Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b8c4943809f31374b9e8f245a7b805ba8d8cb804c954afe70f2b1153c6466b
+oid sha256:a901289acfaf261ca99f8fce199d0ef18efafb593fc4adbc16569e175365f047
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:082989c729f6c2197f46184f15b82d0618ed70705d2eb063606785638c33b48c
+oid sha256:03efce6f4839aac6b09a3ff77b2a5cd14008d0e349f52b50c2683f2928a55556
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f6d4f1e7a172a18196d4af73f4416f5dbae2222daf67fb853e554c8aa388f46
+oid sha256:394cffd5f9ba2a487775b8ed26f91cd80b374a4935a3895fe55cc7a990318c58
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e80f39295701f62f253a4cdc45497251532fc021ede722c8cdba45bced5fc9c
+oid sha256:8793d18c29517684d33f92639ac08774efc835c6295929f4bc9ba059c5aa8346
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 70.1955074875208,
   "best_model_checkpoint": "./whisper-it/checkpoint-300",
-  "epoch": 2.099236641221374,
+  "epoch": 2.8625954198473282,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -370,6 +370,138 @@
       "eval_steps_per_second": 0.106,
       "eval_wer": 158.88103161397672,
       "step": 1100
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 8.231428571428572e-06,
+      "loss": 0.075,
+      "step": 1125
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 8.16e-06,
+      "loss": 0.0701,
+      "step": 1150
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 8.088571428571429e-06,
+      "loss": 0.0732,
+      "step": 1175
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 8.017142857142858e-06,
+      "loss": 0.0769,
+      "step": 1200
+    },
+    {
+      "epoch": 2.29,
+      "eval_loss": 0.3788917660713196,
+      "eval_runtime": 1861.7459,
+      "eval_samples_per_second": 0.806,
+      "eval_steps_per_second": 0.101,
+      "eval_wer": 215.1552967276761,
+      "step": 1200
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 7.945714285714287e-06,
+      "loss": 0.0747,
+      "step": 1225
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 7.874285714285716e-06,
+      "loss": 0.0737,
+      "step": 1250
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 7.802857142857143e-06,
+      "loss": 0.0774,
+      "step": 1275
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.731428571428572e-06,
+      "loss": 0.0814,
+      "step": 1300
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 0.3779347538948059,
+      "eval_runtime": 1837.4869,
+      "eval_samples_per_second": 0.816,
+      "eval_steps_per_second": 0.102,
+      "eval_wer": 170.4520244037715,
+      "step": 1300
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.660000000000001e-06,
+      "loss": 0.0782,
+      "step": 1325
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.588571428571429e-06,
+      "loss": 0.0732,
+      "step": 1350
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7.5171428571428575e-06,
+      "loss": 0.078,
+      "step": 1375
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 7.445714285714286e-06,
+      "loss": 0.0786,
+      "step": 1400
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 0.37702885270118713,
+      "eval_runtime": 1750.66,
+      "eval_samples_per_second": 0.857,
+      "eval_steps_per_second": 0.107,
+      "eval_wer": 140.5851358846367,
+      "step": 1400
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 7.374285714285715e-06,
+      "loss": 0.0774,
+      "step": 1425
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 7.302857142857144e-06,
+      "loss": 0.0717,
+      "step": 1450
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 7.231428571428573e-06,
+      "loss": 0.07,
+      "step": 1475
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 7.16e-06,
+      "loss": 0.0673,
+      "step": 1500
+    },
+    {
+      "epoch": 2.86,
+      "eval_loss": 0.37770169973373413,
+      "eval_runtime": 1736.5025,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.108,
+      "eval_wer": 137.09095951192455,
+      "step": 1500
     }
   ],
   "logging_steps": 25,
@@ -377,7 +509,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 8,
   "save_steps": 100,
-  "total_flos": 1.015416589565952e+19,
+  "total_flos": 1.384805901975552e+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 sha256:26fb5b39845f83ef97933929d4301eb10fbbba57913dc6054b50bd05a1ce5a9f
-size 4792
+oid sha256:6aa21d9517849e744bc2774d0fa736ea880951b90cffefa75582a90947374bfc
+size 4856