Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2acb4494239e0f2939b3554b19b44da1666640d4f17fee2602fc2f73e90c86a2
+oid sha256:aac2c722661dfc970b5b362fbdfe7348728114256cbf16c80817c6883bccfc3c
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e09793699a5f80b3df4ba07dbf1ff576b3a0280feb3ad0da5b0b59817e93f5ca
+oid sha256:a6ebd804fbe71863b75c6e04deb067d66c945809a3503b78c812931908581ff7
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc4c3096e3335993cba70f84f7c74e0bdefbe1836fe1f21fd4c7db981a15d18
+oid sha256:fef3f536e40043cb197cbf070d1d05bc7d1e4addbc3323ceb593a92b77a5ed05
 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": 7200,
   "best_metric": 0.2094017094017094,
   "best_model_checkpoint": "./distil-whisper/checkpoint-7200",
-  "epoch": 9.68911455549617,
+  "epoch": 9.974167112061286,
   "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": 0.435,
       "eval_wer": 0.2163277335691129,
       "step": 13600
+    },
+    {
+      "epoch": 9.760377694637448,
+      "grad_norm": 26.84296417236328,
+      "learning_rate": 2.549889135254989e-06,
+      "loss": 1.7145,
+      "step": 13700
+    },
+    {
+      "epoch": 9.831640833778728,
+      "grad_norm": 22.363689422607422,
+      "learning_rate": 1.8107908351810791e-06,
+      "loss": 1.691,
+      "step": 13800
+    },
+    {
+      "epoch": 9.902903972920008,
+      "grad_norm": 13.84276008605957,
+      "learning_rate": 1.0716925351071693e-06,
+      "loss": 1.5786,
+      "step": 13900
+    },
+    {
+      "epoch": 9.974167112061286,
+      "grad_norm": 14.124626159667969,
+      "learning_rate": 3.3259423503325944e-07,
+      "loss": 1.6427,
+      "step": 14000
+    },
+    {
+      "epoch": 9.974167112061286,
+      "eval_loss": 0.10011343657970428,
+      "eval_runtime": 145.0395,
+      "eval_samples_per_second": 3.447,
+      "eval_steps_per_second": 0.434,
+      "eval_wer": 0.21573828470380194,
+      "step": 14000
     }
   ],
   "logging_steps": 100,
@@ -1285,7 +1322,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.768174066335744e+19,
+  "total_flos": 1.820206924038144e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null