Training in progress, step 3000

checkpoint-3000/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-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a9a6ba3514ea9d6db1a08bb4a0c88bfb930473d0585e67f9c387a723f5f585
+size 580895237

checkpoint-3000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff1da28c51d823737fb4818883912c8ef38a3f7deab6ac12f7330b85ce6746d
+size 290458721

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d2f60cb6280cb118cbcd7fdc141e319d16420633e0be7a8e959cbbd5c286a3
+size 14575

checkpoint-3000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67052f7ccf0c314ec66f8a5e6561069877b7b24a3a43dcf29f3baded513f272d
+size 557

checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb034e50379aa6ea99cbc9d658e4acd9811df68b30554db29c35cbfd17ee561
+size 627

checkpoint-3000/trainer_state.json

@@ -0,0 +1,223 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 333.0003,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 11.0,
+      "learning_rate": 4.85e-06,
+      "loss": 0.716,
+      "step": 100
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 9.85e-06,
+      "loss": 0.0615,
+      "step": 200
+    },
+    {
+      "epoch": 33.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0043,
+      "step": 300
+    },
+    {
+      "epoch": 44.0,
+      "learning_rate": 1e-05,
+      "loss": 0.002,
+      "step": 400
+    },
+    {
+      "epoch": 55.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0008,
+      "step": 500
+    },
+    {
+      "epoch": 66.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0006,
+      "step": 600
+    },
+    {
+      "epoch": 77.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0004,
+      "step": 700
+    },
+    {
+      "epoch": 88.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0003,
+      "step": 800
+    },
+    {
+      "epoch": 99.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0003,
+      "step": 900
+    },
+    {
+      "epoch": 111.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0002,
+      "step": 1000
+    },
+    {
+      "epoch": 111.0,
+      "eval_loss": 0.21552081406116486,
+      "eval_runtime": 10.773,
+      "eval_samples_per_second": 1.671,
+      "eval_steps_per_second": 0.093,
+      "eval_wer": 9.75609756097561,
+      "step": 1000
+    },
+    {
+      "epoch": 122.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0002,
+      "step": 1100
+    },
+    {
+      "epoch": 133.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0002,
+      "step": 1200
+    },
+    {
+      "epoch": 144.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 1300
+    },
+    {
+      "epoch": 155.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 1400
+    },
+    {
+      "epoch": 166.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 1500
+    },
+    {
+      "epoch": 177.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 1600
+    },
+    {
+      "epoch": 188.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 1700
+    },
+    {
+      "epoch": 199.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 1800
+    },
+    {
+      "epoch": 211.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 1900
+    },
+    {
+      "epoch": 222.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 2000
+    },
+    {
+      "epoch": 222.0,
+      "eval_loss": 0.2447899729013443,
+      "eval_runtime": 14.1456,
+      "eval_samples_per_second": 1.272,
+      "eval_steps_per_second": 0.071,
+      "eval_wer": 12.195121951219512,
+      "step": 2000
+    },
+    {
+      "epoch": 233.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 2100
+    },
+    {
+      "epoch": 244.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 2200
+    },
+    {
+      "epoch": 255.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 2300
+    },
+    {
+      "epoch": 266.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 2400
+    },
+    {
+      "epoch": 277.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 2500
+    },
+    {
+      "epoch": 288.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 2600
+    },
+    {
+      "epoch": 299.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 2700
+    },
+    {
+      "epoch": 311.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 2800
+    },
+    {
+      "epoch": 322.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 2900
+    },
+    {
+      "epoch": 333.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 3000
+    },
+    {
+      "epoch": 333.0,
+      "eval_loss": 0.2674005329608917,
+      "eval_runtime": 8.0249,
+      "eval_samples_per_second": 2.243,
+      "eval_steps_per_second": 0.125,
+      "eval_wer": 13.414634146341465,
+      "step": 3000
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 5.88098557181952e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c36b35e37212c7c09dbca6abb82e5ea958e60ecae5b6ed572ed342d641b50f3
+size 3643

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41743ac18fc5950c53b1ff840c995ec5a357f3cc4970952fee087c9addd50905
+oid sha256:9ff1da28c51d823737fb4818883912c8ef38a3f7deab6ac12f7330b85ce6746d
 size 290458721

runs/Dec29_11-05-20_srv/events.out.tfevents.1672311942.srv.13534.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b96c31bd693e2285579df0988e25ac68a155b117c3840ab359950adfc4ea43ce
-size 8204
+oid sha256:22cbbf28149bb7214579e204ce6f59b932c0bdae6db17a9957ee2d1d31711a4b
+size 10092