End of training

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: openai/whisper-small
+model-index:
+- name: Whisper-small-new
+  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. -->
+
+# Whisper-small-new
+
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0162
+
+## 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: 0.001
+- train_batch_size: 6
+- eval_batch_size: 6
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 6.1628        | 1.0   | 137  | 4.2124          |
+| 2.7143        | 2.0   | 274  | 2.2921          |
+| 1.1388        | 3.0   | 411  | 0.8535          |
+| 0.4082        | 4.0   | 548  | 0.2754          |
+| 0.2126        | 5.0   | 685  | 0.1487          |
+| 0.1209        | 6.0   | 822  | 0.1083          |
+| 0.1082        | 7.0   | 959  | 0.0546          |
+| 0.0435        | 8.0   | 1096 | 0.0327          |
+| 0.0309        | 9.0   | 1233 | 0.0201          |
+| 0.0213        | 10.0  | 1370 | 0.0162          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

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-small",
+  "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
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f671fda1f01ac0e2456c682a47adfefd9f97c4d68b58b26fd888e95c8aa33246
+size 14176064

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "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
+}

trainer_state.json

@@ -0,0 +1,500 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1370,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18248175182481752,
+      "grad_norm": 3.480720043182373,
+      "learning_rate": 0.00044,
+      "loss": 4.161,
+      "step": 25
+    },
+    {
+      "epoch": 0.36496350364963503,
+      "grad_norm": 1.4096753597259521,
+      "learning_rate": 0.00094,
+      "loss": 1.0537,
+      "step": 50
+    },
+    {
+      "epoch": 0.5474452554744526,
+      "grad_norm": 2.793295383453369,
+      "learning_rate": 0.0009833333333333332,
+      "loss": 0.4546,
+      "step": 75
+    },
+    {
+      "epoch": 0.7299270072992701,
+      "grad_norm": 0.4571402370929718,
+      "learning_rate": 0.0009643939393939394,
+      "loss": 0.1519,
+      "step": 100
+    },
+    {
+      "epoch": 0.9124087591240876,
+      "grad_norm": 1.6245888471603394,
+      "learning_rate": 0.0009462121212121212,
+      "loss": 6.1628,
+      "step": 125
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.212439060211182,
+      "eval_runtime": 192.7878,
+      "eval_samples_per_second": 4.243,
+      "eval_steps_per_second": 0.711,
+      "step": 137
+    },
+    {
+      "epoch": 1.094890510948905,
+      "grad_norm": 0.5284515023231506,
+      "learning_rate": 0.0009272727272727273,
+      "loss": 4.8818,
+      "step": 150
+    },
+    {
+      "epoch": 1.2773722627737225,
+      "grad_norm": 0.5723586678504944,
+      "learning_rate": 0.0009083333333333334,
+      "loss": 3.4981,
+      "step": 175
+    },
+    {
+      "epoch": 1.4598540145985401,
+      "grad_norm": 0.4482167661190033,
+      "learning_rate": 0.0008893939393939394,
+      "loss": 3.3316,
+      "step": 200
+    },
+    {
+      "epoch": 1.6423357664233578,
+      "grad_norm": 0.5379208922386169,
+      "learning_rate": 0.0008704545454545455,
+      "loss": 3.1343,
+      "step": 225
+    },
+    {
+      "epoch": 1.8248175182481752,
+      "grad_norm": 2.225010395050049,
+      "learning_rate": 0.0008515151515151516,
+      "loss": 2.7143,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.292099714279175,
+      "eval_runtime": 196.2028,
+      "eval_samples_per_second": 4.169,
+      "eval_steps_per_second": 0.698,
+      "step": 274
+    },
+    {
+      "epoch": 2.0072992700729926,
+      "grad_norm": 0.8666009902954102,
+      "learning_rate": 0.0008325757575757576,
+      "loss": 2.438,
+      "step": 275
+    },
+    {
+      "epoch": 2.18978102189781,
+      "grad_norm": 1.0309600830078125,
+      "learning_rate": 0.0008136363636363636,
+      "loss": 2.1385,
+      "step": 300
+    },
+    {
+      "epoch": 2.372262773722628,
+      "grad_norm": 3.2585089206695557,
+      "learning_rate": 0.0007946969696969696,
+      "loss": 1.9635,
+      "step": 325
+    },
+    {
+      "epoch": 2.554744525547445,
+      "grad_norm": 1.6428176164627075,
+      "learning_rate": 0.0007757575757575758,
+      "loss": 1.7211,
+      "step": 350
+    },
+    {
+      "epoch": 2.7372262773722627,
+      "grad_norm": 2.730184316635132,
+      "learning_rate": 0.0007568181818181819,
+      "loss": 1.3848,
+      "step": 375
+    },
+    {
+      "epoch": 2.9197080291970803,
+      "grad_norm": 2.9515888690948486,
+      "learning_rate": 0.0007378787878787879,
+      "loss": 1.1388,
+      "step": 400
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8534712195396423,
+      "eval_runtime": 195.2055,
+      "eval_samples_per_second": 4.19,
+      "eval_steps_per_second": 0.702,
+      "step": 411
+    },
+    {
+      "epoch": 3.102189781021898,
+      "grad_norm": 3.407141923904419,
+      "learning_rate": 0.0007189393939393941,
+      "loss": 0.8781,
+      "step": 425
+    },
+    {
+      "epoch": 3.2846715328467155,
+      "grad_norm": 2.300389528274536,
+      "learning_rate": 0.0007,
+      "loss": 0.7192,
+      "step": 450
+    },
+    {
+      "epoch": 3.4671532846715327,
+      "grad_norm": 1.6451431512832642,
+      "learning_rate": 0.000681060606060606,
+      "loss": 0.6457,
+      "step": 475
+    },
+    {
+      "epoch": 3.6496350364963503,
+      "grad_norm": 2.6580169200897217,
+      "learning_rate": 0.0006621212121212121,
+      "loss": 0.4801,
+      "step": 500
+    },
+    {
+      "epoch": 3.832116788321168,
+      "grad_norm": 2.7876107692718506,
+      "learning_rate": 0.0006431818181818182,
+      "loss": 0.4082,
+      "step": 525
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.27536100149154663,
+      "eval_runtime": 193.3916,
+      "eval_samples_per_second": 4.23,
+      "eval_steps_per_second": 0.708,
+      "step": 548
+    },
+    {
+      "epoch": 4.014598540145985,
+      "grad_norm": 0.8029674887657166,
+      "learning_rate": 0.0006242424242424243,
+      "loss": 0.335,
+      "step": 550
+    },
+    {
+      "epoch": 4.197080291970803,
+      "grad_norm": 1.664339303970337,
+      "learning_rate": 0.0006053030303030303,
+      "loss": 0.2257,
+      "step": 575
+    },
+    {
+      "epoch": 4.37956204379562,
+      "grad_norm": 1.4657175540924072,
+      "learning_rate": 0.0005863636363636363,
+      "loss": 0.2869,
+      "step": 600
+    },
+    {
+      "epoch": 4.562043795620438,
+      "grad_norm": 1.3024441003799438,
+      "learning_rate": 0.0005674242424242424,
+      "loss": 0.2747,
+      "step": 625
+    },
+    {
+      "epoch": 4.744525547445256,
+      "grad_norm": 0.9062749743461609,
+      "learning_rate": 0.0005484848484848485,
+      "loss": 0.1877,
+      "step": 650
+    },
+    {
+      "epoch": 4.927007299270073,
+      "grad_norm": 0.833874523639679,
+      "learning_rate": 0.0005295454545454545,
+      "loss": 0.2126,
+      "step": 675
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.14872248470783234,
+      "eval_runtime": 197.8887,
+      "eval_samples_per_second": 4.134,
+      "eval_steps_per_second": 0.692,
+      "step": 685
+    },
+    {
+      "epoch": 5.109489051094891,
+      "grad_norm": 0.9996502995491028,
+      "learning_rate": 0.0005106060606060607,
+      "loss": 0.1559,
+      "step": 700
+    },
+    {
+      "epoch": 5.291970802919708,
+      "grad_norm": 0.6231667399406433,
+      "learning_rate": 0.0004916666666666666,
+      "loss": 0.1486,
+      "step": 725
+    },
+    {
+      "epoch": 5.474452554744525,
+      "grad_norm": 0.5377147197723389,
+      "learning_rate": 0.0004727272727272727,
+      "loss": 0.1135,
+      "step": 750
+    },
+    {
+      "epoch": 5.656934306569343,
+      "grad_norm": 0.24335509538650513,
+      "learning_rate": 0.0004537878787878788,
+      "loss": 0.137,
+      "step": 775
+    },
+    {
+      "epoch": 5.839416058394161,
+      "grad_norm": 1.0016026496887207,
+      "learning_rate": 0.00043484848484848487,
+      "loss": 0.1209,
+      "step": 800
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.10833244770765305,
+      "eval_runtime": 195.5746,
+      "eval_samples_per_second": 4.183,
+      "eval_steps_per_second": 0.701,
+      "step": 822
+    },
+    {
+      "epoch": 6.021897810218978,
+      "grad_norm": 1.0397971868515015,
+      "learning_rate": 0.0004159090909090909,
+      "loss": 0.1496,
+      "step": 825
+    },
+    {
+      "epoch": 6.204379562043796,
+      "grad_norm": 1.5983672142028809,
+      "learning_rate": 0.00039696969696969696,
+      "loss": 0.1017,
+      "step": 850
+    },
+    {
+      "epoch": 6.386861313868613,
+      "grad_norm": 0.4575522840023041,
+      "learning_rate": 0.00037803030303030306,
+      "loss": 0.0895,
+      "step": 875
+    },
+    {
+      "epoch": 6.569343065693431,
+      "grad_norm": 0.6511216163635254,
+      "learning_rate": 0.00035909090909090906,
+      "loss": 0.0666,
+      "step": 900
+    },
+    {
+      "epoch": 6.751824817518248,
+      "grad_norm": 1.270704984664917,
+      "learning_rate": 0.00034015151515151516,
+      "loss": 0.0831,
+      "step": 925
+    },
+    {
+      "epoch": 6.934306569343065,
+      "grad_norm": 0.3851993978023529,
+      "learning_rate": 0.00032121212121212126,
+      "loss": 0.1082,
+      "step": 950
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.05455175042152405,
+      "eval_runtime": 200.4227,
+      "eval_samples_per_second": 4.081,
+      "eval_steps_per_second": 0.684,
+      "step": 959
+    },
+    {
+      "epoch": 7.116788321167883,
+      "grad_norm": 0.2679482698440552,
+      "learning_rate": 0.00030227272727272725,
+      "loss": 0.0586,
+      "step": 975
+    },
+    {
+      "epoch": 7.299270072992701,
+      "grad_norm": 0.44625118374824524,
+      "learning_rate": 0.00028333333333333335,
+      "loss": 0.0558,
+      "step": 1000
+    },
+    {
+      "epoch": 7.481751824817518,
+      "grad_norm": 0.4908747375011444,
+      "learning_rate": 0.0002643939393939394,
+      "loss": 0.0711,
+      "step": 1025
+    },
+    {
+      "epoch": 7.664233576642336,
+      "grad_norm": 1.205810785293579,
+      "learning_rate": 0.00024545454545454545,
+      "loss": 0.0573,
+      "step": 1050
+    },
+    {
+      "epoch": 7.846715328467154,
+      "grad_norm": 0.07598499953746796,
+      "learning_rate": 0.0002265151515151515,
+      "loss": 0.0435,
+      "step": 1075
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.03274066373705864,
+      "eval_runtime": 202.8108,
+      "eval_samples_per_second": 4.033,
+      "eval_steps_per_second": 0.676,
+      "step": 1096
+    },
+    {
+      "epoch": 8.02919708029197,
+      "grad_norm": 0.4313261806964874,
+      "learning_rate": 0.0002075757575757576,
+      "loss": 0.0452,
+      "step": 1100
+    },
+    {
+      "epoch": 8.211678832116789,
+      "grad_norm": 0.25643861293792725,
+      "learning_rate": 0.00018863636363636364,
+      "loss": 0.0446,
+      "step": 1125
+    },
+    {
+      "epoch": 8.394160583941606,
+      "grad_norm": 0.35274460911750793,
+      "learning_rate": 0.00016969696969696972,
+      "loss": 0.0423,
+      "step": 1150
+    },
+    {
+      "epoch": 8.576642335766424,
+      "grad_norm": 0.08310751616954803,
+      "learning_rate": 0.00015075757575757576,
+      "loss": 0.0272,
+      "step": 1175
+    },
+    {
+      "epoch": 8.75912408759124,
+      "grad_norm": 1.2015907764434814,
+      "learning_rate": 0.0001318181818181818,
+      "loss": 0.0274,
+      "step": 1200
+    },
+    {
+      "epoch": 8.941605839416058,
+      "grad_norm": 0.3477329611778259,
+      "learning_rate": 0.00011287878787878789,
+      "loss": 0.0309,
+      "step": 1225
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.02009008266031742,
+      "eval_runtime": 200.6591,
+      "eval_samples_per_second": 4.077,
+      "eval_steps_per_second": 0.683,
+      "step": 1233
+    },
+    {
+      "epoch": 9.124087591240876,
+      "grad_norm": 0.37782296538352966,
+      "learning_rate": 9.393939393939393e-05,
+      "loss": 0.027,
+      "step": 1250
+    },
+    {
+      "epoch": 9.306569343065693,
+      "grad_norm": 0.07126203179359436,
+      "learning_rate": 7.5e-05,
+      "loss": 0.0148,
+      "step": 1275
+    },
+    {
+      "epoch": 9.489051094890511,
+      "grad_norm": 0.0341663658618927,
+      "learning_rate": 5.606060606060606e-05,
+      "loss": 0.0187,
+      "step": 1300
+    },
+    {
+      "epoch": 9.671532846715328,
+      "grad_norm": 0.2040582299232483,
+      "learning_rate": 3.712121212121213e-05,
+      "loss": 0.0234,
+      "step": 1325
+    },
+    {
+      "epoch": 9.854014598540147,
+      "grad_norm": 0.3192838430404663,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.0213,
+      "step": 1350
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.016194986179471016,
+      "eval_runtime": 199.5522,
+      "eval_samples_per_second": 4.099,
+      "eval_steps_per_second": 0.687,
+      "step": 1370
+    },
+    {
+      "epoch": 10.0,
+      "step": 1370,
+      "total_flos": 2.4023145037824e+18,
+      "train_loss": 0.8555449325890436,
+      "train_runtime": 4862.7206,
+      "train_samples_per_second": 1.682,
+      "train_steps_per_second": 0.282
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1370,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 2.4023145037824e+18,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eaee302738ca585efa41acdcafac3f902174528001161c8201042bdd30b24c4
+size 5304