Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7060279d45e7459b967e15db711d8cd9a1a17424e52d7e90ff35cb16d2ba87fb
+oid sha256:df99a406fd4e7a9f486934f8fc91ca5fea5fbeda134839a6397edae2c28f810d
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79848332ea3785016fa03281822579bfa2a3e4281c3070d1112792454b5a75b5
+oid sha256:0c89b7f6ce34f4634f681a539266445fc82cf8655d87d75223f7f3a5be780b8d
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c380529cf06397e865a2ec4a90a8b0334d0b540ca21dea720996a4d58cbfe97
+oid sha256:4eb8b589bc0f9fc2ded989d3a40e07724301f383d8307d4ec1d41c66b9f6bfc8
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d13fec0d58a698a1588dfadf5d00d4fb69b490cb8fc2864fda3b2a2af6f17146
+oid sha256:fe901f3488345253ab27036dffafec4bebac63e87632ab024a1c268eea13b76c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45c8cf259ef238a9913feac351553475b48cc5d3f6153c06161cc934160ae3d6
+oid sha256:e7dd03a3ec49e4f6d8256968a34ec8adb177fe3d2cfce1011557149c70298286
 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": 9.692677712453234,
+  "epoch": 9.97773026901835,
   "eval_steps": 400,
-  "global_step": 13600,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1266,6 +1266,43 @@
       "eval_steps_per_second": 0.432,
       "eval_wer": 0.20837017388741527,
       "step": 13600
+    },
+    {
+      "epoch": 9.763940851594512,
+      "grad_norm": 26.37179183959961,
+      "learning_rate": 2.549889135254989e-06,
+      "loss": 1.546,
+      "step": 13700
+    },
+    {
+      "epoch": 9.835203990735792,
+      "grad_norm": 17.592809677124023,
+      "learning_rate": 1.8107908351810791e-06,
+      "loss": 1.4815,
+      "step": 13800
+    },
+    {
+      "epoch": 9.906467129877072,
+      "grad_norm": 14.37030029296875,
+      "learning_rate": 1.0716925351071693e-06,
+      "loss": 1.414,
+      "step": 13900
+    },
+    {
+      "epoch": 9.97773026901835,
+      "grad_norm": 21.16905975341797,
+      "learning_rate": 3.3259423503325944e-07,
+      "loss": 1.4709,
+      "step": 14000
+    },
+    {
+      "epoch": 9.97773026901835,
+      "eval_loss": 0.097068190574646,
+      "eval_runtime": 145.6677,
+      "eval_samples_per_second": 3.432,
+      "eval_steps_per_second": 0.432,
+      "eval_wer": 0.20439139404656645,
+      "step": 14000
     }
   ],
   "logging_steps": 100,
@@ -1285,7 +1322,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.768186261536768e+19,
+  "total_flos": 1.820219119239168e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null