Training in progress, step 1100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:363a18dff03938cbab3ea0517e5fd8baacab97d4647e9d18d67491af3678daa6
+oid sha256:b6b8c4943809f31374b9e8f245a7b805ba8d8cb804c954afe70f2b1153c6466b
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec51eb4084dc7356ccd5e4f6e60d6eb446a9f6b453cb22d3a3f27e5a78818d65
+oid sha256:082989c729f6c2197f46184f15b82d0618ed70705d2eb063606785638c33b48c
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:140766ee026fe5edfef0f038f98f0479f8a9d10cfc1f7fe43d81468743578807
+oid sha256:0f6d4f1e7a172a18196d4af73f4416f5dbae2222daf67fb853e554c8aa388f46
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5923d5ad322acc38eebeb7826b39a3fb9c19734502e2060fc78e9bf4e91b73b
+oid sha256:5e80f39295701f62f253a4cdc45497251532fc021ede722c8cdba45bced5fc9c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 70.1955074875208,
   "best_model_checkpoint": "./whisper-it/checkpoint-300",
-  "epoch": 1.33587786259542,
+  "epoch": 2.099236641221374,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -238,6 +238,138 @@
       "eval_steps_per_second": 0.112,
       "eval_wer": 90.3563505268996,
       "step": 700
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 9.374285714285715e-06,
+      "loss": 0.1626,
+      "step": 725
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 9.302857142857144e-06,
+      "loss": 0.1674,
+      "step": 750
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 9.231428571428573e-06,
+      "loss": 0.1717,
+      "step": 775
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.16e-06,
+      "loss": 0.1607,
+      "step": 800
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 0.3789268732070923,
+      "eval_runtime": 1834.2673,
+      "eval_samples_per_second": 0.818,
+      "eval_steps_per_second": 0.102,
+      "eval_wer": 134.98336106489182,
+      "step": 800
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.08857142857143e-06,
+      "loss": 0.1636,
+      "step": 825
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.017142857142858e-06,
+      "loss": 0.1625,
+      "step": 850
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.945714285714286e-06,
+      "loss": 0.1762,
+      "step": 875
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.874285714285715e-06,
+      "loss": 0.154,
+      "step": 900
+    },
+    {
+      "epoch": 1.72,
+      "eval_loss": 0.3783314824104309,
+      "eval_runtime": 1787.7259,
+      "eval_samples_per_second": 0.839,
+      "eval_steps_per_second": 0.105,
+      "eval_wer": 99.0501941209096,
+      "step": 900
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 8.802857142857144e-06,
+      "loss": 0.1703,
+      "step": 925
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 8.731428571428571e-06,
+      "loss": 0.1593,
+      "step": 950
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 8.66e-06,
+      "loss": 0.1648,
+      "step": 975
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 8.588571428571429e-06,
+      "loss": 0.1562,
+      "step": 1000
+    },
+    {
+      "epoch": 1.91,
+      "eval_loss": 0.36686423420906067,
+      "eval_runtime": 1815.5283,
+      "eval_samples_per_second": 0.826,
+      "eval_steps_per_second": 0.104,
+      "eval_wer": 98.31530782029951,
+      "step": 1000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 8.517142857142858e-06,
+      "loss": 0.1751,
+      "step": 1025
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.445714285714285e-06,
+      "loss": 0.1593,
+      "step": 1050
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 8.374285714285714e-06,
+      "loss": 0.0693,
+      "step": 1075
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 8.302857142857143e-06,
+      "loss": 0.0723,
+      "step": 1100
+    },
+    {
+      "epoch": 2.1,
+      "eval_loss": 0.3756558299064636,
+      "eval_runtime": 1775.3191,
+      "eval_samples_per_second": 0.845,
+      "eval_steps_per_second": 0.106,
+      "eval_wer": 158.88103161397672,
+      "step": 1100
     }
   ],
   "logging_steps": 25,
@@ -245,7 +377,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 8,
   "save_steps": 100,
-  "total_flos": 6.46229286936576e+18,
+  "total_flos": 1.015416589565952e+19,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8639ff321d8732686fcd47480f025401063d95f80a6017764993068cc24ca794
+oid sha256:26fb5b39845f83ef97933929d4301eb10fbbba57913dc6054b50bd05a1ce5a9f
 size 4792