Training in progress, step 40

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./whisper-tiny-hi2_test/whisper-tiny-hi-checkpoint-5",
+  "_name_or_path": "openai/whisper-tiny",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65486a040e9edffe3575e458f27f57a36d8b2427a1a78dbd727b53bf7ff9bc9a
+oid sha256:4aa0a5f2be765194ceb37b7b5a11f8c161e39c5d682d08c4e15906e203be3d97
 size 151061672

runs/Jun20_08-30-19_bharatsahaiyak-test/events.out.tfevents.1718872220.bharatsahaiyak-test.505065.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36de5cbe836b3aa9a3020223a41b2e1b7f68f06f2409002fd638f68f2e7cb892
+size 6044

runs/Jun20_14-52-54_bharatsahaiyak-test/events.out.tfevents.1718895174.bharatsahaiyak-test.584004.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4bac9a366d8c6e15cd3ae97117e2e6e8e8f764f2ffff1e13c99bf41c29fe57
+size 6380

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1445f90ea066b719c6f11b72dfcb44e26f1f122c5f102a79c5ebab74ddd094d
+oid sha256:8c982fa9327e2e49f4765e9f4a5be54ca2c672121610ce55b8168505a2beb3b7
 size 5240

whisper-tiny-hi-checkpoint-6/trainer_state.json

@@ -0,0 +1,247 @@
+{
+  "best_metric": 63.60403082394783,
+  "best_model_checkpoint": "./whisper-tiny-hi2_test/checkpoint-200",
+  "epoch": 6.40625,
+  "eval_steps": 40,
+  "global_step": 205,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.625,
+      "grad_norm": 10.62358283996582,
+      "learning_rate": 1e-05,
+      "loss": 2.3669,
+      "step": 20
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 7.5668721199035645,
+      "learning_rate": 1e-05,
+      "loss": 1.1887,
+      "step": 40
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 0.9953901171684265,
+      "eval_runtime": 571.1605,
+      "eval_samples_per_second": 1.751,
+      "eval_steps_per_second": 1.751,
+      "eval_wer": 87.29782369379288,
+      "step": 40
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 6.932765960693359,
+      "learning_rate": 1e-05,
+      "loss": 0.855,
+      "step": 60
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 6.589940547943115,
+      "learning_rate": 1e-05,
+      "loss": 0.6663,
+      "step": 80
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.6780964136123657,
+      "eval_runtime": 554.1893,
+      "eval_samples_per_second": 1.804,
+      "eval_steps_per_second": 1.804,
+      "eval_wer": 73.29155728681515,
+      "step": 80
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 6.102142810821533,
+      "learning_rate": 1e-05,
+      "loss": 0.5761,
+      "step": 100
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 5.4204583168029785,
+      "learning_rate": 1e-05,
+      "loss": 0.5053,
+      "step": 120
+    },
+    {
+      "epoch": 3.75,
+      "eval_loss": 0.5857690572738647,
+      "eval_runtime": 567.8481,
+      "eval_samples_per_second": 1.761,
+      "eval_steps_per_second": 1.761,
+      "eval_wer": 66.22914726056398,
+      "step": 120
+    },
+    {
+      "epoch": 4.375,
+      "grad_norm": 4.851945400238037,
+      "learning_rate": 1e-05,
+      "loss": 0.4369,
+      "step": 140
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 9.788898468017578,
+      "learning_rate": 1e-05,
+      "loss": 0.406,
+      "step": 160
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5440137982368469,
+      "eval_runtime": 560.2795,
+      "eval_samples_per_second": 1.785,
+      "eval_steps_per_second": 1.785,
+      "eval_wer": 66.13599796765179,
+      "step": 160
+    },
+    {
+      "epoch": 5.625,
+      "grad_norm": 4.664266109466553,
+      "learning_rate": 1e-05,
+      "loss": 0.356,
+      "step": 180
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 4.6183037757873535,
+      "learning_rate": 1e-05,
+      "loss": 0.3236,
+      "step": 200
+    },
+    {
+      "epoch": 6.25,
+      "eval_loss": 0.5290657877922058,
+      "eval_runtime": 553.81,
+      "eval_samples_per_second": 1.806,
+      "eval_steps_per_second": 1.806,
+      "eval_wer": 63.60403082394783,
+      "step": 200
+    },
+    {
+      "epoch": 6.25,
+      "step": 200,
+      "total_flos": 1.5401574531072e+17,
+      "train_loss": 0.7680861353874207,
+      "train_runtime": 3626.9505,
+      "train_samples_per_second": 1.765,
+      "train_steps_per_second": 0.055
+    },
+    {
+      "epoch": 6.28125,
+      "step": 201,
+      "total_flos": 1.5480354963456e+17,
+      "train_loss": 0.002653346132876268,
+      "train_runtime": 7.7901,
+      "train_samples_per_second": 821.558,
+      "train_steps_per_second": 25.674
+    },
+    {
+      "epoch": 6.28125,
+      "eval_loss": 0.5290657877922058,
+      "eval_runtime": 551.3177,
+      "eval_samples_per_second": 1.814,
+      "eval_steps_per_second": 1.814,
+      "eval_wer": 63.60403082394783,
+      "step": 201
+    },
+    {
+      "epoch": 6.3125,
+      "step": 202,
+      "total_flos": 1.555913539584e+17,
+      "train_loss": 0.002912604867821873,
+      "train_runtime": 7.6856,
+      "train_samples_per_second": 832.727,
+      "train_steps_per_second": 26.023
+    },
+    {
+      "epoch": 6.3125,
+      "eval_loss": 0.5290657877922058,
+      "eval_runtime": 543.8685,
+      "eval_samples_per_second": 1.839,
+      "eval_steps_per_second": 1.839,
+      "eval_wer": 63.60403082394783,
+      "step": 202
+    },
+    {
+      "epoch": 6.34375,
+      "step": 203,
+      "total_flos": 1.5637915828224e+17,
+      "train_loss": 0.0022250449128926094,
+      "train_runtime": 7.6745,
+      "train_samples_per_second": 833.935,
+      "train_steps_per_second": 26.06
+    },
+    {
+      "epoch": 6.34375,
+      "eval_loss": 0.5290657877922058,
+      "eval_runtime": 542.3404,
+      "eval_samples_per_second": 1.844,
+      "eval_steps_per_second": 1.844,
+      "eval_wer": 63.60403082394783,
+      "step": 203
+    },
+    {
+      "epoch": 6.375,
+      "step": 204,
+      "total_flos": 1.5716696260608e+17,
+      "train_loss": 0.002586784608223859,
+      "train_runtime": 7.6824,
+      "train_samples_per_second": 833.073,
+      "train_steps_per_second": 26.034
+    },
+    {
+      "epoch": 6.375,
+      "eval_loss": 0.5290657877922058,
+      "eval_runtime": 544.5113,
+      "eval_samples_per_second": 1.837,
+      "eval_steps_per_second": 1.837,
+      "eval_wer": 63.60403082394783,
+      "step": 204
+    },
+    {
+      "epoch": 6.40625,
+      "step": 205,
+      "total_flos": 1.5795476692992e+17,
+      "train_loss": 0.002658948665711938,
+      "train_runtime": 7.6873,
+      "train_samples_per_second": 832.539,
+      "train_steps_per_second": 26.017
+    },
+    {
+      "epoch": 6.40625,
+      "eval_loss": 0.5290657877922058,
+      "eval_runtime": 543.8428,
+      "eval_samples_per_second": 1.839,
+      "eval_steps_per_second": 1.839,
+      "eval_wer": 63.60403082394783,
+      "step": 205
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5795476692992e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}