diff --git a/README.md b/README.md index dba24454b7830fc2b11e00c4b03aac852ed19d74..37743e4b1a49721914a43bf03c9c9cc617cf1998 100644 --- a/README.md +++ b/README.md @@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. --> This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the b-brave/speech_disorders_voice dataset. It achieves the following results on the evaluation set: -- Loss: 0.3430 +- Loss: 0.3513 ## Model description @@ -40,29 +40,25 @@ More information needed The following hyperparameters were used during training: - learning_rate: 0.001 -- train_batch_size: 16 +- train_batch_size: 8 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 2 -- total_train_batch_size: 32 +- total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear -- lr_scheduler_warmup_steps: 50 -- num_epochs: 15 +- lr_scheduler_warmup_steps: 100 +- num_epochs: 7 - mixed_precision_training: Native AMP ### Training results -| Training Loss | Epoch | Step | Validation Loss | -|:-------------:|:-------:|:----:|:---------------:| -| 1.2968 | 1.7241 | 50 | 0.3434 | -| 0.2001 | 3.4483 | 100 | 0.3107 | -| 0.0827 | 5.1724 | 150 | 0.3031 | -| 0.0266 | 6.8966 | 200 | 0.3290 | -| 0.015 | 8.6207 | 250 | 0.3057 | -| 0.0083 | 10.3448 | 300 | 0.3294 | -| 0.0042 | 12.0690 | 350 | 0.3423 | -| 0.002 | 13.7931 | 400 | 0.3430 | +| Training Loss | Epoch | Step | Validation Loss | +|:-------------:|:------:|:----:|:---------------:| +| 1.0439 | 1.6529 | 100 | 0.3800 | +| 0.1939 | 3.3058 | 200 | 0.3690 | +| 0.07 | 4.9587 | 300 | 0.3301 | +| 0.0187 | 6.6116 | 400 | 0.3513 | ### Framework versions diff --git a/adapter_model.safetensors b/adapter_model.safetensors index 5c49907ace3aeb13e9443f121bb7bed24dfda489..c14d622a242937eb62a1a8ff616209a71ee4ceab 100644 --- a/adapter_model.safetensors +++ b/adapter_model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c3da27ee8a8a8ab39333e019e5a97ab357d2ea402c9d024977b22fdd3d65cd66 +oid sha256:7e836508ba6cc11e70f41aaed259e28d251cbfcb4c5a5b7978e2dc4d5f082d6d size 62969640 diff --git a/run-0/checkpoint-500/README.md b/run-0/checkpoint-500/README.md new file mode 100644 index 0000000000000000000000000000000000000000..4aa23bca34250d45e5f8a17f4e076efd91b742d4 --- /dev/null +++ b/run-0/checkpoint-500/README.md @@ -0,0 +1,202 @@ +--- +base_model: openai/whisper-large-v3 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.11.2.dev0 \ No newline at end of file diff --git a/run-0/checkpoint-500/adapter_config.json b/run-0/checkpoint-500/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a1573cdec967d02c99b5de3d3777e107a6eb09b2 --- /dev/null +++ b/run-0/checkpoint-500/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": { + "base_model_class": "WhisperForConditionalGeneration", + "parent_library": "transformers.models.whisper.modeling_whisper" + }, + "base_model_name_or_path": "openai/whisper-large-v3", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 64, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/run-0/checkpoint-500/adapter_model.safetensors b/run-0/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..371ea7271b63a2bf4ec029c5cc8e2459013e3c4a --- /dev/null +++ b/run-0/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24fec58d8c223f56fc9c03bf13d6251479405d0f322305deb87f71554401b646 +size 62969640 diff --git a/run-0/checkpoint-500/optimizer.pt b/run-0/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..63441842a6f0c6f8be6cd37002352806b3008edf --- /dev/null +++ b/run-0/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cbab46823b18f040948f161ef1b3f67a38c0aed0d36e6d8921022298dc07678 +size 126151570 diff --git a/run-0/checkpoint-500/preprocessor_config.json b/run-0/checkpoint-500/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f --- /dev/null +++ b/run-0/checkpoint-500/preprocessor_config.json @@ -0,0 +1,14 @@ +{ + "chunk_length": 30, + "feature_extractor_type": "WhisperFeatureExtractor", + "feature_size": 128, + "hop_length": 160, + "n_fft": 400, + "n_samples": 480000, + "nb_max_frames": 3000, + "padding_side": "right", + "padding_value": 0.0, + "processor_class": "WhisperProcessor", + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/run-0/checkpoint-500/rng_state.pth b/run-0/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..08ef8a6ef7f3cd33bf3d1d468ca19dee0969bc60 --- /dev/null +++ b/run-0/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610f67e3ef2a38bc4d059bf16b5476de440640d0cf679700dfa9d3a6aa152c59 +size 14244 diff --git a/run-0/checkpoint-500/scheduler.pt b/run-0/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f8a80e7045dfab94c55f677032f93accbd142eae --- /dev/null +++ b/run-0/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c3553622cafc378ebbc0729e6ab9e744631a120f1792c9359ebdf479fa218b0 +size 1064 diff --git a/run-0/checkpoint-500/trainer_state.json b/run-0/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..6752989001a1a45be59aabeff237ba82df076192 --- /dev/null +++ b/run-0/checkpoint-500/trainer_state.json @@ -0,0 +1,112 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.310344827586207, + "eval_steps": 100, + "global_step": 500, + "is_hyper_param_search": true, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.8620689655172413, + "grad_norm": 1.9135559797286987, + "learning_rate": 0.00012074932525523017, + "loss": 1.5845, + "step": 100 + }, + { + "epoch": 0.8620689655172413, + "eval_loss": 0.4098469614982605, + "eval_runtime": 21.3928, + "eval_samples_per_second": 4.815, + "eval_steps_per_second": 1.215, + "step": 100 + }, + { + "epoch": 1.7241379310344827, + "grad_norm": 1.4393121004104614, + "learning_rate": 9.569759802385461e-05, + "loss": 0.3018, + "step": 200 + }, + { + "epoch": 1.7241379310344827, + "eval_loss": 0.3046342730522156, + "eval_runtime": 21.0334, + "eval_samples_per_second": 4.897, + "eval_steps_per_second": 1.236, + "step": 200 + }, + { + "epoch": 2.586206896551724, + "grad_norm": 3.1296520233154297, + "learning_rate": 7.064587079247906e-05, + "loss": 0.1927, + "step": 300 + }, + { + "epoch": 2.586206896551724, + "eval_loss": 0.27630501985549927, + "eval_runtime": 21.0116, + "eval_samples_per_second": 4.902, + "eval_steps_per_second": 1.237, + "step": 300 + }, + { + "epoch": 3.4482758620689653, + "grad_norm": 1.2734673023223877, + "learning_rate": 4.559414356110351e-05, + "loss": 0.1304, + "step": 400 + }, + { + "epoch": 3.4482758620689653, + "eval_loss": 0.27304860949516296, + "eval_runtime": 20.891, + "eval_samples_per_second": 4.93, + "eval_steps_per_second": 1.245, + "step": 400 + }, + { + "epoch": 4.310344827586207, + "grad_norm": 1.0342594385147095, + "learning_rate": 2.0542416329727953e-05, + "loss": 0.1007, + "step": 500 + }, + { + "epoch": 4.310344827586207, + "eval_loss": 0.275942862033844, + "eval_runtime": 20.8484, + "eval_samples_per_second": 4.94, + "eval_steps_per_second": 1.247, + "step": 500 + } + ], + "logging_steps": 100, + "max_steps": 580, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "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": 1.370747847573504e+19, + "train_batch_size": 8, + "trial_name": null, + "trial_params": { + "learning_rate": 0.00013277415432629043, + "per_device_train_batch_size": 8, + "weight_decay": 0.0021291159421780548 + } +} diff --git a/run-0/checkpoint-500/training_args.bin b/run-0/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..a68fd252b75e8958d479596ba998ba0cc0f15026 --- /dev/null +++ b/run-0/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51dd06c8f8e2f8b00a912118364d06f67f1f5a631534d6cc03d23bfb515a9b22 +size 5240 diff --git a/run-1/checkpoint-500/README.md b/run-1/checkpoint-500/README.md new file mode 100644 index 0000000000000000000000000000000000000000..4aa23bca34250d45e5f8a17f4e076efd91b742d4 --- /dev/null +++ b/run-1/checkpoint-500/README.md @@ -0,0 +1,202 @@ +--- +base_model: openai/whisper-large-v3 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.11.2.dev0 \ No newline at end of file diff --git a/run-1/checkpoint-500/adapter_config.json b/run-1/checkpoint-500/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a1573cdec967d02c99b5de3d3777e107a6eb09b2 --- /dev/null +++ b/run-1/checkpoint-500/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": { + "base_model_class": "WhisperForConditionalGeneration", + "parent_library": "transformers.models.whisper.modeling_whisper" + }, + "base_model_name_or_path": "openai/whisper-large-v3", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 64, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/run-1/checkpoint-500/adapter_model.safetensors b/run-1/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..433d6da77853ad539eaf9cb786c02805d05df013 --- /dev/null +++ b/run-1/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:301ecb046fd37114d45719f410fb2d4707317c97f15b99227fbcf9de9c2ff2a4 +size 62969640 diff --git a/run-1/checkpoint-500/optimizer.pt b/run-1/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..aff659212807bfebe5e4cb17105ce04a26ab8049 --- /dev/null +++ b/run-1/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f7f0647119995372d44a8188e13a108e3ef5d9a523007d03b3ae8146f183d7d +size 126151570 diff --git a/run-1/checkpoint-500/preprocessor_config.json b/run-1/checkpoint-500/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f --- /dev/null +++ b/run-1/checkpoint-500/preprocessor_config.json @@ -0,0 +1,14 @@ +{ + "chunk_length": 30, + "feature_extractor_type": "WhisperFeatureExtractor", + "feature_size": 128, + "hop_length": 160, + "n_fft": 400, + "n_samples": 480000, + "nb_max_frames": 3000, + "padding_side": "right", + "padding_value": 0.0, + "processor_class": "WhisperProcessor", + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/run-1/checkpoint-500/rng_state.pth b/run-1/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..08ef8a6ef7f3cd33bf3d1d468ca19dee0969bc60 --- /dev/null +++ b/run-1/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610f67e3ef2a38bc4d059bf16b5476de440640d0cf679700dfa9d3a6aa152c59 +size 14244 diff --git a/run-1/checkpoint-500/scheduler.pt b/run-1/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..24484ba85a5764e428a3b7463fe3304ee0ff1410 --- /dev/null +++ b/run-1/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:697be74c5751a48948b5062099f3c0e459b59442bbc7d6efa5c14f9a1c356fc2 +size 1064 diff --git a/run-1/checkpoint-500/trainer_state.json b/run-1/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..8a2b31df292bad30f5999838949b24fb46f4b1e0 --- /dev/null +++ b/run-1/checkpoint-500/trainer_state.json @@ -0,0 +1,112 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.310344827586207, + "eval_steps": 100, + "global_step": 500, + "is_hyper_param_search": true, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.8620689655172413, + "grad_norm": 1.0919902324676514, + "learning_rate": 0.000511963042168714, + "loss": 1.1243, + "step": 100 + }, + { + "epoch": 0.8620689655172413, + "eval_loss": 0.3352593779563904, + "eval_runtime": 21.0273, + "eval_samples_per_second": 4.898, + "eval_steps_per_second": 1.236, + "step": 100 + }, + { + "epoch": 1.7241379310344827, + "grad_norm": 0.7907235622406006, + "learning_rate": 0.0004055258192646154, + "loss": 0.2577, + "step": 200 + }, + { + "epoch": 1.7241379310344827, + "eval_loss": 0.2866515517234802, + "eval_runtime": 20.7228, + "eval_samples_per_second": 4.97, + "eval_steps_per_second": 1.255, + "step": 200 + }, + { + "epoch": 2.586206896551724, + "grad_norm": 0.10258855670690536, + "learning_rate": 0.0002990885963605169, + "loss": 0.1337, + "step": 300 + }, + { + "epoch": 2.586206896551724, + "eval_loss": 0.2725263833999634, + "eval_runtime": 20.8639, + "eval_samples_per_second": 4.937, + "eval_steps_per_second": 1.246, + "step": 300 + }, + { + "epoch": 3.4482758620689653, + "grad_norm": 0.2434462606906891, + "learning_rate": 0.00019265137345641833, + "loss": 0.0734, + "step": 400 + }, + { + "epoch": 3.4482758620689653, + "eval_loss": 0.27984029054641724, + "eval_runtime": 20.7967, + "eval_samples_per_second": 4.953, + "eval_steps_per_second": 1.25, + "step": 400 + }, + { + "epoch": 4.310344827586207, + "grad_norm": 0.4092065393924713, + "learning_rate": 8.621415055231981e-05, + "loss": 0.0422, + "step": 500 + }, + { + "epoch": 4.310344827586207, + "eval_loss": 0.2786606252193451, + "eval_runtime": 20.6352, + "eval_samples_per_second": 4.991, + "eval_steps_per_second": 1.26, + "step": 500 + } + ], + "logging_steps": 100, + "max_steps": 580, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "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": 1.370747847573504e+19, + "train_batch_size": 8, + "trial_name": null, + "trial_params": { + "learning_rate": 0.0005641172813917223, + "per_device_train_batch_size": 8, + "weight_decay": 0.0006732813397449721 + } +} diff --git a/run-1/checkpoint-500/training_args.bin b/run-1/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..5a1b0eb614b6d8311b4171ff8c3befb7a59796ba --- /dev/null +++ b/run-1/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586b5e4b6f0b63d98f1fb72f63d9cfa27c3f5271d96663ef93dac3b215590cac +size 5240 diff --git a/run-11/checkpoint-500/README.md b/run-11/checkpoint-500/README.md new file mode 100644 index 0000000000000000000000000000000000000000..4aa23bca34250d45e5f8a17f4e076efd91b742d4 --- /dev/null +++ b/run-11/checkpoint-500/README.md @@ -0,0 +1,202 @@ +--- +base_model: openai/whisper-large-v3 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.11.2.dev0 \ No newline at end of file diff --git a/run-11/checkpoint-500/adapter_config.json b/run-11/checkpoint-500/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e8156acf5e2192154feaf3ebd8e6c850f48a7256 --- /dev/null +++ b/run-11/checkpoint-500/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": { + "base_model_class": "WhisperForConditionalGeneration", + "parent_library": "transformers.models.whisper.modeling_whisper" + }, + "base_model_name_or_path": "openai/whisper-large-v3", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 64, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj" + ], + "task_type": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/run-11/checkpoint-500/adapter_model.safetensors b/run-11/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..03b7eec858e44de2f013182f67d0cf96158b5a2e --- /dev/null +++ b/run-11/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc1578b5c1ed9b672936f479c98346886397fe5bb539e468cc79bac92327f5b3 +size 62969640 diff --git a/run-11/checkpoint-500/optimizer.pt b/run-11/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6e026e73999a9b1ea867a75a0079f48cf7957b0 --- /dev/null +++ b/run-11/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3e3151830d547370b456265c4be2a67e395b2100069af1aa9fb4418c89be29e +size 126151570 diff --git a/run-11/checkpoint-500/preprocessor_config.json b/run-11/checkpoint-500/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f --- /dev/null +++ b/run-11/checkpoint-500/preprocessor_config.json @@ -0,0 +1,14 @@ +{ + "chunk_length": 30, + "feature_extractor_type": "WhisperFeatureExtractor", + "feature_size": 128, + "hop_length": 160, + "n_fft": 400, + "n_samples": 480000, + "nb_max_frames": 3000, + "padding_side": "right", + "padding_value": 0.0, + "processor_class": "WhisperProcessor", + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/run-11/checkpoint-500/rng_state.pth b/run-11/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..384dac93125873ec4b04a2c7bbb54872e0bf8257 --- /dev/null +++ b/run-11/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e8ee737576623fd1565b4ad626caaadf9a95e0f8cbaa53304cbd8316b784fc7 +size 14244 diff --git a/run-11/checkpoint-500/scheduler.pt b/run-11/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..493ee9540081c43fd399e63bfa586318cd29a956 --- /dev/null +++ b/run-11/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a9ac6f5a41063d009620aaf578bb32960c6c36ab869fa1af8b00a00116fd422 +size 1064 diff --git a/run-11/checkpoint-500/trainer_state.json b/run-11/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..37988490cb6353150e0fa3493e405238018571f8 --- /dev/null +++ b/run-11/checkpoint-500/trainer_state.json @@ -0,0 +1,187 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.1551724137931036, + "eval_steps": 50, + "global_step": 500, + "is_hyper_param_search": true, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.21551724137931033, + "grad_norm": 1.7124779224395752, + "learning_rate": 0.0004653203635082234, + "loss": 1.8899, + "step": 50 + }, + { + "epoch": 0.21551724137931033, + "eval_loss": 0.7426255941390991, + "eval_runtime": 21.193, + "eval_samples_per_second": 4.86, + "eval_steps_per_second": 1.227, + "step": 50 + }, + { + "epoch": 0.43103448275862066, + "grad_norm": 0.7779552936553955, + "learning_rate": 0.00044027121018106054, + "loss": 0.5956, + "step": 100 + }, + { + "epoch": 0.43103448275862066, + "eval_loss": 0.4363415837287903, + "eval_runtime": 21.3828, + "eval_samples_per_second": 4.817, + "eval_steps_per_second": 1.216, + "step": 100 + }, + { + "epoch": 0.646551724137931, + "grad_norm": 1.916613221168518, + "learning_rate": 0.0004035206918020071, + "loss": 0.3791, + "step": 150 + }, + { + "epoch": 0.646551724137931, + "eval_loss": 0.4209233522415161, + "eval_runtime": 21.3351, + "eval_samples_per_second": 4.828, + "eval_steps_per_second": 1.219, + "step": 150 + }, + { + "epoch": 0.8620689655172413, + "grad_norm": 1.6026177406311035, + "learning_rate": 0.0003667701734229536, + "loss": 0.3729, + "step": 200 + }, + { + "epoch": 0.8620689655172413, + "eval_loss": 0.41846963763237, + "eval_runtime": 21.4128, + "eval_samples_per_second": 4.81, + "eval_steps_per_second": 1.214, + "step": 200 + }, + { + "epoch": 1.0775862068965518, + "grad_norm": 1.0747971534729004, + "learning_rate": 0.00033001965504390017, + "loss": 0.2689, + "step": 250 + }, + { + "epoch": 1.0775862068965518, + "eval_loss": 0.3982403576374054, + "eval_runtime": 21.299, + "eval_samples_per_second": 4.836, + "eval_steps_per_second": 1.221, + "step": 250 + }, + { + "epoch": 1.293103448275862, + "grad_norm": 0.07190462946891785, + "learning_rate": 0.0002932691366648467, + "loss": 0.2102, + "step": 300 + }, + { + "epoch": 1.293103448275862, + "eval_loss": 0.3758964240550995, + "eval_runtime": 21.465, + "eval_samples_per_second": 4.799, + "eval_steps_per_second": 1.211, + "step": 300 + }, + { + "epoch": 1.5086206896551724, + "grad_norm": 1.1930207014083862, + "learning_rate": 0.00025651861828579324, + "loss": 0.2177, + "step": 350 + }, + { + "epoch": 1.5086206896551724, + "eval_loss": 0.3926349878311157, + "eval_runtime": 21.5556, + "eval_samples_per_second": 4.778, + "eval_steps_per_second": 1.206, + "step": 350 + }, + { + "epoch": 1.7241379310344827, + "grad_norm": 2.48095703125, + "learning_rate": 0.00021976809990673974, + "loss": 0.1461, + "step": 400 + }, + { + "epoch": 1.7241379310344827, + "eval_loss": 0.3509480059146881, + "eval_runtime": 21.4602, + "eval_samples_per_second": 4.8, + "eval_steps_per_second": 1.212, + "step": 400 + }, + { + "epoch": 1.9396551724137931, + "grad_norm": 0.2920898497104645, + "learning_rate": 0.00018301758152768628, + "loss": 0.116, + "step": 450 + }, + { + "epoch": 1.9396551724137931, + "eval_loss": 0.34957313537597656, + "eval_runtime": 21.5134, + "eval_samples_per_second": 4.788, + "eval_steps_per_second": 1.209, + "step": 450 + }, + { + "epoch": 2.1551724137931036, + "grad_norm": 1.2332462072372437, + "learning_rate": 0.0001462670631486328, + "loss": 0.1267, + "step": 500 + }, + { + "epoch": 2.1551724137931036, + "eval_loss": 0.347840815782547, + "eval_runtime": 21.5522, + "eval_samples_per_second": 4.779, + "eval_steps_per_second": 1.206, + "step": 500 + } + ], + "logging_steps": 50, + "max_steps": 696, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 6.85373923786752e+18, + "train_batch_size": 4, + "trial_name": null, + "trial_params": { + "learning_rate": 0.0004748166974573708, + "per_device_train_batch_size": 4, + "weight_decay": 1.1048142278460074e-05 + } +} diff --git a/run-11/checkpoint-500/training_args.bin b/run-11/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..494d20d1aebb2c4da2f3c438a69e7c0a6471f38a --- /dev/null +++ b/run-11/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c7daea9ee3a72c1f0ccde9bdbb90b3fc2a862ce798a504a18fb3cd0854f2461 +size 5240 diff --git a/run-14/checkpoint-500/README.md b/run-14/checkpoint-500/README.md new file mode 100644 index 0000000000000000000000000000000000000000..4aa23bca34250d45e5f8a17f4e076efd91b742d4 --- /dev/null +++ b/run-14/checkpoint-500/README.md @@ -0,0 +1,202 @@ +--- +base_model: openai/whisper-large-v3 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.11.2.dev0 \ No newline at end of file diff --git a/run-14/checkpoint-500/adapter_config.json b/run-14/checkpoint-500/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e8156acf5e2192154feaf3ebd8e6c850f48a7256 --- /dev/null +++ b/run-14/checkpoint-500/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": { + "base_model_class": "WhisperForConditionalGeneration", + "parent_library": "transformers.models.whisper.modeling_whisper" + }, + "base_model_name_or_path": "openai/whisper-large-v3", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 64, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj" + ], + "task_type": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/run-14/checkpoint-500/adapter_model.safetensors b/run-14/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..560658201d70bb1ee286081d131d2758899f8550 --- /dev/null +++ b/run-14/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65753749f9dec960bf0e91bb6d44e92354ee377b13564af56cf911c6ed0451ae +size 62969640 diff --git a/run-14/checkpoint-500/optimizer.pt b/run-14/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..51c79be46211e675411a2a1593d17ed680fc92ad --- /dev/null +++ b/run-14/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205be8da36802a453b8ccc171f51cbcb8d46c31f700c2dee5c6a1f1d05b86a66 +size 126151570 diff --git a/run-14/checkpoint-500/preprocessor_config.json b/run-14/checkpoint-500/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f --- /dev/null +++ b/run-14/checkpoint-500/preprocessor_config.json @@ -0,0 +1,14 @@ +{ + "chunk_length": 30, + "feature_extractor_type": "WhisperFeatureExtractor", + "feature_size": 128, + "hop_length": 160, + "n_fft": 400, + "n_samples": 480000, + "nb_max_frames": 3000, + "padding_side": "right", + "padding_value": 0.0, + "processor_class": "WhisperProcessor", + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/run-14/checkpoint-500/rng_state.pth b/run-14/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..384dac93125873ec4b04a2c7bbb54872e0bf8257 --- /dev/null +++ b/run-14/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e8ee737576623fd1565b4ad626caaadf9a95e0f8cbaa53304cbd8316b784fc7 +size 14244 diff --git a/run-14/checkpoint-500/scheduler.pt b/run-14/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b21b14bf33e6b3f4a69f5164bbb5ce6614328d2 --- /dev/null +++ b/run-14/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d125eaa094e272a98c53c93763667ee1b063b8df0becf7b73d774466b90f5ca8 +size 1064 diff --git a/run-14/checkpoint-500/trainer_state.json b/run-14/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..ff38414f74641dea7731d64b6e53e4eab330c813 --- /dev/null +++ b/run-14/checkpoint-500/trainer_state.json @@ -0,0 +1,187 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.1551724137931036, + "eval_steps": 50, + "global_step": 500, + "is_hyper_param_search": true, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.21551724137931033, + "grad_norm": 1.521485686302185, + "learning_rate": 0.00027335775706699585, + "loss": 2.1579, + "step": 50 + }, + { + "epoch": 0.21551724137931033, + "eval_loss": 0.8509826064109802, + "eval_runtime": 21.3286, + "eval_samples_per_second": 4.829, + "eval_steps_per_second": 1.219, + "step": 50 + }, + { + "epoch": 0.43103448275862066, + "grad_norm": 1.5416312217712402, + "learning_rate": 0.0002590741363495885, + "loss": 0.9505, + "step": 100 + }, + { + "epoch": 0.43103448275862066, + "eval_loss": 0.45885732769966125, + "eval_runtime": 21.5445, + "eval_samples_per_second": 4.781, + "eval_steps_per_second": 1.207, + "step": 100 + }, + { + "epoch": 0.646551724137931, + "grad_norm": 1.1615911722183228, + "learning_rate": 0.0002374846249871228, + "loss": 0.3657, + "step": 150 + }, + { + "epoch": 0.646551724137931, + "eval_loss": 0.4113822281360626, + "eval_runtime": 21.6048, + "eval_samples_per_second": 4.767, + "eval_steps_per_second": 1.203, + "step": 150 + }, + { + "epoch": 0.8620689655172413, + "grad_norm": 1.142115592956543, + "learning_rate": 0.00021589511362465712, + "loss": 0.3628, + "step": 200 + }, + { + "epoch": 0.8620689655172413, + "eval_loss": 0.41732752323150635, + "eval_runtime": 21.7592, + "eval_samples_per_second": 4.734, + "eval_steps_per_second": 1.195, + "step": 200 + }, + { + "epoch": 1.0775862068965518, + "grad_norm": 1.0338547229766846, + "learning_rate": 0.0001943056022621914, + "loss": 0.2827, + "step": 250 + }, + { + "epoch": 1.0775862068965518, + "eval_loss": 0.36462482810020447, + "eval_runtime": 21.5612, + "eval_samples_per_second": 4.777, + "eval_steps_per_second": 1.206, + "step": 250 + }, + { + "epoch": 1.293103448275862, + "grad_norm": 0.10536845773458481, + "learning_rate": 0.0001727160908997257, + "loss": 0.2163, + "step": 300 + }, + { + "epoch": 1.293103448275862, + "eval_loss": 0.37129101157188416, + "eval_runtime": 21.6513, + "eval_samples_per_second": 4.757, + "eval_steps_per_second": 1.201, + "step": 300 + }, + { + "epoch": 1.5086206896551724, + "grad_norm": 1.3671547174453735, + "learning_rate": 0.00015112657953726, + "loss": 0.2207, + "step": 350 + }, + { + "epoch": 1.5086206896551724, + "eval_loss": 0.3586764633655548, + "eval_runtime": 21.5998, + "eval_samples_per_second": 4.769, + "eval_steps_per_second": 1.204, + "step": 350 + }, + { + "epoch": 1.7241379310344827, + "grad_norm": 1.0158982276916504, + "learning_rate": 0.00012953706817479425, + "loss": 0.1471, + "step": 400 + }, + { + "epoch": 1.7241379310344827, + "eval_loss": 0.3449494242668152, + "eval_runtime": 21.587, + "eval_samples_per_second": 4.771, + "eval_steps_per_second": 1.204, + "step": 400 + }, + { + "epoch": 1.9396551724137931, + "grad_norm": 1.3887505531311035, + "learning_rate": 0.00010794755681232856, + "loss": 0.127, + "step": 450 + }, + { + "epoch": 1.9396551724137931, + "eval_loss": 0.35482650995254517, + "eval_runtime": 21.5569, + "eval_samples_per_second": 4.778, + "eval_steps_per_second": 1.206, + "step": 450 + }, + { + "epoch": 2.1551724137931036, + "grad_norm": 1.2020519971847534, + "learning_rate": 8.635804544986286e-05, + "loss": 0.1393, + "step": 500 + }, + { + "epoch": 2.1551724137931036, + "eval_loss": 0.35960131883621216, + "eval_runtime": 21.525, + "eval_samples_per_second": 4.785, + "eval_steps_per_second": 1.208, + "step": 500 + } + ], + "logging_steps": 50, + "max_steps": 696, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 6.85373923786752e+18, + "train_batch_size": 4, + "trial_name": null, + "trial_params": { + "learning_rate": 0.000278936486803057, + "per_device_train_batch_size": 4, + "weight_decay": 0.00018977840930045 + } +} diff --git a/run-14/checkpoint-500/training_args.bin b/run-14/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..54414d934e7806c53e86c80160d39ef5a9c48ef4 --- /dev/null +++ b/run-14/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ffb4ecb13597b62de8ca87970646438e1a5e0711c023ad7845f440752d9a66 +size 5240 diff --git a/run-2/checkpoint-1000/README.md b/run-2/checkpoint-1000/README.md new file mode 100644 index 0000000000000000000000000000000000000000..4aa23bca34250d45e5f8a17f4e076efd91b742d4 --- /dev/null +++ b/run-2/checkpoint-1000/README.md @@ -0,0 +1,202 @@ +--- +base_model: openai/whisper-large-v3 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.11.2.dev0 \ No newline at end of file diff --git a/run-2/checkpoint-1000/adapter_config.json b/run-2/checkpoint-1000/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a1573cdec967d02c99b5de3d3777e107a6eb09b2 --- /dev/null +++ b/run-2/checkpoint-1000/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": { + "base_model_class": "WhisperForConditionalGeneration", + "parent_library": "transformers.models.whisper.modeling_whisper" + }, + "base_model_name_or_path": "openai/whisper-large-v3", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 64, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/run-2/checkpoint-1000/adapter_model.safetensors b/run-2/checkpoint-1000/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..014150e78e20e4010851d809712a06722b45423e --- /dev/null +++ b/run-2/checkpoint-1000/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb7579f8b5f03d1ad5d26d88649c690729bd42a41c96b79e0709277ff6fd0447 +size 62969640 diff --git a/run-2/checkpoint-1000/optimizer.pt b/run-2/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ea91712a59b9b9d45899bf87c17475d1a122a7a --- /dev/null +++ b/run-2/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21b1730bf12097dfa3d8ef0399635edc289a66c56dd4334f7115cc044e1bee76 +size 126151570 diff --git a/run-2/checkpoint-1000/preprocessor_config.json b/run-2/checkpoint-1000/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f --- /dev/null +++ b/run-2/checkpoint-1000/preprocessor_config.json @@ -0,0 +1,14 @@ +{ + "chunk_length": 30, + "feature_extractor_type": "WhisperFeatureExtractor", + "feature_size": 128, + "hop_length": 160, + "n_fft": 400, + "n_samples": 480000, + "nb_max_frames": 3000, + "padding_side": "right", + "padding_value": 0.0, + "processor_class": "WhisperProcessor", + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/run-2/checkpoint-1000/rng_state.pth b/run-2/checkpoint-1000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..a83021f40fcba6b6f9e3db4d2752fd910ffd9ca4 --- /dev/null +++ b/run-2/checkpoint-1000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ea3c5a2f00688c8f2d21b62d2c759f3e10550fb6cd1104d2317252f3df05792 +size 14244 diff --git a/run-2/checkpoint-1000/scheduler.pt b/run-2/checkpoint-1000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..104f1570f0c203a093b1073b2c13b8164b9e5079 --- /dev/null +++ b/run-2/checkpoint-1000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a75ba99085d46a7ab302dd0b2fa0081115e6f095fdc524727c48f4ce2f7bbb +size 1064 diff --git a/run-2/checkpoint-1000/trainer_state.json b/run-2/checkpoint-1000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..df64824b7e834454808678aa3a9753b23362c0a0 --- /dev/null +++ b/run-2/checkpoint-1000/trainer_state.json @@ -0,0 +1,187 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.310344827586207, + "eval_steps": 100, + "global_step": 1000, + "is_hyper_param_search": true, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.43103448275862066, + "grad_norm": 0.2723050117492676, + "learning_rate": 0.008792554642694678, + "loss": 7.2774, + "step": 100 + }, + { + "epoch": 0.43103448275862066, + "eval_loss": 6.054980754852295, + "eval_runtime": 20.3527, + "eval_samples_per_second": 5.061, + "eval_steps_per_second": 1.277, + "step": 100 + }, + { + "epoch": 0.8620689655172413, + "grad_norm": 0.18630041182041168, + "learning_rate": 0.007966186725148186, + "loss": 5.427, + "step": 200 + }, + { + "epoch": 0.8620689655172413, + "eval_loss": 4.836428642272949, + "eval_runtime": 20.9898, + "eval_samples_per_second": 4.907, + "eval_steps_per_second": 1.239, + "step": 200 + }, + { + "epoch": 1.293103448275862, + "grad_norm": 0.2724410593509674, + "learning_rate": 0.007139818807601695, + "loss": 4.768, + "step": 300 + }, + { + "epoch": 1.293103448275862, + "eval_loss": 4.6033172607421875, + "eval_runtime": 21.1004, + "eval_samples_per_second": 4.881, + "eval_steps_per_second": 1.232, + "step": 300 + }, + { + "epoch": 1.7241379310344827, + "grad_norm": 0.14782890677452087, + "learning_rate": 0.006313450890055201, + "loss": 4.407, + "step": 400 + }, + { + "epoch": 1.7241379310344827, + "eval_loss": 4.464559555053711, + "eval_runtime": 21.3779, + "eval_samples_per_second": 4.818, + "eval_steps_per_second": 1.216, + "step": 400 + }, + { + "epoch": 2.1551724137931036, + "grad_norm": 0.14380355179309845, + "learning_rate": 0.005487082972508709, + "loss": 4.4103, + "step": 500 + }, + { + "epoch": 2.1551724137931036, + "eval_loss": 4.4448137283325195, + "eval_runtime": 21.3614, + "eval_samples_per_second": 4.822, + "eval_steps_per_second": 1.217, + "step": 500 + }, + { + "epoch": 2.586206896551724, + "grad_norm": 0.853726863861084, + "learning_rate": 0.004660715054962217, + "loss": 4.4563, + "step": 600 + }, + { + "epoch": 2.586206896551724, + "eval_loss": 4.372040748596191, + "eval_runtime": 21.4365, + "eval_samples_per_second": 4.805, + "eval_steps_per_second": 1.213, + "step": 600 + }, + { + "epoch": 3.0172413793103448, + "grad_norm": 29.915081024169922, + "learning_rate": 0.0038343471374157247, + "loss": 4.3135, + "step": 700 + }, + { + "epoch": 3.0172413793103448, + "eval_loss": 4.337521553039551, + "eval_runtime": 21.4878, + "eval_samples_per_second": 4.793, + "eval_steps_per_second": 1.21, + "step": 700 + }, + { + "epoch": 3.4482758620689653, + "grad_norm": 0.6140814423561096, + "learning_rate": 0.003007979219869232, + "loss": 4.1072, + "step": 800 + }, + { + "epoch": 3.4482758620689653, + "eval_loss": 4.2883219718933105, + "eval_runtime": 21.4591, + "eval_samples_per_second": 4.8, + "eval_steps_per_second": 1.212, + "step": 800 + }, + { + "epoch": 3.8793103448275863, + "grad_norm": 0.20803356170654297, + "learning_rate": 0.0021816113023227397, + "loss": 4.3397, + "step": 900 + }, + { + "epoch": 3.8793103448275863, + "eval_loss": 4.263036727905273, + "eval_runtime": 21.4871, + "eval_samples_per_second": 4.794, + "eval_steps_per_second": 1.21, + "step": 900 + }, + { + "epoch": 4.310344827586207, + "grad_norm": 0.19872911274433136, + "learning_rate": 0.0013552433847762474, + "loss": 3.9199, + "step": 1000 + }, + { + "epoch": 4.310344827586207, + "eval_loss": 4.16709566116333, + "eval_runtime": 21.4824, + "eval_samples_per_second": 4.795, + "eval_steps_per_second": 1.21, + "step": 1000 + } + ], + "logging_steps": 100, + "max_steps": 1160, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "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": 1.370747847573504e+19, + "train_batch_size": 4, + "trial_name": null, + "trial_params": { + "learning_rate": 0.009172683884766065, + "per_device_train_batch_size": 4, + "weight_decay": 0.0003005652075108987 + } +} diff --git a/run-2/checkpoint-1000/training_args.bin b/run-2/checkpoint-1000/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..d60873a627d3b6bfe3eff2d9fc88a1b8510335bc --- /dev/null +++ b/run-2/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f85248d48b74fd5496584a4c64687155d035a3e8ea717f3345e58d241e2dd13 +size 5240 diff --git a/run-2/checkpoint-500/README.md b/run-2/checkpoint-500/README.md new file mode 100644 index 0000000000000000000000000000000000000000..4aa23bca34250d45e5f8a17f4e076efd91b742d4 --- /dev/null +++ b/run-2/checkpoint-500/README.md @@ -0,0 +1,202 @@ +--- +base_model: openai/whisper-large-v3 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.11.2.dev0 \ No newline at end of file diff --git a/run-2/checkpoint-500/adapter_config.json b/run-2/checkpoint-500/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e8156acf5e2192154feaf3ebd8e6c850f48a7256 --- /dev/null +++ b/run-2/checkpoint-500/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": { + "base_model_class": "WhisperForConditionalGeneration", + "parent_library": "transformers.models.whisper.modeling_whisper" + }, + "base_model_name_or_path": "openai/whisper-large-v3", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 64, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "q_proj", + "v_proj" + ], + "task_type": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/run-2/checkpoint-500/adapter_model.safetensors b/run-2/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3419f6c053212d28370de278ca6c79f0f7cd022a --- /dev/null +++ b/run-2/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6c0ff3e26a63daef37b7245cfc1182cc3a7acc128bb743fa4c3c349b9179b6a +size 62969640 diff --git a/run-2/checkpoint-500/optimizer.pt b/run-2/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b9f9d335ccc3b11fa6a868c51976a7ec080b2c5 --- /dev/null +++ b/run-2/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c56fe310d850a19aa1c58462b7d9941e1a6467d221f7896357c8a8e65eec96 +size 126151570 diff --git a/run-2/checkpoint-500/preprocessor_config.json b/run-2/checkpoint-500/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f --- /dev/null +++ b/run-2/checkpoint-500/preprocessor_config.json @@ -0,0 +1,14 @@ +{ + "chunk_length": 30, + "feature_extractor_type": "WhisperFeatureExtractor", + "feature_size": 128, + "hop_length": 160, + "n_fft": 400, + "n_samples": 480000, + "nb_max_frames": 3000, + "padding_side": "right", + "padding_value": 0.0, + "processor_class": "WhisperProcessor", + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/run-2/checkpoint-500/rng_state.pth b/run-2/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..384dac93125873ec4b04a2c7bbb54872e0bf8257 --- /dev/null +++ b/run-2/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e8ee737576623fd1565b4ad626caaadf9a95e0f8cbaa53304cbd8316b784fc7 +size 14244 diff --git a/run-2/checkpoint-500/scheduler.pt b/run-2/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a6bd28945aa5aa33abfc71a11a8c5db2b563eafd --- /dev/null +++ b/run-2/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb2814994f83c52adee84a16a55afe3de5aea01775d6943890a3a2cf353f1822 +size 1064 diff --git a/run-2/checkpoint-500/trainer_state.json b/run-2/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..82876b4137874d0879a3b9f3a55283f7522bbda3 --- /dev/null +++ b/run-2/checkpoint-500/trainer_state.json @@ -0,0 +1,187 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.1551724137931036, + "eval_steps": 50, + "global_step": 500, + "is_hyper_param_search": true, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.21551724137931033, + "grad_norm": 1.3638863563537598, + "learning_rate": 7.105567136563152e-05, + "loss": 2.688, + "step": 50 + }, + { + "epoch": 0.21551724137931033, + "eval_loss": 2.2933294773101807, + "eval_runtime": 21.2956, + "eval_samples_per_second": 4.837, + "eval_steps_per_second": 1.221, + "step": 50 + }, + { + "epoch": 0.43103448275862066, + "grad_norm": 3.059149742126465, + "learning_rate": 6.555600639925138e-05, + "loss": 1.4119, + "step": 100 + }, + { + "epoch": 0.43103448275862066, + "eval_loss": 0.9544830918312073, + "eval_runtime": 21.1878, + "eval_samples_per_second": 4.861, + "eval_steps_per_second": 1.227, + "step": 100 + }, + { + "epoch": 0.646551724137931, + "grad_norm": 3.0382325649261475, + "learning_rate": 6.005634143287122e-05, + "loss": 0.6159, + "step": 150 + }, + { + "epoch": 0.646551724137931, + "eval_loss": 0.48086249828338623, + "eval_runtime": 21.6274, + "eval_samples_per_second": 4.762, + "eval_steps_per_second": 1.202, + "step": 150 + }, + { + "epoch": 0.8620689655172413, + "grad_norm": 1.0172477960586548, + "learning_rate": 5.488665636447389e-05, + "loss": 0.4644, + "step": 200 + }, + { + "epoch": 0.8620689655172413, + "eval_loss": 0.42798206210136414, + "eval_runtime": 21.1558, + "eval_samples_per_second": 4.869, + "eval_steps_per_second": 1.229, + "step": 200 + }, + { + "epoch": 1.0775862068965518, + "grad_norm": 1.890181541442871, + "learning_rate": 4.938699139809374e-05, + "loss": 0.3564, + "step": 250 + }, + { + "epoch": 1.0775862068965518, + "eval_loss": 0.39772284030914307, + "eval_runtime": 21.361, + "eval_samples_per_second": 4.822, + "eval_steps_per_second": 1.217, + "step": 250 + }, + { + "epoch": 1.293103448275862, + "grad_norm": 1.2151236534118652, + "learning_rate": 4.388732643171359e-05, + "loss": 0.2957, + "step": 300 + }, + { + "epoch": 1.293103448275862, + "eval_loss": 0.39809828996658325, + "eval_runtime": 21.2608, + "eval_samples_per_second": 4.845, + "eval_steps_per_second": 1.223, + "step": 300 + }, + { + "epoch": 1.5086206896551724, + "grad_norm": 2.4856667518615723, + "learning_rate": 3.838766146533344e-05, + "loss": 0.3311, + "step": 350 + }, + { + "epoch": 1.5086206896551724, + "eval_loss": 0.38849785923957825, + "eval_runtime": 21.2393, + "eval_samples_per_second": 4.849, + "eval_steps_per_second": 1.224, + "step": 350 + }, + { + "epoch": 1.7241379310344827, + "grad_norm": 1.9023874998092651, + "learning_rate": 3.288799649895329e-05, + "loss": 0.2135, + "step": 400 + }, + { + "epoch": 1.7241379310344827, + "eval_loss": 0.3564490079879761, + "eval_runtime": 21.2326, + "eval_samples_per_second": 4.851, + "eval_steps_per_second": 1.225, + "step": 400 + }, + { + "epoch": 1.9396551724137931, + "grad_norm": 1.9959230422973633, + "learning_rate": 2.7388331532573143e-05, + "loss": 0.1971, + "step": 450 + }, + { + "epoch": 1.9396551724137931, + "eval_loss": 0.3635966181755066, + "eval_runtime": 21.3595, + "eval_samples_per_second": 4.822, + "eval_steps_per_second": 1.217, + "step": 450 + }, + { + "epoch": 2.1551724137931036, + "grad_norm": 3.10198712348938, + "learning_rate": 2.1888666566192993e-05, + "loss": 0.2504, + "step": 500 + }, + { + "epoch": 2.1551724137931036, + "eval_loss": 0.3609098196029663, + "eval_runtime": 21.2604, + "eval_samples_per_second": 4.845, + "eval_steps_per_second": 1.223, + "step": 500 + } + ], + "logging_steps": 50, + "max_steps": 696, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 6.85373923786752e+18, + "train_batch_size": 4, + "trial_name": null, + "trial_params": { + "learning_rate": 7.105567136563152e-05, + "per_device_train_batch_size": 4, + "weight_decay": 2.982120275433049e-05 + } +} diff --git a/run-2/checkpoint-500/training_args.bin b/run-2/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..e4952faf1499a471f15548ca130c903124b354af --- /dev/null +++ b/run-2/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98d8f1d5c1e39024709945638d926acf35c94d55c197beae8d0e8671f077bb08 +size 5240 diff --git a/run-3/checkpoint-1000/README.md b/run-3/checkpoint-1000/README.md new file mode 100644 index 0000000000000000000000000000000000000000..4aa23bca34250d45e5f8a17f4e076efd91b742d4 --- /dev/null +++ b/run-3/checkpoint-1000/README.md @@ -0,0 +1,202 @@ +--- +base_model: openai/whisper-large-v3 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.11.2.dev0 \ No newline at end of file diff --git a/run-3/checkpoint-1000/adapter_config.json b/run-3/checkpoint-1000/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a1573cdec967d02c99b5de3d3777e107a6eb09b2 --- /dev/null +++ b/run-3/checkpoint-1000/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": { + "base_model_class": "WhisperForConditionalGeneration", + "parent_library": "transformers.models.whisper.modeling_whisper" + }, + "base_model_name_or_path": "openai/whisper-large-v3", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 64, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/run-3/checkpoint-1000/adapter_model.safetensors b/run-3/checkpoint-1000/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..145851f8f7cc9048ede8f5f2095ec75da4ac8e78 --- /dev/null +++ b/run-3/checkpoint-1000/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09710b0c16fb1ddc46687c780ef8f29e1f4fb96b9f8fe5256b2e46d20b6a9787 +size 62969640 diff --git a/run-3/checkpoint-1000/optimizer.pt b/run-3/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4954074ad8bd58b151ec6f4a9fa7d071183b0a3 --- /dev/null +++ b/run-3/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1629b7f65e98eaeef8473fb3123d4c6442c045797f4aa13f5c6181d6e6b1ffc3 +size 126151570 diff --git a/run-3/checkpoint-1000/preprocessor_config.json b/run-3/checkpoint-1000/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f --- /dev/null +++ b/run-3/checkpoint-1000/preprocessor_config.json @@ -0,0 +1,14 @@ +{ + "chunk_length": 30, + "feature_extractor_type": "WhisperFeatureExtractor", + "feature_size": 128, + "hop_length": 160, + "n_fft": 400, + "n_samples": 480000, + "nb_max_frames": 3000, + "padding_side": "right", + "padding_value": 0.0, + "processor_class": "WhisperProcessor", + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/run-3/checkpoint-1000/rng_state.pth b/run-3/checkpoint-1000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..a83021f40fcba6b6f9e3db4d2752fd910ffd9ca4 --- /dev/null +++ b/run-3/checkpoint-1000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ea3c5a2f00688c8f2d21b62d2c759f3e10550fb6cd1104d2317252f3df05792 +size 14244 diff --git a/run-3/checkpoint-1000/scheduler.pt b/run-3/checkpoint-1000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a30924582c078313528a868826803e8f92c97691 --- /dev/null +++ b/run-3/checkpoint-1000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c9d79d2d6372aa7db16d7f2b994968e91c8151874fc4fb8aa44a7776f4a4b70 +size 1064 diff --git a/run-3/checkpoint-1000/trainer_state.json b/run-3/checkpoint-1000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b0b620ca5b48c545cf78a2719b8e4c657e7b7756 --- /dev/null +++ b/run-3/checkpoint-1000/trainer_state.json @@ -0,0 +1,187 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.310344827586207, + "eval_steps": 100, + "global_step": 1000, + "is_hyper_param_search": true, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.43103448275862066, + "grad_norm": 2.038851499557495, + "learning_rate": 2.7385733706109983e-05, + "loss": 2.6183, + "step": 100 + }, + { + "epoch": 0.43103448275862066, + "eval_loss": 1.9287675619125366, + "eval_runtime": 21.0079, + "eval_samples_per_second": 4.903, + "eval_steps_per_second": 1.238, + "step": 100 + }, + { + "epoch": 0.8620689655172413, + "grad_norm": 3.1079177856445312, + "learning_rate": 2.480703938350076e-05, + "loss": 1.3341, + "step": 200 + }, + { + "epoch": 0.8620689655172413, + "eval_loss": 0.7545433044433594, + "eval_runtime": 20.9967, + "eval_samples_per_second": 4.906, + "eval_steps_per_second": 1.238, + "step": 200 + }, + { + "epoch": 1.293103448275862, + "grad_norm": 31.098602294921875, + "learning_rate": 2.2254132004117625e-05, + "loss": 0.5723, + "step": 300 + }, + { + "epoch": 1.293103448275862, + "eval_loss": 0.4216664433479309, + "eval_runtime": 21.024, + "eval_samples_per_second": 4.899, + "eval_steps_per_second": 1.237, + "step": 300 + }, + { + "epoch": 1.7241379310344827, + "grad_norm": 4.484708786010742, + "learning_rate": 1.9675437681508397e-05, + "loss": 0.3171, + "step": 400 + }, + { + "epoch": 1.7241379310344827, + "eval_loss": 0.38382911682128906, + "eval_runtime": 20.9128, + "eval_samples_per_second": 4.925, + "eval_steps_per_second": 1.243, + "step": 400 + }, + { + "epoch": 2.1551724137931036, + "grad_norm": 0.38779252767562866, + "learning_rate": 1.7096743358899172e-05, + "loss": 0.3163, + "step": 500 + }, + { + "epoch": 2.1551724137931036, + "eval_loss": 0.35805144906044006, + "eval_runtime": 20.964, + "eval_samples_per_second": 4.913, + "eval_steps_per_second": 1.24, + "step": 500 + }, + { + "epoch": 2.586206896551724, + "grad_norm": 0.8454769849777222, + "learning_rate": 1.4518049036289945e-05, + "loss": 0.2859, + "step": 600 + }, + { + "epoch": 2.586206896551724, + "eval_loss": 0.3379548192024231, + "eval_runtime": 20.8492, + "eval_samples_per_second": 4.94, + "eval_steps_per_second": 1.247, + "step": 600 + }, + { + "epoch": 3.0172413793103448, + "grad_norm": 2.986409902572632, + "learning_rate": 1.1939354713680719e-05, + "loss": 0.2826, + "step": 700 + }, + { + "epoch": 3.0172413793103448, + "eval_loss": 0.3366047143936157, + "eval_runtime": 20.8727, + "eval_samples_per_second": 4.935, + "eval_steps_per_second": 1.246, + "step": 700 + }, + { + "epoch": 3.4482758620689653, + "grad_norm": 2.4868862628936768, + "learning_rate": 9.360660391071492e-06, + "loss": 0.2005, + "step": 800 + }, + { + "epoch": 3.4482758620689653, + "eval_loss": 0.32498306035995483, + "eval_runtime": 20.8713, + "eval_samples_per_second": 4.935, + "eval_steps_per_second": 1.246, + "step": 800 + }, + { + "epoch": 3.8793103448275863, + "grad_norm": 4.245973587036133, + "learning_rate": 6.7819660684622655e-06, + "loss": 0.2738, + "step": 900 + }, + { + "epoch": 3.8793103448275863, + "eval_loss": 0.3215656280517578, + "eval_runtime": 20.8619, + "eval_samples_per_second": 4.937, + "eval_steps_per_second": 1.246, + "step": 900 + }, + { + "epoch": 4.310344827586207, + "grad_norm": 2.5610294342041016, + "learning_rate": 4.203271745853039e-06, + "loss": 0.1793, + "step": 1000 + }, + { + "epoch": 4.310344827586207, + "eval_loss": 0.3199079930782318, + "eval_runtime": 20.8816, + "eval_samples_per_second": 4.933, + "eval_steps_per_second": 1.245, + "step": 1000 + } + ], + "logging_steps": 100, + "max_steps": 1160, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "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": 1.370747847573504e+19, + "train_batch_size": 4, + "trial_name": null, + "trial_params": { + "learning_rate": 2.8623506980962413e-05, + "per_device_train_batch_size": 4, + "weight_decay": 0.0002564487997469974 + } +} diff --git a/run-3/checkpoint-1000/training_args.bin b/run-3/checkpoint-1000/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..20c8ffb934d1ad41ee6bcdd0b9227ebf26e525e5 --- /dev/null +++ b/run-3/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:495eed51f9cc52be9cc85b81ed7ad4732c4666172dec994145ffcfe43f53ca26 +size 5240 diff --git a/run-3/checkpoint-500/README.md b/run-3/checkpoint-500/README.md new file mode 100644 index 0000000000000000000000000000000000000000..4aa23bca34250d45e5f8a17f4e076efd91b742d4 --- /dev/null +++ b/run-3/checkpoint-500/README.md @@ -0,0 +1,202 @@ +--- +base_model: openai/whisper-large-v3 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.11.2.dev0 \ No newline at end of file diff --git a/run-3/checkpoint-500/adapter_config.json b/run-3/checkpoint-500/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a1573cdec967d02c99b5de3d3777e107a6eb09b2 --- /dev/null +++ b/run-3/checkpoint-500/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": { + "base_model_class": "WhisperForConditionalGeneration", + "parent_library": "transformers.models.whisper.modeling_whisper" + }, + "base_model_name_or_path": "openai/whisper-large-v3", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 64, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/run-3/checkpoint-500/adapter_model.safetensors b/run-3/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d5b64baf0f444315e744f8dbd675608fee457bb --- /dev/null +++ b/run-3/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9c2993d4498497f3ce7e37dc2a53f84437dc12f4d26a724a76a7c6786a73e9 +size 62969640 diff --git a/run-3/checkpoint-500/optimizer.pt b/run-3/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..29c536e61085321fcaa530bb45f0e532fa78adfc --- /dev/null +++ b/run-3/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b59b49f11a2b356edbc74cff90b1465589fcc62d67bca6d415ccb5f3cfbd280 +size 126151570 diff --git a/run-3/checkpoint-500/preprocessor_config.json b/run-3/checkpoint-500/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f --- /dev/null +++ b/run-3/checkpoint-500/preprocessor_config.json @@ -0,0 +1,14 @@ +{ + "chunk_length": 30, + "feature_extractor_type": "WhisperFeatureExtractor", + "feature_size": 128, + "hop_length": 160, + "n_fft": 400, + "n_samples": 480000, + "nb_max_frames": 3000, + "padding_side": "right", + "padding_value": 0.0, + "processor_class": "WhisperProcessor", + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/run-3/checkpoint-500/rng_state.pth b/run-3/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..15510f74408e76b91faab61a3bdf1988830de0b0 --- /dev/null +++ b/run-3/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0304c2bfdd0a1ea00f81002e6bcea16f60834a8a6d00facadff96d5d95981a2e +size 14244 diff --git a/run-3/checkpoint-500/scheduler.pt b/run-3/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..9acabd478b0e515495c0c4d8c2a7e0989dfeb7fd --- /dev/null +++ b/run-3/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a76133c762716def19db0a2405fb8f85dfac386da0351b06af07b179a0ee7a41 +size 1064 diff --git a/run-3/checkpoint-500/trainer_state.json b/run-3/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..9561832fe80ccde7d60381e95416c450e248c462 --- /dev/null +++ b/run-3/checkpoint-500/trainer_state.json @@ -0,0 +1,112 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.1551724137931036, + "eval_steps": 100, + "global_step": 500, + "is_hyper_param_search": true, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.43103448275862066, + "grad_norm": 2.038851499557495, + "learning_rate": 2.7385733706109983e-05, + "loss": 2.6183, + "step": 100 + }, + { + "epoch": 0.43103448275862066, + "eval_loss": 1.9287675619125366, + "eval_runtime": 21.0079, + "eval_samples_per_second": 4.903, + "eval_steps_per_second": 1.238, + "step": 100 + }, + { + "epoch": 0.8620689655172413, + "grad_norm": 3.1079177856445312, + "learning_rate": 2.480703938350076e-05, + "loss": 1.3341, + "step": 200 + }, + { + "epoch": 0.8620689655172413, + "eval_loss": 0.7545433044433594, + "eval_runtime": 20.9967, + "eval_samples_per_second": 4.906, + "eval_steps_per_second": 1.238, + "step": 200 + }, + { + "epoch": 1.293103448275862, + "grad_norm": 31.098602294921875, + "learning_rate": 2.2254132004117625e-05, + "loss": 0.5723, + "step": 300 + }, + { + "epoch": 1.293103448275862, + "eval_loss": 0.4216664433479309, + "eval_runtime": 21.024, + "eval_samples_per_second": 4.899, + "eval_steps_per_second": 1.237, + "step": 300 + }, + { + "epoch": 1.7241379310344827, + "grad_norm": 4.484708786010742, + "learning_rate": 1.9675437681508397e-05, + "loss": 0.3171, + "step": 400 + }, + { + "epoch": 1.7241379310344827, + "eval_loss": 0.38382911682128906, + "eval_runtime": 20.9128, + "eval_samples_per_second": 4.925, + "eval_steps_per_second": 1.243, + "step": 400 + }, + { + "epoch": 2.1551724137931036, + "grad_norm": 0.38779252767562866, + "learning_rate": 1.7096743358899172e-05, + "loss": 0.3163, + "step": 500 + }, + { + "epoch": 2.1551724137931036, + "eval_loss": 0.35805144906044006, + "eval_runtime": 20.964, + "eval_samples_per_second": 4.913, + "eval_steps_per_second": 1.24, + "step": 500 + } + ], + "logging_steps": 100, + "max_steps": 1160, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "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": 6.85373923786752e+18, + "train_batch_size": 4, + "trial_name": null, + "trial_params": { + "learning_rate": 2.8623506980962413e-05, + "per_device_train_batch_size": 4, + "weight_decay": 0.0002564487997469974 + } +} diff --git a/run-3/checkpoint-500/training_args.bin b/run-3/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..20c8ffb934d1ad41ee6bcdd0b9227ebf26e525e5 --- /dev/null +++ b/run-3/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:495eed51f9cc52be9cc85b81ed7ad4732c4666172dec994145ffcfe43f53ca26 +size 5240 diff --git a/run-4/checkpoint-1000/README.md b/run-4/checkpoint-1000/README.md new file mode 100644 index 0000000000000000000000000000000000000000..4aa23bca34250d45e5f8a17f4e076efd91b742d4 --- /dev/null +++ b/run-4/checkpoint-1000/README.md @@ -0,0 +1,202 @@ +--- +base_model: openai/whisper-large-v3 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.11.2.dev0 \ No newline at end of file diff --git a/run-4/checkpoint-1000/adapter_config.json b/run-4/checkpoint-1000/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a1573cdec967d02c99b5de3d3777e107a6eb09b2 --- /dev/null +++ b/run-4/checkpoint-1000/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": { + "base_model_class": "WhisperForConditionalGeneration", + "parent_library": "transformers.models.whisper.modeling_whisper" + }, + "base_model_name_or_path": "openai/whisper-large-v3", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 64, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/run-4/checkpoint-1000/adapter_model.safetensors b/run-4/checkpoint-1000/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1924471fd59c3b6255bcc0d0ef0397c772b6556d --- /dev/null +++ b/run-4/checkpoint-1000/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:933e901f1be6be9143365e2113c44a17de57fd4acf37950f158990e00803ab5a +size 62969640 diff --git a/run-4/checkpoint-1000/optimizer.pt b/run-4/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..8354d93bb604466f3744d4421daf8500078c2510 --- /dev/null +++ b/run-4/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74cfa6bd27311eeec698f8f391bca976e044bacc39269d04ec817f8a03e7b32f +size 126151570 diff --git a/run-4/checkpoint-1000/preprocessor_config.json b/run-4/checkpoint-1000/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f --- /dev/null +++ b/run-4/checkpoint-1000/preprocessor_config.json @@ -0,0 +1,14 @@ +{ + "chunk_length": 30, + "feature_extractor_type": "WhisperFeatureExtractor", + "feature_size": 128, + "hop_length": 160, + "n_fft": 400, + "n_samples": 480000, + "nb_max_frames": 3000, + "padding_side": "right", + "padding_value": 0.0, + "processor_class": "WhisperProcessor", + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/run-4/checkpoint-1000/rng_state.pth b/run-4/checkpoint-1000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..a83021f40fcba6b6f9e3db4d2752fd910ffd9ca4 --- /dev/null +++ b/run-4/checkpoint-1000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ea3c5a2f00688c8f2d21b62d2c759f3e10550fb6cd1104d2317252f3df05792 +size 14244 diff --git a/run-4/checkpoint-1000/scheduler.pt b/run-4/checkpoint-1000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb0b9ac89809e45dc179aeef2a1ce1e7c93035e2 --- /dev/null +++ b/run-4/checkpoint-1000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:552f0e5784ad9e369abfd53fad46df6beb43e40b46fcefeb02d26d8102ff2f46 +size 1064 diff --git a/run-4/checkpoint-1000/trainer_state.json b/run-4/checkpoint-1000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..42e53502887f58be8ab2bc4eee205e35fa4f37e7 --- /dev/null +++ b/run-4/checkpoint-1000/trainer_state.json @@ -0,0 +1,187 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.310344827586207, + "eval_steps": 100, + "global_step": 1000, + "is_hyper_param_search": true, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.43103448275862066, + "grad_norm": 2.0799944400787354, + "learning_rate": 0.0008505514368287741, + "loss": 1.1288, + "step": 100 + }, + { + "epoch": 0.43103448275862066, + "eval_loss": 0.45160382986068726, + "eval_runtime": 20.9625, + "eval_samples_per_second": 4.914, + "eval_steps_per_second": 1.24, + "step": 100 + }, + { + "epoch": 0.8620689655172413, + "grad_norm": 4.587525844573975, + "learning_rate": 0.0007704618476735224, + "loss": 0.4782, + "step": 200 + }, + { + "epoch": 0.8620689655172413, + "eval_loss": 0.5653709769248962, + "eval_runtime": 20.9749, + "eval_samples_per_second": 4.911, + "eval_steps_per_second": 1.24, + "step": 200 + }, + { + "epoch": 1.293103448275862, + "grad_norm": 0.8965305089950562, + "learning_rate": 0.0006903722585182705, + "loss": 0.3686, + "step": 300 + }, + { + "epoch": 1.293103448275862, + "eval_loss": 0.37166354060173035, + "eval_runtime": 21.0098, + "eval_samples_per_second": 4.902, + "eval_steps_per_second": 1.238, + "step": 300 + }, + { + "epoch": 1.7241379310344827, + "grad_norm": 1.4389190673828125, + "learning_rate": 0.0006102826693630186, + "loss": 0.2196, + "step": 400 + }, + { + "epoch": 1.7241379310344827, + "eval_loss": 0.3420710861682892, + "eval_runtime": 20.9067, + "eval_samples_per_second": 4.927, + "eval_steps_per_second": 1.244, + "step": 400 + }, + { + "epoch": 2.1551724137931036, + "grad_norm": 0.03094407171010971, + "learning_rate": 0.000530193080207767, + "loss": 0.2273, + "step": 500 + }, + { + "epoch": 2.1551724137931036, + "eval_loss": 0.32964229583740234, + "eval_runtime": 20.7324, + "eval_samples_per_second": 4.968, + "eval_steps_per_second": 1.254, + "step": 500 + }, + { + "epoch": 2.586206896551724, + "grad_norm": 1.477461338043213, + "learning_rate": 0.00045010349105251515, + "loss": 0.162, + "step": 600 + }, + { + "epoch": 2.586206896551724, + "eval_loss": 0.3319362998008728, + "eval_runtime": 20.8786, + "eval_samples_per_second": 4.933, + "eval_steps_per_second": 1.245, + "step": 600 + }, + { + "epoch": 3.0172413793103448, + "grad_norm": 0.5502158403396606, + "learning_rate": 0.00037001390189726334, + "loss": 0.1491, + "step": 700 + }, + { + "epoch": 3.0172413793103448, + "eval_loss": 0.3399050533771515, + "eval_runtime": 20.9822, + "eval_samples_per_second": 4.909, + "eval_steps_per_second": 1.239, + "step": 700 + }, + { + "epoch": 3.4482758620689653, + "grad_norm": 0.015873726457357407, + "learning_rate": 0.0002899243127420115, + "loss": 0.0508, + "step": 800 + }, + { + "epoch": 3.4482758620689653, + "eval_loss": 0.3408341109752655, + "eval_runtime": 20.9466, + "eval_samples_per_second": 4.917, + "eval_steps_per_second": 1.241, + "step": 800 + }, + { + "epoch": 3.8793103448275863, + "grad_norm": 1.5245095491409302, + "learning_rate": 0.0002098347235867597, + "loss": 0.0809, + "step": 900 + }, + { + "epoch": 3.8793103448275863, + "eval_loss": 0.30382341146469116, + "eval_runtime": 20.9944, + "eval_samples_per_second": 4.906, + "eval_steps_per_second": 1.238, + "step": 900 + }, + { + "epoch": 4.310344827586207, + "grad_norm": 0.9764588475227356, + "learning_rate": 0.00012974513443150793, + "loss": 0.0289, + "step": 1000 + }, + { + "epoch": 4.310344827586207, + "eval_loss": 0.3065425455570221, + "eval_runtime": 20.8406, + "eval_samples_per_second": 4.942, + "eval_steps_per_second": 1.248, + "step": 1000 + } + ], + "logging_steps": 100, + "max_steps": 1160, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "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": 1.370747847573504e+19, + "train_batch_size": 4, + "trial_name": null, + "trial_params": { + "learning_rate": 0.000888994439623295, + "per_device_train_batch_size": 4, + "weight_decay": 7.230520338117164e-05 + } +} diff --git a/run-4/checkpoint-1000/training_args.bin b/run-4/checkpoint-1000/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..896091b0ba09c8dfaf5bfa8454c1b990fa8530da --- /dev/null +++ b/run-4/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:873c744acc8154b9893436e275186d255aa85ed9b253b62dadc294fd46610919 +size 5240 diff --git a/run-4/checkpoint-500/README.md b/run-4/checkpoint-500/README.md new file mode 100644 index 0000000000000000000000000000000000000000..4aa23bca34250d45e5f8a17f4e076efd91b742d4 --- /dev/null +++ b/run-4/checkpoint-500/README.md @@ -0,0 +1,202 @@ +--- +base_model: openai/whisper-large-v3 +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.11.2.dev0 \ No newline at end of file diff --git a/run-4/checkpoint-500/adapter_config.json b/run-4/checkpoint-500/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a1573cdec967d02c99b5de3d3777e107a6eb09b2 --- /dev/null +++ b/run-4/checkpoint-500/adapter_config.json @@ -0,0 +1,32 @@ +{ + "alpha_pattern": {}, + "auto_mapping": { + "base_model_class": "WhisperForConditionalGeneration", + "parent_library": "transformers.models.whisper.modeling_whisper" + }, + "base_model_name_or_path": "openai/whisper-large-v3", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 64, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "v_proj", + "q_proj" + ], + "task_type": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/run-4/checkpoint-500/adapter_model.safetensors b/run-4/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..614da7a9d342191bcbc05ae94caf3ea32fb9a28a --- /dev/null +++ b/run-4/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1c4f7c6c732bb8f18475d64d7065f6f592fe8f9fdf4fce390373c7c028a9fbc +size 62969640 diff --git a/run-4/checkpoint-500/optimizer.pt b/run-4/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..857c06fbf377183f04b07a7e6985c06cad605009 --- /dev/null +++ b/run-4/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00806f10eb6998f4f715652a593bb48198f6f83e70e1465d51101b8f3269b3e6 +size 126151570 diff --git a/run-4/checkpoint-500/preprocessor_config.json b/run-4/checkpoint-500/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f --- /dev/null +++ b/run-4/checkpoint-500/preprocessor_config.json @@ -0,0 +1,14 @@ +{ + "chunk_length": 30, + "feature_extractor_type": "WhisperFeatureExtractor", + "feature_size": 128, + "hop_length": 160, + "n_fft": 400, + "n_samples": 480000, + "nb_max_frames": 3000, + "padding_side": "right", + "padding_value": 0.0, + "processor_class": "WhisperProcessor", + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/run-4/checkpoint-500/rng_state.pth b/run-4/checkpoint-500/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..15510f74408e76b91faab61a3bdf1988830de0b0 --- /dev/null +++ b/run-4/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0304c2bfdd0a1ea00f81002e6bcea16f60834a8a6d00facadff96d5d95981a2e +size 14244 diff --git a/run-4/checkpoint-500/scheduler.pt b/run-4/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ff131de951b43360d80dbdfbc5df6961ba99b7db --- /dev/null +++ b/run-4/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f98a1791974e926779867c9c9ffbcde7cffd1f7833b88f46d615245780bf5db +size 1064 diff --git a/run-4/checkpoint-500/trainer_state.json b/run-4/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..bd78bef0c1ba1417e1d120c5d4fba7cb1b9714f6 --- /dev/null +++ b/run-4/checkpoint-500/trainer_state.json @@ -0,0 +1,112 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.1551724137931036, + "eval_steps": 100, + "global_step": 500, + "is_hyper_param_search": true, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.43103448275862066, + "grad_norm": 2.0799944400787354, + "learning_rate": 0.0008505514368287741, + "loss": 1.1288, + "step": 100 + }, + { + "epoch": 0.43103448275862066, + "eval_loss": 0.45160382986068726, + "eval_runtime": 20.9625, + "eval_samples_per_second": 4.914, + "eval_steps_per_second": 1.24, + "step": 100 + }, + { + "epoch": 0.8620689655172413, + "grad_norm": 4.587525844573975, + "learning_rate": 0.0007704618476735224, + "loss": 0.4782, + "step": 200 + }, + { + "epoch": 0.8620689655172413, + "eval_loss": 0.5653709769248962, + "eval_runtime": 20.9749, + "eval_samples_per_second": 4.911, + "eval_steps_per_second": 1.24, + "step": 200 + }, + { + "epoch": 1.293103448275862, + "grad_norm": 0.8965305089950562, + "learning_rate": 0.0006903722585182705, + "loss": 0.3686, + "step": 300 + }, + { + "epoch": 1.293103448275862, + "eval_loss": 0.37166354060173035, + "eval_runtime": 21.0098, + "eval_samples_per_second": 4.902, + "eval_steps_per_second": 1.238, + "step": 300 + }, + { + "epoch": 1.7241379310344827, + "grad_norm": 1.4389190673828125, + "learning_rate": 0.0006102826693630186, + "loss": 0.2196, + "step": 400 + }, + { + "epoch": 1.7241379310344827, + "eval_loss": 0.3420710861682892, + "eval_runtime": 20.9067, + "eval_samples_per_second": 4.927, + "eval_steps_per_second": 1.244, + "step": 400 + }, + { + "epoch": 2.1551724137931036, + "grad_norm": 0.03094407171010971, + "learning_rate": 0.000530193080207767, + "loss": 0.2273, + "step": 500 + }, + { + "epoch": 2.1551724137931036, + "eval_loss": 0.32964229583740234, + "eval_runtime": 20.7324, + "eval_samples_per_second": 4.968, + "eval_steps_per_second": 1.254, + "step": 500 + } + ], + "logging_steps": 100, + "max_steps": 1160, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "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": 6.85373923786752e+18, + "train_batch_size": 4, + "trial_name": null, + "trial_params": { + "learning_rate": 0.000888994439623295, + "per_device_train_batch_size": 4, + "weight_decay": 7.230520338117164e-05 + } +} diff --git a/run-4/checkpoint-500/training_args.bin b/run-4/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..896091b0ba09c8dfaf5bfa8454c1b990fa8530da --- /dev/null +++ b/run-4/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:873c744acc8154b9893436e275186d255aa85ed9b253b62dadc294fd46610919 +size 5240 diff --git a/runs/Jul04_15-19-58_gigio-desktop/events.out.tfevents.1720099198.gigio-desktop.9315.0 b/runs/Jul04_15-19-58_gigio-desktop/events.out.tfevents.1720099198.gigio-desktop.9315.0 new file mode 100644 index 0000000000000000000000000000000000000000..c52db3da7c63da166f9c1d45e482639b58688219 --- /dev/null +++ b/runs/Jul04_15-19-58_gigio-desktop/events.out.tfevents.1720099198.gigio-desktop.9315.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f39169b1b0436bd9c9ebdeaa0a01dd91bacaba2573e070a5d3bb233528e52f7 +size 6254 diff --git a/runs/Jul04_15-22-14_gigio-desktop/events.out.tfevents.1720099334.gigio-desktop.10361.0 b/runs/Jul04_15-22-14_gigio-desktop/events.out.tfevents.1720099334.gigio-desktop.10361.0 new file mode 100644 index 0000000000000000000000000000000000000000..80c49f15809a39a3e78ff758e0a6ee76ff515ab2 --- /dev/null +++ b/runs/Jul04_15-22-14_gigio-desktop/events.out.tfevents.1720099334.gigio-desktop.10361.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d98c64d19018cb3e55aa4c77593017d3191f2ca037d354be031fd5c4e056a0 +size 6457 diff --git a/runs/Jul05_16-24-10_gigio-desktop/events.out.tfevents.1720189454.gigio-desktop.3195.0 b/runs/Jul05_16-24-10_gigio-desktop/events.out.tfevents.1720189454.gigio-desktop.3195.0 new file mode 100644 index 0000000000000000000000000000000000000000..e9e364716b6ffe66b6ed5a8d1279015f474af882 --- /dev/null +++ b/runs/Jul05_16-24-10_gigio-desktop/events.out.tfevents.1720189454.gigio-desktop.3195.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:811e94687a9fb4e9de34ac24b36742a1ce8dddde4f1d0ed7fe5171f0b2c23172 +size 6249 diff --git a/runs/Jul05_16-29-38_gigio-desktop/events.out.tfevents.1720189782.gigio-desktop.4434.0 b/runs/Jul05_16-29-38_gigio-desktop/events.out.tfevents.1720189782.gigio-desktop.4434.0 new file mode 100644 index 0000000000000000000000000000000000000000..ec03b0a8f13d46321b4a9009dbc1778e70d0c2c5 --- /dev/null +++ b/runs/Jul05_16-29-38_gigio-desktop/events.out.tfevents.1720189782.gigio-desktop.4434.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a92ec7d9117965564c6207091981c4f48114fc2162b43d921cbd19ff5993e1df +size 6455 diff --git a/runs/Jul05_16-35-03_gigio-desktop/events.out.tfevents.1720190107.gigio-desktop.5966.0 b/runs/Jul05_16-35-03_gigio-desktop/events.out.tfevents.1720190107.gigio-desktop.5966.0 new file mode 100644 index 0000000000000000000000000000000000000000..ed0ee1b581f4601c308b2d77d8185e9d47939dfc --- /dev/null +++ b/runs/Jul05_16-35-03_gigio-desktop/events.out.tfevents.1720190107.gigio-desktop.5966.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e5ac0930ae0bb3274cf4789d54322d372b4f9e96a5c9f03a07a0eb00c39c79a +size 7562 diff --git a/runs/Jul05_16-35-03_gigio-desktop/events.out.tfevents.1720190651.gigio-desktop.5966.1 b/runs/Jul05_16-35-03_gigio-desktop/events.out.tfevents.1720190651.gigio-desktop.5966.1 new file mode 100644 index 0000000000000000000000000000000000000000..05fe25567c7be8e0af06dd849a9ebb408d0dfe72 --- /dev/null +++ b/runs/Jul05_16-35-03_gigio-desktop/events.out.tfevents.1720190651.gigio-desktop.5966.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65999d2c3f48bb9cb27a54396d9cf2273c98d80d1c68de44c2a4c9e7a8a8572d +size 7074 diff --git a/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720425539.gigio-desktop.4003.0 b/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720425539.gigio-desktop.4003.0 new file mode 100644 index 0000000000000000000000000000000000000000..9dea304fa00c22d014ba68619093991a6d884361 --- /dev/null +++ b/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720425539.gigio-desktop.4003.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae79916e52327deebc6cecf511390c278660c6316c40a835af61a5224fea4de7 +size 9043 diff --git a/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720428242.gigio-desktop.4003.1 b/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720428242.gigio-desktop.4003.1 new file mode 100644 index 0000000000000000000000000000000000000000..1246d218e9698320790bf7cf8414d6e2a245d03b --- /dev/null +++ b/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720428242.gigio-desktop.4003.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1730015407cdc6bc5c5d6ea436216d59eba6c2a8ae19b0985037e8e3d081f30 +size 9042 diff --git a/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720430932.gigio-desktop.4003.2 b/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720430932.gigio-desktop.4003.2 new file mode 100644 index 0000000000000000000000000000000000000000..243e9182cf3590f8ac3d4349c9dff36c29b9e590 --- /dev/null +++ b/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720430932.gigio-desktop.4003.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be9158a67be33077ca7243e97ac38427011d71255dab22ce6d0770089838603d +size 11933 diff --git a/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720433655.gigio-desktop.4003.3 b/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720433655.gigio-desktop.4003.3 new file mode 100644 index 0000000000000000000000000000000000000000..83b8d772043d1fca6cb907ece24aaa6d26b2cdd5 --- /dev/null +++ b/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720433655.gigio-desktop.4003.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b3f2f671ca1c7a68b3c86f8035d3b4854c19131a69336577f77fd8521bcfeb0 +size 11935 diff --git a/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720436361.gigio-desktop.4003.4 b/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720436361.gigio-desktop.4003.4 new file mode 100644 index 0000000000000000000000000000000000000000..15188403f35153c49728afa63f39d6ea7d2b0312 --- /dev/null +++ b/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720436361.gigio-desktop.4003.4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3da9e1510998f0f726f553566eed9f9f7ca5b47ee7f3fb76fd3b564a6476333a +size 11933 diff --git a/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720439063.gigio-desktop.4003.5 b/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720439063.gigio-desktop.4003.5 new file mode 100644 index 0000000000000000000000000000000000000000..a80783c1c460ab94aa26ae837ae43a01a4526371 --- /dev/null +++ b/runs/Jul08_09-58-54_gigio-desktop/events.out.tfevents.1720439063.gigio-desktop.4003.5 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6131214f906fa0bdb6523f326040f46fd8aa15224a07d21682a4ce0cb348169 +size 6759 diff --git a/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450853.gigio-desktop.5088.0 b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450853.gigio-desktop.5088.0 new file mode 100644 index 0000000000000000000000000000000000000000..448ba8b84a174f882f58d4e26cfd149243e4efc2 --- /dev/null +++ b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450853.gigio-desktop.5088.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5e4891b2896ccc803e102b376fc9d89e1225593adb5461d6423d91cb68a1247 +size 7576 diff --git a/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450889.gigio-desktop.5088.1 b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450889.gigio-desktop.5088.1 new file mode 100644 index 0000000000000000000000000000000000000000..4407b3160d362ee99cabc81d7ecfe5cfa0956901 --- /dev/null +++ b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450889.gigio-desktop.5088.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:427764c12532b5966c04a678fa0d1141fc6c8b8c821e2236dd199843926f4b5f +size 7104 diff --git a/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450918.gigio-desktop.5088.2 b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450918.gigio-desktop.5088.2 new file mode 100644 index 0000000000000000000000000000000000000000..368fe6b6623cc298782ac15bfa71d8a0a4a98b74 --- /dev/null +++ b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450918.gigio-desktop.5088.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89138604ea88726ab4a8e989cd3bed23ec94b50c45a750203d9fc6f02f589dcc +size 7576 diff --git a/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450947.gigio-desktop.5088.3 b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450947.gigio-desktop.5088.3 new file mode 100644 index 0000000000000000000000000000000000000000..5528e895bf929c8de2c6f1737bc3b54fefb77b1c --- /dev/null +++ b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450947.gigio-desktop.5088.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fddb21aba3347d8d8f0b97e98b25c15db37d4c4370d989da1de880fded92637 +size 7574 diff --git a/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450977.gigio-desktop.5088.4 b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450977.gigio-desktop.5088.4 new file mode 100644 index 0000000000000000000000000000000000000000..c7415a2eb97bfecc43c4b5bc6f219399ff89f86a --- /dev/null +++ b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720450977.gigio-desktop.5088.4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6692c153df06f6ed307a707350b83c86f21d5a64ebecfb45398e194809be3fa8 +size 7577 diff --git a/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451006.gigio-desktop.5088.5 b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451006.gigio-desktop.5088.5 new file mode 100644 index 0000000000000000000000000000000000000000..29eef014b5ab51c963cc94ac908e88b5a3bec672 --- /dev/null +++ b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451006.gigio-desktop.5088.5 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d274f84094e08148639e9d3374299694265a15aac6e46e9351594266006fa054 +size 6755 diff --git a/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451021.gigio-desktop.5088.6 b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451021.gigio-desktop.5088.6 new file mode 100644 index 0000000000000000000000000000000000000000..fd2096c8b4c060e7c71ae55449f6a89ff3d5bbe1 --- /dev/null +++ b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451021.gigio-desktop.5088.6 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa502c428c7678d7676aef936aa0af32328dcc4528f568aeab6bb75658fbab01 +size 7575 diff --git a/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451051.gigio-desktop.5088.7 b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451051.gigio-desktop.5088.7 new file mode 100644 index 0000000000000000000000000000000000000000..20a835c261b0c2f3515d24b6ded273771d4d0257 --- /dev/null +++ b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451051.gigio-desktop.5088.7 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ed249ef97ef645ede3afa77a0bff68fbe7fb7bbf9ccc2abd59be525b61bb06 +size 6753 diff --git a/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451065.gigio-desktop.5088.8 b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451065.gigio-desktop.5088.8 new file mode 100644 index 0000000000000000000000000000000000000000..61811d46300ea946c9ca20ac3991889b52ec3c1f --- /dev/null +++ b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451065.gigio-desktop.5088.8 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb152e34209d6676b0d3e680faecaf6c51a2ebfb4af25f87132dc07e11fdbf72 +size 7102 diff --git a/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451094.gigio-desktop.5088.9 b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451094.gigio-desktop.5088.9 new file mode 100644 index 0000000000000000000000000000000000000000..8b1f3bda2ceae7862f0f19c28a001f2051ae13af --- /dev/null +++ b/runs/Jul08_17-00-49_gigio-desktop/events.out.tfevents.1720451094.gigio-desktop.5088.9 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82387a49ae6f6f56468a83ad414132cf2bb35cbe6bc62b6fcc180c4ebd51293b +size 6754 diff --git a/runs/Jul08_17-52-14_gigio-desktop/events.out.tfevents.1720453938.gigio-desktop.8042.0 b/runs/Jul08_17-52-14_gigio-desktop/events.out.tfevents.1720453938.gigio-desktop.8042.0 new file mode 100644 index 0000000000000000000000000000000000000000..9bcce00f408853a79f0372cac6168d97952bbbd5 --- /dev/null +++ b/runs/Jul08_17-52-14_gigio-desktop/events.out.tfevents.1720453938.gigio-desktop.8042.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61471d72aed16c73931dde87a86b5f88ca931322c9696076fc7201852c5c5741 +size 6755 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454050.gigio-desktop.8547.0 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454050.gigio-desktop.8547.0 new file mode 100644 index 0000000000000000000000000000000000000000..8dccbc60f84d44bdf123a4dc4a57da24a04370af --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454050.gigio-desktop.8547.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51624876f5afaf596273c9d7a062801b20f54452ce3cfc44dd2f66c8793febbf +size 7576 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454080.gigio-desktop.8547.1 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454080.gigio-desktop.8547.1 new file mode 100644 index 0000000000000000000000000000000000000000..f03f025e961d9513b8bedc6ae39b1418d79adc57 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454080.gigio-desktop.8547.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264f1606747ba0b93138302094d7c287c8338b45f9ca3c73bb63ae502e159d53 +size 7104 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454109.gigio-desktop.8547.2 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454109.gigio-desktop.8547.2 new file mode 100644 index 0000000000000000000000000000000000000000..d54d770533597bcdc0806819764c3f9df36a6a05 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454109.gigio-desktop.8547.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca46409917a534ad0cf91899fee312952652ea4b12b0b91e02d93b933c0cd3b4 +size 7103 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454138.gigio-desktop.8547.3 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454138.gigio-desktop.8547.3 new file mode 100644 index 0000000000000000000000000000000000000000..e992837cec7c171ace14b6811c109cb586acf8e3 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454138.gigio-desktop.8547.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:215f7529ca83d3b1d74590f6c88a84ff2432322a01ef448d6c289d59aeb4630e +size 7576 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454168.gigio-desktop.8547.4 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454168.gigio-desktop.8547.4 new file mode 100644 index 0000000000000000000000000000000000000000..0d05a105e6811bdf6bca0717fb7543ad7ae807ca --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454168.gigio-desktop.8547.4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eed382f0cf05640f8bf455f7a523c737144bc029aa5c2187c4b450adac549d3 +size 7102 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454197.gigio-desktop.8547.5 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454197.gigio-desktop.8547.5 new file mode 100644 index 0000000000000000000000000000000000000000..03b798c89e24be7c4113d89d49ce1ad79e8b0918 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454197.gigio-desktop.8547.5 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321f001d4178f14401a8b84c9d489b375101111e49d8183337eac0be67cb7ca4 +size 7577 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454226.gigio-desktop.8547.6 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454226.gigio-desktop.8547.6 new file mode 100644 index 0000000000000000000000000000000000000000..b9bf45a2a5ed54a090e30554834719e12eb08455 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454226.gigio-desktop.8547.6 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:958435134b9fbf7c4d3e1431b190ef08eaadfd8e9d9ac364551339227b0279c7 +size 7101 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454255.gigio-desktop.8547.7 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454255.gigio-desktop.8547.7 new file mode 100644 index 0000000000000000000000000000000000000000..181f479e9d402f60a3e215b39f041c0fc9fc1d5d --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454255.gigio-desktop.8547.7 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:491d6246e7bd667d35b147813afdaf81e2e50ca96bffea02df2a11cf7e316a1a +size 6757 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454282.gigio-desktop.8547.8 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454282.gigio-desktop.8547.8 new file mode 100644 index 0000000000000000000000000000000000000000..1e666c499ecb3d39673fe751439343cfa04dd498 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454282.gigio-desktop.8547.8 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bbf24726933c5050606bbeb3a1bf8aefe88613f45aeafedf4dda343bc3e93bd +size 6755 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454308.gigio-desktop.8547.9 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454308.gigio-desktop.8547.9 new file mode 100644 index 0000000000000000000000000000000000000000..946611f4da887d2336f83e68dd0d581ebd12cd46 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454308.gigio-desktop.8547.9 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df5086d22f6a05eba832057db4596dbd5fed59bbe4d92da5d238d87ba6ad5a53 +size 6754 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454323.gigio-desktop.8547.10 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454323.gigio-desktop.8547.10 new file mode 100644 index 0000000000000000000000000000000000000000..267455851b9c157e939d7a807a719e0e6c372cb5 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454323.gigio-desktop.8547.10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a0551a6fb5ff0a75289ed26b787b2a6e10d8110e10762b6a0df029b522af74b +size 7574 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454352.gigio-desktop.8547.11 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454352.gigio-desktop.8547.11 new file mode 100644 index 0000000000000000000000000000000000000000..14096ea5d6b493d64d68402db295376b551b2110 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454352.gigio-desktop.8547.11 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d6c6aa734de326e30b805d1bb66a45ac9b7fbdb7ac17356a4fe4810c02cfa0b +size 7573 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454382.gigio-desktop.8547.12 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454382.gigio-desktop.8547.12 new file mode 100644 index 0000000000000000000000000000000000000000..e299e15d8f8af917d21b9859c5d8c44b0c6d2d76 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454382.gigio-desktop.8547.12 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:625cc1d0a56d31d01902a8820dc8ea1067510b94dd5c96f950ab53879e563d12 +size 7575 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454411.gigio-desktop.8547.13 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454411.gigio-desktop.8547.13 new file mode 100644 index 0000000000000000000000000000000000000000..cca727515a0e4746ea108cf1c61b0c40d1af2e2f --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454411.gigio-desktop.8547.13 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb23f24fda1f61b8f10c13ac385b783d6c7091cfd504f8350e023d9cb146669a +size 7226 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454438.gigio-desktop.8547.14 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454438.gigio-desktop.8547.14 new file mode 100644 index 0000000000000000000000000000000000000000..331ac89f729c402c64e42afdeed52b39c9e7323c --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454438.gigio-desktop.8547.14 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0764b09e408c0778c133582445d343f73ab8ddea9f594f6599b0f0a2ab6f6f0 +size 6755 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454453.gigio-desktop.8547.15 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454453.gigio-desktop.8547.15 new file mode 100644 index 0000000000000000000000000000000000000000..b3a5763851626e237a0898e8c461bae0d3114f50 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454453.gigio-desktop.8547.15 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29c6abb056fa6aa2be1e3551b63eef98d78c10d60fd77ccbc2f683f3e4ba3179 +size 7227 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454480.gigio-desktop.8547.16 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454480.gigio-desktop.8547.16 new file mode 100644 index 0000000000000000000000000000000000000000..405773852ee8171240ab36a09884b3e8f7d7f3f7 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454480.gigio-desktop.8547.16 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:812de433878488d335a858a19e16b4d389008109fde17a1ab2f99017bc77320d +size 6754 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454495.gigio-desktop.8547.17 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454495.gigio-desktop.8547.17 new file mode 100644 index 0000000000000000000000000000000000000000..941fb95895227bb5ff07b68f6e17876b5de74a5b --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454495.gigio-desktop.8547.17 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f998875e5bf5de6c8f41d1d9729092ed7bc00af464dbca41f9565c391c394f +size 6755 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454509.gigio-desktop.8547.18 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454509.gigio-desktop.8547.18 new file mode 100644 index 0000000000000000000000000000000000000000..c1148b930d968102b9a9438da4863843ca0191f9 --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454509.gigio-desktop.8547.18 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a0d638215a3e18316b2448813cd416170668a89d02348809be1457b388b504 +size 6754 diff --git a/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454524.gigio-desktop.8547.19 b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454524.gigio-desktop.8547.19 new file mode 100644 index 0000000000000000000000000000000000000000..42b11798dd8bf4931689caa5fcb23c1f21361d7f --- /dev/null +++ b/runs/Jul08_17-54-06_gigio-desktop/events.out.tfevents.1720454524.gigio-desktop.8547.19 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:419a46bcde8076a407aa4c7d7edb6d186b46b1b58925bcc48c9275abcbc65ee2 +size 6755 diff --git a/runs/Jul09_09-30-50_gigio-desktop/events.out.tfevents.1720510279.gigio-desktop.3063.0 b/runs/Jul09_09-30-50_gigio-desktop/events.out.tfevents.1720510279.gigio-desktop.3063.0 new file mode 100644 index 0000000000000000000000000000000000000000..f38d0a569b81c1b0b33c51f9dd9704bd0321b231 --- /dev/null +++ b/runs/Jul09_09-30-50_gigio-desktop/events.out.tfevents.1720510279.gigio-desktop.3063.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a157f62144816ff9bcc812862567518610a5b2e2fe6ea5d5f81e5045c1ef69c +size 6282 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720510436.gigio-desktop.4223.0 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720510436.gigio-desktop.4223.0 new file mode 100644 index 0000000000000000000000000000000000000000..7af4e9131d019659caf5be81e78894b5be56deff --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720510436.gigio-desktop.4223.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e627ba93f95414cc9311e34720b7e7ae569a1f881c55fd45a651a87edcacf56a +size 9513 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720512128.gigio-desktop.4223.1 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720512128.gigio-desktop.4223.1 new file mode 100644 index 0000000000000000000000000000000000000000..8173c2d03756fb8a0517782f43b7383fde424577 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720512128.gigio-desktop.4223.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef4fc86eac95018124414ad3551e382efb62ebf88e1674dc38e8d61002e5279 +size 9513 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720513821.gigio-desktop.4223.2 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720513821.gigio-desktop.4223.2 new file mode 100644 index 0000000000000000000000000000000000000000..cf27695e94d094d8c4331360e2d85209cf522d14 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720513821.gigio-desktop.4223.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7288760909d71f6a4ccc7fa280a72995e5cce36bf4e64d6991b67e896814eb32 +size 12887 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720515600.gigio-desktop.4223.3 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720515600.gigio-desktop.4223.3 new file mode 100644 index 0000000000000000000000000000000000000000..df99ddee668bf2016d18f3fe2f438f5ca0b8f3f8 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720515600.gigio-desktop.4223.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:545ea76cf338f05aa32aa15e64139c71b951bc94398e8765626165ec67f0a8e0 +size 9513 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720517304.gigio-desktop.4223.4 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720517304.gigio-desktop.4223.4 new file mode 100644 index 0000000000000000000000000000000000000000..b7a85f183f52adac90586c607d811a5730eb7d04 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720517304.gigio-desktop.4223.4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f928ca5faff325bebd57a7333065e514d9f3afa711bd81ecfacf3351bc0685a2 +size 9514 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720519017.gigio-desktop.4223.5 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720519017.gigio-desktop.4223.5 new file mode 100644 index 0000000000000000000000000000000000000000..76a0b4535f9348a7fd768890d2f558c7681eee3b --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720519017.gigio-desktop.4223.5 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:903732540a1a8012103e802d8c300f28c99e7c6720a86857249cd7c5c34ca527 +size 6758 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720519151.gigio-desktop.4223.6 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720519151.gigio-desktop.4223.6 new file mode 100644 index 0000000000000000000000000000000000000000..a447859debdef667e35645fa791535fc0de86bd3 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720519151.gigio-desktop.4223.6 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed406831d60b3319621e8a797d394cb073eaa8aed5bcbd9c9fefe00edc74b45 +size 6759 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720519402.gigio-desktop.4223.7 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720519402.gigio-desktop.4223.7 new file mode 100644 index 0000000000000000000000000000000000000000..021432e24380e525d47e32a141652da10652f2c9 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720519402.gigio-desktop.4223.7 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dc5a6ab1b3ac74ff68973b7a1f62d1a3162f4a0da826062b0458ce0c20c60bb +size 10123 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720520439.gigio-desktop.4223.8 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720520439.gigio-desktop.4223.8 new file mode 100644 index 0000000000000000000000000000000000000000..70cdb75be71deee40d9b2c2927382e727baebe48 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720520439.gigio-desktop.4223.8 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43b8ec575e7eca23b9cbff2c8130cb0f4ea6820c6308c4ddf07288211bbd4806 +size 6756 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720520571.gigio-desktop.4223.9 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720520571.gigio-desktop.4223.9 new file mode 100644 index 0000000000000000000000000000000000000000..06d65988561393ea9a976597d477f433343a86c7 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720520571.gigio-desktop.4223.9 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aa1ed5c4dedd53333a46babe9794ba98c3b69aa1789bfa79d00a7822acf6e25 +size 6757 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720520822.gigio-desktop.4223.10 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720520822.gigio-desktop.4223.10 new file mode 100644 index 0000000000000000000000000000000000000000..f556097c82e0cd00f68a80cc30757cb509994269 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720520822.gigio-desktop.4223.10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e90ea1a1c95923d482c1ce37585d1a1d3931aca280825fb681f17618cc497d92 +size 8677 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720522033.gigio-desktop.4223.11 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720522033.gigio-desktop.4223.11 new file mode 100644 index 0000000000000000000000000000000000000000..f836f6e96349902daf2963dd73efc32439427678 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720522033.gigio-desktop.4223.11 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1204290e28a8d88c0085066e1d58c0f8b95eaaa5e559d946f70fdfdce33dfc1b +size 12888 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720523816.gigio-desktop.4223.12 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720523816.gigio-desktop.4223.12 new file mode 100644 index 0000000000000000000000000000000000000000..4a8678320fd7afa1a433733a43ff4c84e77bf3c7 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720523816.gigio-desktop.4223.12 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bc9f7c9be3ce70255edaca02a1551f3fd716e39cdea0edf98a89fec1541e769 +size 9160 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720524592.gigio-desktop.4223.13 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720524592.gigio-desktop.4223.13 new file mode 100644 index 0000000000000000000000000000000000000000..1b0f3423f02fc5e287094e73bc95c087ae811ed1 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720524592.gigio-desktop.4223.13 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a5fff8829a40f1b9f559c9a6628455deb5cfb1ac0c0ea5763389ec8737c5055 +size 6755 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720524722.gigio-desktop.4223.14 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720524722.gigio-desktop.4223.14 new file mode 100644 index 0000000000000000000000000000000000000000..c398818be09a0f2c41f090e0db7d91fc12fd67a9 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720524722.gigio-desktop.4223.14 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f2e953edcbdf9180a8768f8337d802a3a6bb8dd11ae3e2a9f1c909d8ca4c1c3 +size 12884 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720526510.gigio-desktop.4223.15 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720526510.gigio-desktop.4223.15 new file mode 100644 index 0000000000000000000000000000000000000000..4c1448480a062eea75d6cc9b67c4e29d7e7a4891 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720526510.gigio-desktop.4223.15 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69e3cbe0673ef9ececa4e78bfb3b01a9715e6f07590add283d365a7d1d925978 +size 9515 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720528202.gigio-desktop.4223.16 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720528202.gigio-desktop.4223.16 new file mode 100644 index 0000000000000000000000000000000000000000..58d096a47291d0209caa5e859dfa86c7ff72b476 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720528202.gigio-desktop.4223.16 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ff8ee1034b7157012a5dcb3d4933ea179c17315852eb533f8f6208e4817df5 +size 9514 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720529893.gigio-desktop.4223.17 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720529893.gigio-desktop.4223.17 new file mode 100644 index 0000000000000000000000000000000000000000..4a65a1791153b2ebe6247a01e2433bedfc89fa0b --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720529893.gigio-desktop.4223.17 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a30c54ce1a9c81e050ed1d9754bbce8d70c679c66058e22ff2d1b2917d12b3a0 +size 9512 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720531589.gigio-desktop.4223.18 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720531589.gigio-desktop.4223.18 new file mode 100644 index 0000000000000000000000000000000000000000..0ac11614bc3c51b396f8ffec77ffac02b466e87c --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720531589.gigio-desktop.4223.18 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc606ee0db6cab867a2362c7db276c9e90bbd86a2f71d6e7e630b64c2e3096bb +size 6760 diff --git a/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720531839.gigio-desktop.4223.19 b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720531839.gigio-desktop.4223.19 new file mode 100644 index 0000000000000000000000000000000000000000..303127fdfdf8924f83fb6b872a48dd5985295011 --- /dev/null +++ b/runs/Jul09_09-33-52_gigio-desktop/events.out.tfevents.1720531839.gigio-desktop.4223.19 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd6550454b878b7638a50fbe6a9d53bbe6b0a3eb86f9ba3096cee4caf5da623 +size 6758 diff --git a/runs/Jul10_10-05-45_gigio-desktop/events.out.tfevents.1720598774.gigio-desktop.4206.0 b/runs/Jul10_10-05-45_gigio-desktop/events.out.tfevents.1720598774.gigio-desktop.4206.0 new file mode 100644 index 0000000000000000000000000000000000000000..fc9e2a7589840636b4e04a64197266ca484b0720 --- /dev/null +++ b/runs/Jul10_10-05-45_gigio-desktop/events.out.tfevents.1720598774.gigio-desktop.4206.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ffddaad838e745a9907880b72277799dc792004c37233447207ba9b0c1a43aa +size 8529 diff --git a/training_args.bin b/training_args.bin index 02422eba38bfad72a4903381655b8c654a5a31a5..30b2bd8eba88dca184982a10456fa7a42345b62d 100644 --- a/training_args.bin +++ b/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4a113632c518d0626aa116ac777cfca5624f8782a691592ab1876cd7c59a7af3 +oid sha256:9eb30090886a1573f9430761bb091277503b7a72098a2385fa28f44f4d6f6e7e size 5240