Training in progress, step 13600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ac4290640598dceb77135310af03477fc527a08702173117820a3f0b608a550
+oid sha256:7060279d45e7459b967e15db711d8cd9a1a17424e52d7e90ff35cb16d2ba87fb
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6223c792fe2fedd67376643c060243639c17fd0e7777012ac3b19b15717ca7b5
+oid sha256:79848332ea3785016fa03281822579bfa2a3e4281c3070d1112792454b5a75b5
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a3c6d4339d07e8ddf01aaa0b578cae9c13ec8ba232b16c8c20e6158df854a4f
+oid sha256:7c380529cf06397e865a2ec4a90a8b0334d0b540ca21dea720996a4d58cbfe97
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c0e095caeca862fdaf1f2a0bf15f3e74d530ed7cad799d4b08a06d363f3b11f
+oid sha256:d13fec0d58a698a1588dfadf5d00d4fb69b490cb8fc2864fda3b2a2af6f17146
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:808bb30e45f71065eb0cc43ff5a0467b811e2fe4cef3653bb3a24e25f6d1c7b1
+oid sha256:45c8cf259ef238a9913feac351553475b48cc5d3f6153c06161cc934160ae3d6
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 13200,
   "best_metric": 0.20100206307102858,
   "best_model_checkpoint": "./distil-whisper/checkpoint-13200",
-  "epoch": 9.407625155888116,
+  "epoch": 9.692677712453234,
   "eval_steps": 400,
-  "global_step": 13200,
+  "global_step": 13600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1229,6 +1229,43 @@
       "eval_steps_per_second": 0.435,
       "eval_wer": 0.20100206307102858,
       "step": 13200
+    },
+    {
+      "epoch": 9.478888295029396,
+      "grad_norm": 19.601333618164062,
+      "learning_rate": 5.506282335550628e-06,
+      "loss": 1.6243,
+      "step": 13300
+    },
+    {
+      "epoch": 9.550151434170676,
+      "grad_norm": 26.340774536132812,
+      "learning_rate": 4.767184035476718e-06,
+      "loss": 1.4496,
+      "step": 13400
+    },
+    {
+      "epoch": 9.621414573311954,
+      "grad_norm": 19.866046905517578,
+      "learning_rate": 4.028085735402809e-06,
+      "loss": 1.5778,
+      "step": 13500
+    },
+    {
+      "epoch": 9.692677712453234,
+      "grad_norm": 16.61330223083496,
+      "learning_rate": 3.288987435328899e-06,
+      "loss": 1.5726,
+      "step": 13600
+    },
+    {
+      "epoch": 9.692677712453234,
+      "eval_loss": 0.09693081676959991,
+      "eval_runtime": 145.8875,
+      "eval_samples_per_second": 3.427,
+      "eval_steps_per_second": 0.432,
+      "eval_wer": 0.20837017388741527,
+      "step": 13600
     }
   ],
   "logging_steps": 100,
@@ -1248,7 +1285,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.716153403834368e+19,
+  "total_flos": 1.768186261536768e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null