Training in progress, step 3800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c20757676a83e9b79b55197874149746ed730a010a68d7587e7a7a8797e4af1
+oid sha256:95d21fe86e17b73959794ce11ad74e73bd1518a97c41faa4f8be18d8b2bf9ffd
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8502d4c8fda153d19bf8f43fc8963d5f83d32afabe6587e68b89400a1db97099
+oid sha256:bb75cb3c8888c58d9bbbf5f27c5c4b39a276e2cb1132258d4d397bc75a0794e6
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e965350b0250570f0290355734c648f6a779f3eafb0bec172682cdf9092f567d
+oid sha256:6295971cadb4eb4446c807f39815a8d622e5c0ad4c399dae68672ed76bc9bf06
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:069be83226f429c691ea9e58c35ae52310d302cf0b73d3f098f087a042d5fe52
+oid sha256:08eb48843e7de4cc16819ecf94466b3964c70de64215674fcb462d6faa6bbb4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 70.1955074875208,
   "best_model_checkpoint": "./whisper-it/checkpoint-300",
-  "epoch": 6.488549618320611,
+  "epoch": 7.251908396946565,
   "eval_steps": 100,
-  "global_step": 3400,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1129,6 +1129,138 @@
       "eval_steps_per_second": 0.112,
       "eval_wer": 189.57986688851912,
       "step": 3400
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 1.6600000000000002e-06,
+      "loss": 0.006,
+      "step": 3425
+    },
+    {
+      "epoch": 6.58,
+      "learning_rate": 1.5885714285714288e-06,
+      "loss": 0.0069,
+      "step": 3450
+    },
+    {
+      "epoch": 6.63,
+      "learning_rate": 1.5171428571428574e-06,
+      "loss": 0.0049,
+      "step": 3475
+    },
+    {
+      "epoch": 6.68,
+      "learning_rate": 1.4457142857142858e-06,
+      "loss": 0.0051,
+      "step": 3500
+    },
+    {
+      "epoch": 6.68,
+      "eval_loss": 0.45023292303085327,
+      "eval_runtime": 1638.7418,
+      "eval_samples_per_second": 0.915,
+      "eval_steps_per_second": 0.115,
+      "eval_wer": 194.2179700499168,
+      "step": 3500
+    },
+    {
+      "epoch": 6.73,
+      "learning_rate": 1.3742857142857143e-06,
+      "loss": 0.0059,
+      "step": 3525
+    },
+    {
+      "epoch": 6.77,
+      "learning_rate": 1.302857142857143e-06,
+      "loss": 0.0061,
+      "step": 3550
+    },
+    {
+      "epoch": 6.82,
+      "learning_rate": 1.2314285714285715e-06,
+      "loss": 0.0053,
+      "step": 3575
+    },
+    {
+      "epoch": 6.87,
+      "learning_rate": 1.1600000000000001e-06,
+      "loss": 0.0064,
+      "step": 3600
+    },
+    {
+      "epoch": 6.87,
+      "eval_loss": 0.4511769413948059,
+      "eval_runtime": 1630.1101,
+      "eval_samples_per_second": 0.92,
+      "eval_steps_per_second": 0.115,
+      "eval_wer": 187.41680532445923,
+      "step": 3600
+    },
+    {
+      "epoch": 6.92,
+      "learning_rate": 1.0885714285714287e-06,
+      "loss": 0.0063,
+      "step": 3625
+    },
+    {
+      "epoch": 6.97,
+      "learning_rate": 1.0171428571428573e-06,
+      "loss": 0.0057,
+      "step": 3650
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 9.457142857142858e-07,
+      "loss": 0.0045,
+      "step": 3675
+    },
+    {
+      "epoch": 7.06,
+      "learning_rate": 8.742857142857144e-07,
+      "loss": 0.0053,
+      "step": 3700
+    },
+    {
+      "epoch": 7.06,
+      "eval_loss": 0.45203542709350586,
+      "eval_runtime": 1642.6362,
+      "eval_samples_per_second": 0.913,
+      "eval_steps_per_second": 0.114,
+      "eval_wer": 190.1968940654465,
+      "step": 3700
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 8.028571428571429e-07,
+      "loss": 0.0055,
+      "step": 3725
+    },
+    {
+      "epoch": 7.16,
+      "learning_rate": 7.314285714285715e-07,
+      "loss": 0.0047,
+      "step": 3750
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 6.6e-07,
+      "loss": 0.0052,
+      "step": 3775
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 5.885714285714286e-07,
+      "loss": 0.0049,
+      "step": 3800
+    },
+    {
+      "epoch": 7.25,
+      "eval_loss": 0.45453497767448425,
+      "eval_runtime": 1636.9322,
+      "eval_samples_per_second": 0.916,
+      "eval_steps_per_second": 0.115,
+      "eval_wer": 194.88352745424294,
+      "step": 3800
     }
   ],
   "logging_steps": 25,
@@ -1136,7 +1268,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 8,
   "save_steps": 100,
-  "total_flos": 3.138597096800256e+19,
+  "total_flos": 3.507784399429632e+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:f6dbc4dfe40c6e33f03f512f01526c1128aacac99b0beb33850a3ef004ff4c98
+oid sha256:1ae1639f5a86ad76181a01b25b9e64e68e1d290527cd8dd714fc9cee35836950
 size 4856