Model save

README.md

@@ -0,0 +1,74 @@
+---
+library_name: peft
+license: mit
+base_model: openai/whisper-large-v3-turbo
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: v3-turbo-cv17-telephonic-lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# v3-turbo-cv17-telephonic-lora
+
+This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1411
+- Wer: 14.2090
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- training_steps: 5000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.454         | 0.1138 | 500  | 0.1633          | 15.3845 |
+| 0.1463        | 0.2276 | 1000 | 0.1525          | 14.9965 |
+| 0.1393        | 0.3414 | 1500 | 0.1482          | 14.7002 |
+| 0.1344        | 0.4552 | 2000 | 0.1466          | 14.4383 |
+| 0.1305        | 0.5690 | 2500 | 0.1442          | 14.3084 |
+| 0.1235        | 0.6828 | 3000 | 0.1427          | 14.2510 |
+| 0.129         | 0.7966 | 3500 | 0.1418          | 14.2434 |
+| 0.1259        | 0.9104 | 4000 | 0.1416          | 14.1765 |
+| 0.1169        | 1.0241 | 4500 | 0.1412          | 14.2185 |
+| 0.1103        | 1.1379 | 5000 | 0.1411          | 14.2090 |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.48.3
+- Pytorch 2.4.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.21.0

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afc092bd82bf74726cf958a43b3bfc8ac61fa887985e67b56ad49fac7404f85b
+oid sha256:cb17d2835145e2dd53e0457281192b0d0b2cc793b78afdc87b3739679426d27f
 size 111475752

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.1379310344827587,
+    "total_flos": 7.07561145335808e+19,
+    "train_loss": 0.1610086441040039,
+    "train_runtime": 59312.8298,
+    "train_samples_per_second": 0.674,
+    "train_steps_per_second": 0.084
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.1379310344827587,
+    "total_flos": 7.07561145335808e+19,
+    "train_loss": 0.1610086441040039,
+    "train_runtime": 59312.8298,
+    "train_samples_per_second": 0.674,
+    "train_steps_per_second": 0.084
+}

trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_metric": 14.176494199048149,
+  "best_model_checkpoint": "./v3-turbo-cv17-telephonic-lora/v3-turbo-cv17-telephonic-lora/checkpoint-4000",
+  "epoch": 1.1379310344827587,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11380448389666553,
+      "grad_norm": 1.8799397945404053,
+      "learning_rate": 9.757220437383345e-06,
+      "loss": 0.454,
+      "step": 500
+    },
+    {
+      "epoch": 0.11380448389666553,
+      "eval_loss": 0.16326197981834412,
+      "eval_runtime": 4750.4498,
+      "eval_samples_per_second": 2.37,
+      "eval_steps_per_second": 0.296,
+      "eval_wer": 15.384468357575642,
+      "step": 500
+    },
+    {
+      "epoch": 0.22760896779333106,
+      "grad_norm": 2.3445775508880615,
+      "learning_rate": 9.050617527877911e-06,
+      "loss": 0.1463,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22760896779333106,
+      "eval_loss": 0.1524566262960434,
+      "eval_runtime": 4747.2698,
+      "eval_samples_per_second": 2.371,
+      "eval_steps_per_second": 0.297,
+      "eval_wer": 14.996463999694184,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3414134516899966,
+      "grad_norm": 3.6666531562805176,
+      "learning_rate": 7.94908337621646e-06,
+      "loss": 0.1393,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3414134516899966,
+      "eval_loss": 0.148152157664299,
+      "eval_runtime": 4738.8967,
+      "eval_samples_per_second": 2.376,
+      "eval_steps_per_second": 0.297,
+      "eval_wer": 14.700204514612283,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4552179355866621,
+      "grad_norm": 2.111747980117798,
+      "learning_rate": 6.557031408153642e-06,
+      "loss": 0.1344,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4552179355866621,
+      "eval_loss": 0.14661043882369995,
+      "eval_runtime": 4746.3362,
+      "eval_samples_per_second": 2.372,
+      "eval_steps_per_second": 0.297,
+      "eval_wer": 14.438349356830216,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5690224194833277,
+      "grad_norm": 1.8398709297180176,
+      "learning_rate": 5.0125663573850204e-06,
+      "loss": 0.1305,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5690224194833277,
+      "eval_loss": 0.14422065019607544,
+      "eval_runtime": 4749.083,
+      "eval_samples_per_second": 2.371,
+      "eval_steps_per_second": 0.296,
+      "eval_wer": 14.30837745369751,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6828269033799932,
+      "grad_norm": 0.9027289152145386,
+      "learning_rate": 3.4668712240005912e-06,
+      "loss": 0.1235,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6828269033799932,
+      "eval_loss": 0.14272235333919525,
+      "eval_runtime": 4749.4242,
+      "eval_samples_per_second": 2.37,
+      "eval_steps_per_second": 0.296,
+      "eval_wer": 14.251036908197786,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7966313872766587,
+      "grad_norm": 1.789233684539795,
+      "learning_rate": 2.0737962298724513e-06,
+      "loss": 0.129,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7966313872766587,
+      "eval_loss": 0.14178909361362457,
+      "eval_runtime": 4763.1612,
+      "eval_samples_per_second": 2.364,
+      "eval_steps_per_second": 0.296,
+      "eval_wer": 14.243391502131155,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9104358711733243,
+      "grad_norm": 2.0484585762023926,
+      "learning_rate": 9.641678837679985e-07,
+      "loss": 0.1259,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9104358711733243,
+      "eval_loss": 0.14161205291748047,
+      "eval_runtime": 4761.4623,
+      "eval_samples_per_second": 2.364,
+      "eval_steps_per_second": 0.296,
+      "eval_wer": 14.176494199048149,
+      "step": 4000
+    },
+    {
+      "epoch": 1.024126550586093,
+      "grad_norm": 2.5858395099639893,
+      "learning_rate": 2.49594904496141e-07,
+      "loss": 0.1169,
+      "step": 4500
+    },
+    {
+      "epoch": 1.024126550586093,
+      "eval_loss": 0.14117974042892456,
+      "eval_runtime": 4761.2429,
+      "eval_samples_per_second": 2.365,
+      "eval_steps_per_second": 0.296,
+      "eval_wer": 14.21854393241461,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 2.0550997257232666,
+      "learning_rate": 2.467399070893439e-11,
+      "loss": 0.1103,
+      "step": 5000
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "eval_loss": 0.1410815715789795,
+      "eval_runtime": 4761.6981,
+      "eval_samples_per_second": 2.364,
+      "eval_steps_per_second": 0.296,
+      "eval_wer": 14.208987174831321,
+      "step": 5000
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "step": 5000,
+      "total_flos": 7.07561145335808e+19,
+      "train_loss": 0.1610086441040039,
+      "train_runtime": 59312.8298,
+      "train_samples_per_second": 0.674,
+      "train_steps_per_second": 0.084
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.07561145335808e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}