Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a17ef64572270a9ea1fe1e15f9c9fd7db0eb5dcbc7b4c2e7c22e1b289cd045a
+oid sha256:bb48d4529d566b344fe7367bac97351c603bbd85ca9f61087d4dc319f1ae6495
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb58a20df4a5c26d8cc8d650c52be7b7ebb42ea978deb259ee7da10c866c627a
+oid sha256:c75691a1ce258d234722c2d4ab3b85571a4565b6f8c306d9e4e850037046468b
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:470e496359a2cf24c1ca6e38338e3dc7a3a2df79fa39edd6fc9efb7bc5840f7f
+oid sha256:75bd767a73465b16f4ffdfb35ee15891c86eba958fe1f44fc879bf90de6c06cf
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02dbd14bc775d96702bd09aaa6a225264fa5fa3e843e9f9c8c5143c1b071dd8d
+oid sha256:640a2c1972f8c0eea0b1816d3a5ded6495205b53dbb31dc9c8bee27a5b36d529
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d10538eb4038dcded6d04473312c9371c80551f842fa32f7bde8c55d456156b
+oid sha256:332f9130d37f9b28f027125f3d3e057edade6877a2990aa73c37f287b89e9652
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 4000,
-  "best_metric": 0.18818155025051578,
-  "best_model_checkpoint": "./distil-whisper/checkpoint-4000",
-  "epoch": 10.0,
+  "best_global_step": 18000,
+  "best_metric": 0.1865605658709107,
+  "best_model_checkpoint": "./distil-whisper/checkpoint-18000",
+  "epoch": 10.54481546572935,
   "eval_steps": 1000,
-  "global_step": 17070,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1351,12 +1351,91 @@
       "eval_steps_per_second": 0.435,
       "eval_wer": 0.19112879457707044,
       "step": 17000
+    },
+    {
+      "epoch": 10.017574692442881,
+      "grad_norm": 7.963376045227051,
+      "learning_rate": 3.392152957578172e-05,
+      "loss": 0.8347,
+      "step": 17100
+    },
+    {
+      "epoch": 10.076157000585823,
+      "grad_norm": 6.854780673980713,
+      "learning_rate": 3.352320254929297e-05,
+      "loss": 0.8392,
+      "step": 17200
+    },
+    {
+      "epoch": 10.134739308728763,
+      "grad_norm": 7.880845069885254,
+      "learning_rate": 3.312487552280422e-05,
+      "loss": 0.8556,
+      "step": 17300
+    },
+    {
+      "epoch": 10.193321616871705,
+      "grad_norm": 16.49683952331543,
+      "learning_rate": 3.2726548496315476e-05,
+      "loss": 0.9433,
+      "step": 17400
+    },
+    {
+      "epoch": 10.251903925014645,
+      "grad_norm": 9.839179039001465,
+      "learning_rate": 3.232822146982673e-05,
+      "loss": 0.8697,
+      "step": 17500
+    },
+    {
+      "epoch": 10.310486233157587,
+      "grad_norm": 7.640855312347412,
+      "learning_rate": 3.1929894443337984e-05,
+      "loss": 0.934,
+      "step": 17600
+    },
+    {
+      "epoch": 10.369068541300527,
+      "grad_norm": 9.590755462646484,
+      "learning_rate": 3.153156741684923e-05,
+      "loss": 0.8328,
+      "step": 17700
+    },
+    {
+      "epoch": 10.427650849443468,
+      "grad_norm": 6.947925567626953,
+      "learning_rate": 3.1133240390360485e-05,
+      "loss": 0.8759,
+      "step": 17800
+    },
+    {
+      "epoch": 10.486233157586408,
+      "grad_norm": 10.188766479492188,
+      "learning_rate": 3.0734913363871746e-05,
+      "loss": 0.9053,
+      "step": 17900
+    },
+    {
+      "epoch": 10.54481546572935,
+      "grad_norm": 8.809179306030273,
+      "learning_rate": 3.0336586337382993e-05,
+      "loss": 0.8203,
+      "step": 18000
+    },
+    {
+      "epoch": 10.54481546572935,
+      "eval_loss": 0.08442338556051254,
+      "eval_runtime": 157.987,
+      "eval_samples_per_second": 3.165,
+      "eval_steps_per_second": 0.399,
+      "eval_wer": 0.1865605658709107,
+      "step": 18000
     }
   ],
   "logging_steps": 100,
-  "max_steps": 17070,
+  "max_steps": 25605,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "num_train_epochs": 15,
   "save_steps": 1000,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -1365,12 +1444,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.2203395997696e+19,
+  "total_flos": 2.34131599392768e+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 sha256:7ee93f68344d21c77364cf023e65591db8cc68c0d6aa9c42dd07b5f1c55f175d
+oid sha256:bddd4569a5055d59a70490c9da64158bf2e341f257865204c3154f99021841bd
 size 5496