Training in progress, step 40800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e908c33cb5ddafacb872f16b41997491efe990ca6db2aba5dc5f241a9ee8ac8b
+oid sha256:eb3428b5d7351f2f983a8817140c1c8b2e96b29566ec79f4307a4b81ec849b68
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e7335be850a77ed844126afc416152259a212213cb71e7fd7bbcd4ef2aae259
+oid sha256:24a096e10e2fc8125e4596c05a55c5be93a424630c3a8d00b9012ce34e0eb121
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ae5dab173d92222353169663bfdebf6edc75503f1fb78c65f7a9fb76170c4e
+oid sha256:0409b0246d35c8ef79cb2b0e43178bdf95a92462fbd64e2c9dfd213533047dc5
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9383df6acc9eebb713ee9164dce15ff181d1c731d3df4af21e99b066b741bf86
+oid sha256:d0b922550ce28a3681322bb9777a8dd637293414e098f71686c9e28adbd7a3a6
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16389ad3b087c8fe30b05b86b3c616cbcd2a64791ab8d7bf77b40533143885c1
+oid sha256:ea63f0486f536d4a4ac9c36e06e08d63effd7c038d0a64ea9126e98bd07aa911
 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": 28.793158738642436,
+  "epoch": 29.077676821663996,
   "eval_steps": 400,
-  "global_step": 40400,
+  "global_step": 40800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3745,6 +3745,43 @@
       "eval_steps_per_second": 0.433,
       "eval_wer": 0.19982316534040673,
       "step": 40400
+    },
+    {
+      "epoch": 28.864421877783716,
+      "grad_norm": 16.17976188659668,
+      "learning_rate": 3.878336138494831e-06,
+      "loss": 0.9462,
+      "step": 40500
+    },
+    {
+      "epoch": 28.935685016924996,
+      "grad_norm": 12.729133605957031,
+      "learning_rate": 3.637893724452994e-06,
+      "loss": 0.9777,
+      "step": 40600
+    },
+    {
+      "epoch": 29.006413682522716,
+      "grad_norm": 15.731132507324219,
+      "learning_rate": 3.3974513104111564e-06,
+      "loss": 0.9736,
+      "step": 40700
+    },
+    {
+      "epoch": 29.077676821663996,
+      "grad_norm": 9.655588150024414,
+      "learning_rate": 3.15700889636932e-06,
+      "loss": 0.9533,
+      "step": 40800
+    },
+    {
+      "epoch": 29.077676821663996,
+      "eval_loss": 0.09240180999040604,
+      "eval_runtime": 145.3169,
+      "eval_samples_per_second": 3.441,
+      "eval_steps_per_second": 0.434,
+      "eval_wer": 0.1976127320954907,
+      "step": 40800
     }
   ],
   "logging_steps": 100,
@@ -3764,7 +3801,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.252501536505856e+19,
+  "total_flos": 5.304416507265024e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null