End of training

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3da27ee8a8a8ab39333e019e5a97ab357d2ea402c9d024977b22fdd3d65cd66
+oid sha256:7e836508ba6cc11e70f41aaed259e28d251cbfcb4c5a5b7978e2dc4d5f082d6d
 size 62969640

run-0/checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openai/whisper-large-v3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.2.dev0

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
+}

run-0/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24fec58d8c223f56fc9c03bf13d6251479405d0f322305deb87f71554401b646
+size 62969640

run-0/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cbab46823b18f040948f161ef1b3f67a38c0aed0d36e6d8921022298dc07678
+size 126151570

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
+}

run-0/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610f67e3ef2a38bc4d059bf16b5476de440640d0cf679700dfa9d3a6aa152c59
+size 14244

run-0/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3553622cafc378ebbc0729e6ab9e744631a120f1792c9359ebdf479fa218b0
+size 1064

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
+  }
+}

run-0/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51dd06c8f8e2f8b00a912118364d06f67f1f5a631534d6cc03d23bfb515a9b22
+size 5240

run-1/checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openai/whisper-large-v3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.2.dev0

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
+}

run-1/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:301ecb046fd37114d45719f410fb2d4707317c97f15b99227fbcf9de9c2ff2a4
+size 62969640

run-1/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7f0647119995372d44a8188e13a108e3ef5d9a523007d03b3ae8146f183d7d
+size 126151570

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
+}

run-1/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610f67e3ef2a38bc4d059bf16b5476de440640d0cf679700dfa9d3a6aa152c59
+size 14244

run-1/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:697be74c5751a48948b5062099f3c0e459b59442bbc7d6efa5c14f9a1c356fc2
+size 1064

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
+  }
+}

run-1/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586b5e4b6f0b63d98f1fb72f63d9cfa27c3f5271d96663ef93dac3b215590cac
+size 5240

run-11/checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openai/whisper-large-v3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.2.dev0

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
+}

run-11/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc1578b5c1ed9b672936f479c98346886397fe5bb539e468cc79bac92327f5b3
+size 62969640

run-11/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e3151830d547370b456265c4be2a67e395b2100069af1aa9fb4418c89be29e
+size 126151570

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
+}

run-11/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8ee737576623fd1565b4ad626caaadf9a95e0f8cbaa53304cbd8316b784fc7
+size 14244

run-11/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a9ac6f5a41063d009620aaf578bb32960c6c36ab869fa1af8b00a00116fd422
+size 1064

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
+  }
+}

run-11/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7daea9ee3a72c1f0ccde9bdbb90b3fc2a862ce798a504a18fb3cd0854f2461
+size 5240

run-14/checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openai/whisper-large-v3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.2.dev0

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
+}

run-14/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65753749f9dec960bf0e91bb6d44e92354ee377b13564af56cf911c6ed0451ae
+size 62969640

run-14/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205be8da36802a453b8ccc171f51cbcb8d46c31f700c2dee5c6a1f1d05b86a66
+size 126151570

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
+}

run-14/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8ee737576623fd1565b4ad626caaadf9a95e0f8cbaa53304cbd8316b784fc7
+size 14244

run-14/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d125eaa094e272a98c53c93763667ee1b063b8df0becf7b73d774466b90f5ca8
+size 1064

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
+  }
+}

run-14/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ffb4ecb13597b62de8ca87970646438e1a5e0711c023ad7845f440752d9a66
+size 5240

run-2/checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openai/whisper-large-v3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.2.dev0

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
+}

run-2/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7579f8b5f03d1ad5d26d88649c690729bd42a41c96b79e0709277ff6fd0447
+size 62969640

run-2/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b1730bf12097dfa3d8ef0399635edc289a66c56dd4334f7115cc044e1bee76
+size 126151570

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
+}

run-2/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea3c5a2f00688c8f2d21b62d2c759f3e10550fb6cd1104d2317252f3df05792
+size 14244

run-2/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a75ba99085d46a7ab302dd0b2fa0081115e6f095fdc524727c48f4ce2f7bbb
+size 1064

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
+  }
+}

run-2/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f85248d48b74fd5496584a4c64687155d035a3e8ea717f3345e58d241e2dd13
+size 5240

run-2/checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: openai/whisper-large-v3
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.2.dev0

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
+}

run-2/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c0ff3e26a63daef37b7245cfc1182cc3a7acc128bb743fa4c3c349b9179b6a
+size 62969640