Training in progress, step 5000

checkpoint-5000/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "openai/whisper-base",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50266
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "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": 6,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0.dev0",
+  "use_cache": false,
+  "vocab_size": 51865
+}

checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41fc1286eb74fc4b6f3cc51db1a4513998b8dac13900352b8db46880aebb8b38
+size 580895237

checkpoint-5000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a200316dd456070fc2433a73530252da7cda1d5c6c1752891f474252c07d64e
+size 290458721

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d04b8a7bd75a556e42e966c431ad883c916bb16a3d4c7fc1f146d0e22bff078e
+size 14575

checkpoint-5000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6446e04e1914efb3eeb432ecca7cf3b708bfb5c5edb5539627022b7bade06ea1
+size 557

checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c40def7a87418c1d9d60b7cf6590cb76a3191e8a75b2ea1fe7230edbaa0a1b
+size 627

checkpoint-5000/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 17.0223,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.960000000000001e-06,
+      "loss": 0.5615,
+      "step": 500
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 1e-05,
+      "loss": 0.3273,
+      "step": 1000
+    },
+    {
+      "epoch": 3.02,
+      "eval_loss": 0.4225325584411621,
+      "eval_runtime": 1489.9228,
+      "eval_samples_per_second": 3.09,
+      "eval_steps_per_second": 0.193,
+      "eval_wer": 20.82533081951615,
+      "step": 1000
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 1e-05,
+      "loss": 0.1859,
+      "step": 1500
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0923,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.46434369683265686,
+      "eval_runtime": 1504.5618,
+      "eval_samples_per_second": 3.06,
+      "eval_steps_per_second": 0.191,
+      "eval_wer": 21.22002361108664,
+      "step": 2000
+    },
+    {
+      "epoch": 8.03,
+      "learning_rate": 1e-05,
+      "loss": 0.0369,
+      "step": 2500
+    },
+    {
+      "epoch": 10.02,
+      "learning_rate": 1e-05,
+      "loss": 0.0164,
+      "step": 3000
+    },
+    {
+      "epoch": 10.02,
+      "eval_loss": 0.5403426885604858,
+      "eval_runtime": 1504.7378,
+      "eval_samples_per_second": 3.06,
+      "eval_steps_per_second": 0.191,
+      "eval_wer": 22.962662766725987,
+      "step": 3000
+    },
+    {
+      "epoch": 12.01,
+      "learning_rate": 1e-05,
+      "loss": 0.0089,
+      "step": 3500
+    },
+    {
+      "epoch": 14.01,
+      "learning_rate": 1e-05,
+      "loss": 0.006,
+      "step": 4000
+    },
+    {
+      "epoch": 14.01,
+      "eval_loss": 0.5819889307022095,
+      "eval_runtime": 1478.853,
+      "eval_samples_per_second": 3.113,
+      "eval_steps_per_second": 0.195,
+      "eval_wer": 21.086109985375224,
+      "step": 4000
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0057,
+      "step": 4500
+    },
+    {
+      "epoch": 17.02,
+      "learning_rate": 1e-05,
+      "loss": 0.0046,
+      "step": 5000
+    },
+    {
+      "epoch": 17.02,
+      "eval_loss": 0.5851565003395081,
+      "eval_runtime": 1532.3442,
+      "eval_samples_per_second": 3.005,
+      "eval_steps_per_second": 0.188,
+      "eval_wer": 22.072841964301446,
+      "step": 5000
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 1.035334174703616e+19,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63250d2e981e0cfad1a5508019d2b4e5ef4e64d9d02e786f5ee65312228c5eb2
+size 3643

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e9094804c4ffbab761a8f51a689672fef53c808ff5971ca1be1844410a6706
+oid sha256:2a200316dd456070fc2433a73530252da7cda1d5c6c1752891f474252c07d64e
 size 290458721

runs/Dec27_09-55-14_srv/events.out.tfevents.1672134971.srv.1172111.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b882d8f41c24f02537f2a6b2bb95a1d397730b6c0b06cc8e340b51118aeb0f5
-size 6956
+oid sha256:e14d0f45abec490706428810c4dec039b891475ad7d2e90ad1054a6e51a109c0
+size 7588