Training in progress, step 28000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8697dd2e30554939f3fdca476e8f8c14ef00252787d6ed337c4f9c24c9f4e2e
+oid sha256:8e9c5b5c507c25afe3cf4d5aec82c7836af315794f646ccd78331b1ef69b9976
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f55a81dbcdab168b5b56232e68b26448a34e74f5b0c7df45184f5e18e31d7e3
+oid sha256:f37dd8023aeda17192fa3cd957ae713351d08b56ea14a8b05ae51168a5029d04
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32de07988befbf143be2b9e32a6f8bc0b1b31db8931faad85d1d92ab132d45e6
+oid sha256:2940908599d69a8410ea56cae7b048228912580fd3318d429840a0c58b1c925b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b4a296cdf5148ddd1594a16e140d1d657863c4c29f02fff39c8abb2ac48881
+oid sha256:fbd563d83932cc7d0da7780f68883324db1a55e2e28771f70432de2590ff8acb
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ce753046bc02fca905121dc376e6ab4266dc1a838826882290e3881ef7934be
+oid sha256:a62d34f5456d530d45292bdc7a7b57a95952306ee03d49e82ed6ce0cb924518d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 25000,
-  "best_metric": 0.18243442381373415,
-  "best_model_checkpoint": "./distil-whisper/checkpoint-25000",
-  "epoch": 16.0,
+  "best_global_step": 28000,
+  "best_metric": 0.18110816386678455,
+  "best_model_checkpoint": "./distil-whisper/checkpoint-28000",
+  "epoch": 16.403046280023432,
   "eval_steps": 1000,
-  "global_step": 27312,
+  "global_step": 28000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2162,12 +2162,70 @@
       "learning_rate": 1.0070117857675669e-07,
       "loss": 0.7324,
       "step": 27300
+    },
+    {
+      "epoch": 16.05155243116579,
+      "grad_norm": 12.168989181518555,
+      "learning_rate": 2.7443730771306743e-05,
+      "loss": 0.7807,
+      "step": 27400
+    },
+    {
+      "epoch": 16.11013473930873,
+      "grad_norm": 5.686388969421387,
+      "learning_rate": 2.717385437469639e-05,
+      "loss": 0.8098,
+      "step": 27500
+    },
+    {
+      "epoch": 16.16871704745167,
+      "grad_norm": 6.920952320098877,
+      "learning_rate": 2.6903977978086036e-05,
+      "loss": 0.7786,
+      "step": 27600
+    },
+    {
+      "epoch": 16.22729935559461,
+      "grad_norm": 8.017998695373535,
+      "learning_rate": 2.6634101581475683e-05,
+      "loss": 0.8257,
+      "step": 27700
+    },
+    {
+      "epoch": 16.285881663737552,
+      "grad_norm": 6.6050262451171875,
+      "learning_rate": 2.6364225184865333e-05,
+      "loss": 0.7671,
+      "step": 27800
+    },
+    {
+      "epoch": 16.344463971880494,
+      "grad_norm": 8.146703720092773,
+      "learning_rate": 2.609434878825498e-05,
+      "loss": 0.7733,
+      "step": 27900
+    },
+    {
+      "epoch": 16.403046280023432,
+      "grad_norm": 11.652145385742188,
+      "learning_rate": 2.5824472391644626e-05,
+      "loss": 0.7902,
+      "step": 28000
+    },
+    {
+      "epoch": 16.403046280023432,
+      "eval_loss": 0.08416531980037689,
+      "eval_runtime": 148.3349,
+      "eval_samples_per_second": 3.371,
+      "eval_steps_per_second": 0.425,
+      "eval_wer": 0.18110816386678455,
+      "step": 28000
     }
   ],
   "logging_steps": 100,
-  "max_steps": 27312,
+  "max_steps": 37554,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 16,
+  "num_train_epochs": 22,
   "save_steps": 1000,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -2176,12 +2234,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.55254335963136e+19,
+  "total_flos": 3.642039874879488e+19,
   "train_batch_size": 8,
   "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:f8c88ae5031dc0d52713a2b3c363a1fb376926954db49624064f91e4b907e5be
+oid sha256:e81ddeed28465bb51d4919630f0406d970c910999565b6a4160cb0f11418cd99
 size 5496