End of training

last-checkpoint/config.json

@@ -1,42 +0,0 @@
-{
-  "_name_or_path": "openai/whisper-small",
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "architectures": [
-    "WhisperForConditionalGeneration"
-  ],
-  "attention_dropout": 0.0,
-  "begin_suppress_tokens": [
-    220,
-    50257
-  ],
-  "bos_token_id": 50257,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
-  "decoder_start_token_id": 50258,
-  "dropout": 0.0,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
-  "eos_token_id": 50257,
-  "forced_decoder_ids": null,
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "max_length": 448,
-  "max_source_positions": 1500,
-  "max_target_positions": 448,
-  "model_type": "whisper",
-  "num_hidden_layers": 12,
-  "num_mel_bins": 80,
-  "pad_token_id": 50257,
-  "scale_embedding": false,
-  "suppress_tokens": [],
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
-  "use_cache": true,
-  "vocab_size": 51865
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2341c3e08addcee1f80703cf5ae5b9bb54f31defa980ba4e189bbc5fc5570cd6
-size 734250209

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b71d0c8a36c0a62ee68efda2abb716f422fa634d3114074d6fab2fb32d141546
-size 967102601

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eb642eeaf18fedb79ccd61a8c464d040ca5f6dc4a25be7adb1fa64c2fabdad73
-size 14575

last-checkpoint/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ee16356ea91477394f418f2b87beadf6f49ec7eb5382c9d0070098ebb7d494dc
-size 557

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aa5643ea4489d64078264ab922c2c4f3bde3f465fe865754732347a5a8c21ba8
-size 627

last-checkpoint/trainer_state.json

@@ -1,352 +0,0 @@
-{
-  "best_metric": 26.028020838601996,
-  "best_model_checkpoint": "codefactory4791/whisper-small-medicalv3/checkpoint-8000",
-  "epoch": 20.408163265306122,
-  "global_step": 8000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.64,
-      "learning_rate": 4.92e-06,
-      "loss": 1.5334,
-      "step": 250
-    },
-    {
-      "epoch": 1.28,
-      "learning_rate": 9.920000000000002e-06,
-      "loss": 0.5352,
-      "step": 500
-    },
-    {
-      "epoch": 1.28,
-      "eval_loss": 0.4770798087120056,
-      "eval_runtime": 342.0388,
-      "eval_samples_per_second": 4.032,
-      "eval_steps_per_second": 0.129,
-      "eval_wer": 51.11526983966416,
-      "step": 500
-    },
-    {
-      "epoch": 1.91,
-      "learning_rate": 9.672e-06,
-      "loss": 0.4987,
-      "step": 750
-    },
-    {
-      "epoch": 2.55,
-      "learning_rate": 9.338666666666667e-06,
-      "loss": 0.418,
-      "step": 1000
-    },
-    {
-      "epoch": 2.55,
-      "eval_loss": 0.5147032141685486,
-      "eval_runtime": 309.2513,
-      "eval_samples_per_second": 4.459,
-      "eval_steps_per_second": 0.142,
-      "eval_wer": 30.79257498356178,
-      "step": 1000
-    },
-    {
-      "epoch": 3.19,
-      "learning_rate": 9.008e-06,
-      "loss": 0.3823,
-      "step": 1250
-    },
-    {
-      "epoch": 3.83,
-      "learning_rate": 8.674666666666668e-06,
-      "loss": 0.334,
-      "step": 1500
-    },
-    {
-      "epoch": 3.83,
-      "eval_loss": 0.5190795063972473,
-      "eval_runtime": 302.0972,
-      "eval_samples_per_second": 4.565,
-      "eval_steps_per_second": 0.146,
-      "eval_wer": 26.928329371301402,
-      "step": 1500
-    },
-    {
-      "epoch": 4.46,
-      "learning_rate": 8.341333333333334e-06,
-      "loss": 0.258,
-      "step": 1750
-    },
-    {
-      "epoch": 5.1,
-      "learning_rate": 8.008e-06,
-      "loss": 0.2341,
-      "step": 2000
-    },
-    {
-      "epoch": 5.1,
-      "eval_loss": 0.5760442018508911,
-      "eval_runtime": 307.2181,
-      "eval_samples_per_second": 4.489,
-      "eval_steps_per_second": 0.143,
-      "eval_wer": 27.874159121946285,
-      "step": 2000
-    },
-    {
-      "epoch": 5.74,
-      "learning_rate": 7.674666666666666e-06,
-      "loss": 0.1805,
-      "step": 2250
-    },
-    {
-      "epoch": 6.38,
-      "learning_rate": 7.341333333333334e-06,
-      "loss": 0.142,
-      "step": 2500
-    },
-    {
-      "epoch": 6.38,
-      "eval_loss": 0.6293530464172363,
-      "eval_runtime": 317.5809,
-      "eval_samples_per_second": 4.342,
-      "eval_steps_per_second": 0.139,
-      "eval_wer": 30.038945930908906,
-      "step": 2500
-    },
-    {
-      "epoch": 7.02,
-      "learning_rate": 7.0080000000000005e-06,
-      "loss": 0.1268,
-      "step": 2750
-    },
-    {
-      "epoch": 7.65,
-      "learning_rate": 6.674666666666667e-06,
-      "loss": 0.085,
-      "step": 3000
-    },
-    {
-      "epoch": 7.65,
-      "eval_loss": 0.6510938405990601,
-      "eval_runtime": 311.9788,
-      "eval_samples_per_second": 4.42,
-      "eval_steps_per_second": 0.141,
-      "eval_wer": 30.013656365383646,
-      "step": 3000
-    },
-    {
-      "epoch": 8.29,
-      "learning_rate": 6.341333333333334e-06,
-      "loss": 0.0763,
-      "step": 3250
-    },
-    {
-      "epoch": 8.93,
-      "learning_rate": 6.008000000000001e-06,
-      "loss": 0.068,
-      "step": 3500
-    },
-    {
-      "epoch": 8.93,
-      "eval_loss": 0.6710622906684875,
-      "eval_runtime": 305.9908,
-      "eval_samples_per_second": 4.507,
-      "eval_steps_per_second": 0.144,
-      "eval_wer": 29.062768701633708,
-      "step": 3500
-    },
-    {
-      "epoch": 9.57,
-      "learning_rate": 5.6746666666666675e-06,
-      "loss": 0.0495,
-      "step": 3750
-    },
-    {
-      "epoch": 10.2,
-      "learning_rate": 5.341333333333334e-06,
-      "loss": 0.0439,
-      "step": 4000
-    },
-    {
-      "epoch": 10.2,
-      "eval_loss": 0.7179045677185059,
-      "eval_runtime": 301.3864,
-      "eval_samples_per_second": 4.576,
-      "eval_steps_per_second": 0.146,
-      "eval_wer": 28.395124171766728,
-      "step": 4000
-    },
-    {
-      "epoch": 10.84,
-      "learning_rate": 5.008000000000001e-06,
-      "loss": 0.0382,
-      "step": 4250
-    },
-    {
-      "epoch": 11.48,
-      "learning_rate": 4.674666666666667e-06,
-      "loss": 0.0305,
-      "step": 4500
-    },
-    {
-      "epoch": 11.48,
-      "eval_loss": 0.7301719188690186,
-      "eval_runtime": 305.5767,
-      "eval_samples_per_second": 4.513,
-      "eval_steps_per_second": 0.144,
-      "eval_wer": 28.632846087704213,
-      "step": 4500
-    },
-    {
-      "epoch": 12.12,
-      "learning_rate": 4.341333333333334e-06,
-      "loss": 0.0276,
-      "step": 4750
-    },
-    {
-      "epoch": 12.76,
-      "learning_rate": 4.008e-06,
-      "loss": 0.0227,
-      "step": 5000
-    },
-    {
-      "epoch": 12.76,
-      "eval_loss": 0.7424771189689636,
-      "eval_runtime": 303.4778,
-      "eval_samples_per_second": 4.544,
-      "eval_steps_per_second": 0.145,
-      "eval_wer": 26.50852258358201,
-      "step": 5000
-    },
-    {
-      "epoch": 13.39,
-      "learning_rate": 3.6746666666666667e-06,
-      "loss": 0.0198,
-      "step": 5250
-    },
-    {
-      "epoch": 14.03,
-      "learning_rate": 3.3413333333333335e-06,
-      "loss": 0.0178,
-      "step": 5500
-    },
-    {
-      "epoch": 14.03,
-      "eval_loss": 0.7501226663589478,
-      "eval_runtime": 303.3747,
-      "eval_samples_per_second": 4.546,
-      "eval_steps_per_second": 0.145,
-      "eval_wer": 28.55697739112842,
-      "step": 5500
-    },
-    {
-      "epoch": 14.67,
-      "learning_rate": 3.0080000000000003e-06,
-      "loss": 0.0146,
-      "step": 5750
-    },
-    {
-      "epoch": 15.31,
-      "learning_rate": 2.674666666666667e-06,
-      "loss": 0.0128,
-      "step": 6000
-    },
-    {
-      "epoch": 15.31,
-      "eval_loss": 0.7591447234153748,
-      "eval_runtime": 300.021,
-      "eval_samples_per_second": 4.596,
-      "eval_steps_per_second": 0.147,
-      "eval_wer": 26.76647615193971,
-      "step": 6000
-    },
-    {
-      "epoch": 15.94,
-      "learning_rate": 2.3413333333333333e-06,
-      "loss": 0.011,
-      "step": 6250
-    },
-    {
-      "epoch": 16.58,
-      "learning_rate": 2.008e-06,
-      "loss": 0.0088,
-      "step": 6500
-    },
-    {
-      "epoch": 16.58,
-      "eval_loss": 0.7742175459861755,
-      "eval_runtime": 304.3909,
-      "eval_samples_per_second": 4.53,
-      "eval_steps_per_second": 0.145,
-      "eval_wer": 27.064893025137827,
-      "step": 6500
-    },
-    {
-      "epoch": 17.22,
-      "learning_rate": 1.6746666666666668e-06,
-      "loss": 0.0076,
-      "step": 6750
-    },
-    {
-      "epoch": 17.86,
-      "learning_rate": 1.3413333333333334e-06,
-      "loss": 0.0062,
-      "step": 7000
-    },
-    {
-      "epoch": 17.86,
-      "eval_loss": 0.8007826805114746,
-      "eval_runtime": 300.4307,
-      "eval_samples_per_second": 4.59,
-      "eval_steps_per_second": 0.146,
-      "eval_wer": 26.199989884173792,
-      "step": 7000
-    },
-    {
-      "epoch": 18.49,
-      "learning_rate": 1.0080000000000001e-06,
-      "loss": 0.0048,
-      "step": 7250
-    },
-    {
-      "epoch": 19.13,
-      "learning_rate": 6.746666666666667e-07,
-      "loss": 0.0034,
-      "step": 7500
-    },
-    {
-      "epoch": 19.13,
-      "eval_loss": 0.8073320388793945,
-      "eval_runtime": 306.8927,
-      "eval_samples_per_second": 4.493,
-      "eval_steps_per_second": 0.143,
-      "eval_wer": 26.776591978149817,
-      "step": 7500
-    },
-    {
-      "epoch": 19.77,
-      "learning_rate": 3.4133333333333337e-07,
-      "loss": 0.0029,
-      "step": 7750
-    },
-    {
-      "epoch": 20.41,
-      "learning_rate": 8e-09,
-      "loss": 0.0015,
-      "step": 8000
-    },
-    {
-      "epoch": 20.41,
-      "eval_loss": 0.8103999495506287,
-      "eval_runtime": 303.3592,
-      "eval_samples_per_second": 4.546,
-      "eval_steps_per_second": 0.145,
-      "eval_wer": 26.028020838601996,
-      "step": 8000
-    }
-  ],
-  "max_steps": 8000,
-  "num_train_epochs": 21,
-  "total_flos": 1.47495998103552e+20,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5b9df3254c5b6427a467145f75c1dd9f58d63e9b7c39c8b3fb93d298e6c2d612
-size 3643