Training in progress, step 41200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb3428b5d7351f2f983a8817140c1c8b2e96b29566ec79f4307a4b81ec849b68
+oid sha256:b6e2823f88f5f24074d58b21cfe18f66f131ac34667095575c4c40e4eae863e3
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a096e10e2fc8125e4596c05a55c5be93a424630c3a8d00b9012ce34e0eb121
+oid sha256:337d3b57220580ed03ee608a9a877cb6776a0f7fb530d8a389436c6d77d26aed
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0409b0246d35c8ef79cb2b0e43178bdf95a92462fbd64e2c9dfd213533047dc5
+oid sha256:d37da37f32b9da157d0f354c842374bbe28e2210ef8b4e1a2f62909ef09fdefb
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b922550ce28a3681322bb9777a8dd637293414e098f71686c9e28adbd7a3a6
+oid sha256:0bbf1059b349dfce5e1aca93ba02e0a5c14f3145f54aaedb0a25d075e6e0aaa9
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea63f0486f536d4a4ac9c36e06e08d63effd7c038d0a64ea9126e98bd07aa911
+oid sha256:f7e2692c415195d4cb598a1230fff1568c572f90b174e77b60f1d07171445123
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 32400,
   "best_metric": 0.19510757441791923,
   "best_model_checkpoint": "./distil-whisper/checkpoint-32400",
-  "epoch": 29.077676821663996,
+  "epoch": 29.362729378229112,
   "eval_steps": 400,
-  "global_step": 40800,
+  "global_step": 41200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3782,6 +3782,43 @@
       "eval_steps_per_second": 0.434,
       "eval_wer": 0.1976127320954907,
       "step": 40800
+    },
+    {
+      "epoch": 29.148939960805272,
+      "grad_norm": 12.47839641571045,
+      "learning_rate": 2.9165664823274828e-06,
+      "loss": 0.9257,
+      "step": 40900
+    },
+    {
+      "epoch": 29.220203099946552,
+      "grad_norm": 9.78573989868164,
+      "learning_rate": 2.676124068285646e-06,
+      "loss": 0.9376,
+      "step": 41000
+    },
+    {
+      "epoch": 29.291466239087832,
+      "grad_norm": 10.32386589050293,
+      "learning_rate": 2.4356816542438087e-06,
+      "loss": 0.9428,
+      "step": 41100
+    },
+    {
+      "epoch": 29.362729378229112,
+      "grad_norm": 12.5963773727417,
+      "learning_rate": 2.195239240201972e-06,
+      "loss": 0.9519,
+      "step": 41200
+    },
+    {
+      "epoch": 29.362729378229112,
+      "eval_loss": 0.09224098175764084,
+      "eval_runtime": 145.4228,
+      "eval_samples_per_second": 3.438,
+      "eval_steps_per_second": 0.433,
+      "eval_wer": 0.19687592101385204,
+      "step": 41200
     }
   ],
   "logging_steps": 100,
@@ -3801,7 +3838,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.304416507265024e+19,
+  "total_flos": 5.356449364967424e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null