333335,
+      "loss": 4.662850952148437,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.027864055708050728,
+      "learning_rate": 0.0001528,
+      "loss": 4.663832473754883,
+      "step": 180
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.005860226694494486,
+      "learning_rate": 0.00014746666666666666,
+      "loss": 4.6652687072753904,
+      "step": 200
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.004596560262143612,
+      "learning_rate": 0.00014213333333333334,
+      "loss": 4.672823333740235,
+      "step": 220
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.00873731728643179,
+      "learning_rate": 0.00013680000000000002,
+      "loss": 4.66284065246582,
+      "step": 240
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.01795760542154312,
+      "learning_rate": 0.00013146666666666667,
+      "loss": 4.663800430297852,
+      "step": 260
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.017787013202905655,
+      "learning_rate": 0.00012613333333333335,
+      "loss": 4.658986282348633,
+      "step": 280
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.037507686764001846,
+      "learning_rate": 0.0001208,
+      "loss": 4.65656852722168,
+      "step": 300
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.015351720154285431,
+      "learning_rate": 0.00011546666666666668,
+      "loss": 4.6595008850097654,
+      "step": 320
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.012529321946203709,
+      "learning_rate": 0.00011013333333333333,
+      "loss": 4.6615745544433596,
+      "step": 340
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.01247857604175806,
+      "learning_rate": 0.00010480000000000001,
+      "loss": 4.665129089355469,
+      "step": 360
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 0.005744063761085272,
+      "learning_rate": 9.946666666666668e-05,
+      "loss": 4.660833358764648,
+      "step": 380
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.05237531289458275,
+      "learning_rate": 9.413333333333334e-05,
+      "loss": 4.655843353271484,
+      "step": 400
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.0052072759717702866,
+      "learning_rate": 8.88e-05,
+      "loss": 4.667632293701172,
+      "step": 420
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 0.010262785479426384,
+      "learning_rate": 8.346666666666667e-05,
+      "loss": 4.662292861938477,
+      "step": 440
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 0.008771712891757488,
+      "learning_rate": 7.813333333333334e-05,
+      "loss": 4.664548110961914,
+      "step": 460
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.0393998809158802,
+      "learning_rate": 7.280000000000001e-05,
+      "loss": 4.665361404418945,
+      "step": 480
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.02198137529194355,
+      "learning_rate": 6.746666666666666e-05,
+      "loss": 4.664258193969727,
+      "step": 500
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 0.004228212870657444,
+      "learning_rate": 6.213333333333333e-05,
+      "loss": 4.658369827270508,
+      "step": 520
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.020782064646482468,
+      "learning_rate": 5.68e-05,
+      "loss": 4.6657970428466795,
+      "step": 540
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 0.016712293028831482,
+      "learning_rate": 5.146666666666667e-05,
+      "loss": 4.661626815795898,
+      "step": 560
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 0.01664014346897602,
+      "learning_rate": 4.6133333333333334e-05,
+      "loss": 4.665549850463867,
+      "step": 580
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.016694681718945503,
+      "learning_rate": 4.08e-05,
+      "loss": 4.6653087615966795,
+      "step": 600
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 0.029485318809747696,
+      "learning_rate": 3.546666666666667e-05,
+      "loss": 4.663780593872071,
+      "step": 620
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 0.006299078930169344,
+      "learning_rate": 3.0133333333333335e-05,
+      "loss": 4.659475326538086,
+      "step": 640
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.011340032331645489,
+      "learning_rate": 2.48e-05,
+      "loss": 4.660274505615234,
+      "step": 660
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 0.011485017836093903,
+      "learning_rate": 1.9466666666666668e-05,
+      "loss": 4.660123443603515,
+      "step": 680
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.009704177267849445,
+      "learning_rate": 1.4133333333333334e-05,
+      "loss": 4.66224479675293,
+      "step": 700
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.012306122109293938,
+      "learning_rate": 8.8e-06,
+      "loss": 4.660488891601562,
+      "step": 720
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 0.015551215969026089,
+      "learning_rate": 3.466666666666667e-06,
+      "loss": 4.66600456237793,
+      "step": 740
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.00716824549376e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94007b14b916aeb2fb2fd86c81ba83caa6e64d6db54e98bd315b252e8bbcead8
+size 5201

processor_config.json

@@ -1,6 +1,5 @@
 {
   "image_processor": {
-    "data_format": "channels_first",
     "do_convert_rgb": true,
     "do_normalize": true,
     "do_rescale": true,
@@ -10,13 +9,15 @@
       0.4578275,
       0.40821073
     ],
-    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_processor_type": "Qwen2VLImageProcessor",
     "image_std": [
       0.26862954,
       0.26130258,
       0.27577711
     ],
+    "max_pixels": 12845056,
     "merge_size": 2,
+    "min_pixels": 3136,
     "patch_size": 14,
     "resample": 3,
     "rescale_factor": 0.00392156862745098,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:312c03cb421e18f41c20c3e35f3302479a3a8f8b1f06779fd900326a0d32c22f
-size 11420534
+oid sha256:056908c2db70c250bf70521f1b449cd899ff35ec7b25cd694d38f8ce43383ce1
+size 11420632