Upload 6 files

config.json

@@ -0,0 +1,42 @@
+{
+  "_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": "4.25.0.dev0",
+  "use_cache": true,
+  "vocab_size": 51865
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6611253998cc959ddb31036fe4e0ed20492e5b7ce59fffd1b4b575fb5cea46c
+size 14439

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9bc264f504b5bcb120a9af75ccf34ba79a4054a7a813df2af977cf195b4b966
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07cec8c6b3bdc76ab2acc524feadb1af272e065bfb398261482393d0ae89702
+size 623

trainer_state.json

@@ -0,0 +1,265 @@
+{
+  "best_metric": 30.343239390284023,
+  "best_model_checkpoint": "./whisper-small-vi/checkpoint-1000",
+  "epoch": 5.747126436781609,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 5.3288,
+      "step": 25
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 4.0043,
+      "step": 50
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 2.7924,
+      "step": 75
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 1.6418,
+      "step": 100
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.0731,
+      "step": 125
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.9e-06,
+      "loss": 0.917,
+      "step": 150
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.827,
+      "step": 175
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.7365,
+      "step": 200
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 4.4e-06,
+      "loss": 0.6354,
+      "step": 225
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.5332,
+      "step": 250
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.400000000000001e-06,
+      "loss": 0.4384,
+      "step": 275
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 5.9e-06,
+      "loss": 0.2393,
+      "step": 300
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.2146,
+      "step": 325
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 6.9e-06,
+      "loss": 0.2229,
+      "step": 350
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 7.4e-06,
+      "loss": 0.1371,
+      "step": 375
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 7.9e-06,
+      "loss": 0.134,
+      "step": 400
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.1392,
+      "step": 425
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 8.900000000000001e-06,
+      "loss": 0.1468,
+      "step": 450
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 9.4e-06,
+      "loss": 0.1354,
+      "step": 475
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 9.9e-06,
+      "loss": 0.1369,
+      "step": 500
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 9.920000000000002e-06,
+      "loss": 0.1363,
+      "step": 525
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 9.820000000000001e-06,
+      "loss": 0.0728,
+      "step": 550
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 9.72e-06,
+      "loss": 0.0697,
+      "step": 575
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 9.620000000000001e-06,
+      "loss": 0.0744,
+      "step": 600
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 9.52e-06,
+      "loss": 0.0686,
+      "step": 625
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 9.42e-06,
+      "loss": 0.0842,
+      "step": 650
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 9.32e-06,
+      "loss": 0.069,
+      "step": 675
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 9.220000000000002e-06,
+      "loss": 0.0732,
+      "step": 700
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 9.12e-06,
+      "loss": 0.0416,
+      "step": 725
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 9.020000000000002e-06,
+      "loss": 0.0425,
+      "step": 750
+    },
+    {
+      "epoch": 4.45,
+      "learning_rate": 8.920000000000001e-06,
+      "loss": 0.0451,
+      "step": 775
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 8.82e-06,
+      "loss": 0.0402,
+      "step": 800
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 8.720000000000001e-06,
+      "loss": 0.0417,
+      "step": 825
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 8.62e-06,
+      "loss": 0.0414,
+      "step": 850
+    },
+    {
+      "epoch": 5.03,
+      "learning_rate": 8.52e-06,
+      "loss": 0.0363,
+      "step": 875
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 8.42e-06,
+      "loss": 0.0196,
+      "step": 900
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 8.32e-06,
+      "loss": 0.0246,
+      "step": 925
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 8.220000000000001e-06,
+      "loss": 0.024,
+      "step": 950
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 8.120000000000002e-06,
+      "loss": 0.0229,
+      "step": 975
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 8.020000000000001e-06,
+      "loss": 0.0259,
+      "step": 1000
+    },
+    {
+      "epoch": 5.75,
+      "eval_loss": 0.5754263401031494,
+      "eval_runtime": 508.7474,
+      "eval_samples_per_second": 2.431,
+      "eval_steps_per_second": 0.305,
+      "eval_wer": 30.343239390284023,
+      "step": 1000
+    }
+  ],
+  "max_steps": 3000,
+  "num_train_epochs": 18,
+  "total_flos": 4.6014942081024e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48eeaeecd2959530f33cb0fe9e74b61ab76bf2592ce6a01a477a979e5e52b25
+size 3503