Training in progress, step 1000

checkpoint-1000/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "./lab2_id2223",
+  "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": "4.26.0.dev0",
+  "use_cache": false,
+  "vocab_size": 51865
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f20721c0b9a7c610299c984d7dad194d61ca3133df7d98f7c7d332d3160aae6
+size 1934158597

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf08a6aa6026dbc8abee5e5743f086376cc3678ad79ebe2e9e116332be05fad5
+size 967099139

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f90fbf33b1469b721a0c185b0fe40c4526548689d54f89e04165027e4c386af1
+size 14439

checkpoint-1000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1d2dbe61bd26117d1189de7cf832428e092f6b72e3a39185250270a9584a00
+size 559

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d80191163bb665448e3d3769a1ef2c2dd2e2bd83464efbee56ee7d4eec97725
+size 623

checkpoint-1000/trainer_state.json

@@ -0,0 +1,265 @@
+{
+  "best_metric": 20.41339024938216,
+  "best_model_checkpoint": "./lab2_id2223/checkpoint-1000",
+  "epoch": 1.2936610608020698,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.800000000000001e-07,
+      "loss": 0.2225,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.800000000000001e-07,
+      "loss": 0.2081,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.48e-06,
+      "loss": 0.1992,
+      "step": 75
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.98e-06,
+      "loss": 0.2014,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.4800000000000004e-06,
+      "loss": 0.1914,
+      "step": 125
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.9800000000000003e-06,
+      "loss": 0.1978,
+      "step": 150
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.48e-06,
+      "loss": 0.1988,
+      "step": 175
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.980000000000001e-06,
+      "loss": 0.2153,
+      "step": 200
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.48e-06,
+      "loss": 0.1907,
+      "step": 225
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.980000000000001e-06,
+      "loss": 0.1976,
+      "step": 250
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 5.480000000000001e-06,
+      "loss": 0.2256,
+      "step": 275
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 5.98e-06,
+      "loss": 0.1805,
+      "step": 300
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.480000000000001e-06,
+      "loss": 0.2144,
+      "step": 325
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 6.98e-06,
+      "loss": 0.195,
+      "step": 350
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.48e-06,
+      "loss": 0.2053,
+      "step": 375
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 7.980000000000002e-06,
+      "loss": 0.2157,
+      "step": 400
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.48e-06,
+      "loss": 0.2062,
+      "step": 425
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.96e-06,
+      "loss": 0.1979,
+      "step": 450
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.460000000000001e-06,
+      "loss": 0.1868,
+      "step": 475
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.960000000000001e-06,
+      "loss": 0.2211,
+      "step": 500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.934285714285715e-06,
+      "loss": 0.2049,
+      "step": 525
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.862857142857144e-06,
+      "loss": 0.1989,
+      "step": 550
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.791428571428571e-06,
+      "loss": 0.2127,
+      "step": 575
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.72e-06,
+      "loss": 0.2261,
+      "step": 600
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.648571428571429e-06,
+      "loss": 0.2081,
+      "step": 625
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 9.577142857142858e-06,
+      "loss": 0.2281,
+      "step": 650
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.505714285714287e-06,
+      "loss": 0.204,
+      "step": 675
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.434285714285714e-06,
+      "loss": 0.2053,
+      "step": 700
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.362857142857143e-06,
+      "loss": 0.2208,
+      "step": 725
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.291428571428572e-06,
+      "loss": 0.2076,
+      "step": 750
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.220000000000002e-06,
+      "loss": 0.1941,
+      "step": 775
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.148571428571429e-06,
+      "loss": 0.0949,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.077142857142858e-06,
+      "loss": 0.1011,
+      "step": 825
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 9.005714285714287e-06,
+      "loss": 0.1078,
+      "step": 850
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.934285714285716e-06,
+      "loss": 0.0956,
+      "step": 875
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.862857142857143e-06,
+      "loss": 0.1093,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 8.791428571428572e-06,
+      "loss": 0.1133,
+      "step": 925
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 8.720000000000001e-06,
+      "loss": 0.1128,
+      "step": 950
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 8.64857142857143e-06,
+      "loss": 0.1068,
+      "step": 975
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 8.577142857142858e-06,
+      "loss": 0.1015,
+      "step": 1000
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.2880099415779114,
+      "eval_runtime": 2234.5268,
+      "eval_samples_per_second": 1.343,
+      "eval_steps_per_second": 0.168,
+      "eval_wer": 20.41339024938216,
+      "step": 1000
+    }
+  ],
+  "max_steps": 4000,
+  "num_train_epochs": 6,
+  "total_flos": 4.61505772191744e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f1eb1dbb07bf3ca34b6535b0daafae64c8f7caae6fd1291115311f4aa808a8
+size 3567

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-small",
+  "_name_or_path": "./lab2_id2223",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "architectures": [

preprocessor_config.json

@@ -5,7 +5,7 @@
   "hop_length": 160,
   "mel_filters": [
     [
-      -0.0,
+      0.0,
       0.02486259490251541,
       0.0,
       0.0,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9344f27a06d03c3c0c9310f5e59f7459aa3149c52122b20dec366bcf115e0ab2
+oid sha256:cf08a6aa6026dbc8abee5e5743f086376cc3678ad79ebe2e9e116332be05fad5
 size 967099139

runs/Dec07_13-35-04_fb5856445dc3/1670420137.5596879/events.out.tfevents.1670420137.fb5856445dc3.76.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4915130c4500d47dd044573bab166153a985302000a4f8551eb88cf87699f604
+size 5749

runs/Dec07_13-35-04_fb5856445dc3/events.out.tfevents.1670420137.fb5856445dc3.76.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d1c97dbf87fbf7c0e3ececa794d19f4297314942ff4c9a56915d7639045b876
+size 10822

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a9cc63e67bb20c6cd01ce4b2dda14ea2aa6a19c2849c087de5137131125b30e
+oid sha256:b2f1eb1dbb07bf3ca34b6535b0daafae64c8f7caae6fd1291115311f4aa808a8
 size 3567