Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62deb87529039cbc1a82ab0b2c2c097e1116c967e4ff5a61dbfa5f3121bc149d
+oid sha256:cb04c63682b4786c42d9e8bcd69c2b68a0037931f97a599af7cbf1129ff15e31
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:350d7ce567924319983aca0e7f7be8b583f5d84a69d17ee26937019e17041e63
+oid sha256:108be5a941549c57ad5b41aeea576ba2ac85a3d6695d48c5bb5811e64b3badba
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6de54eb0387d3e1bf778e48ab81b040825a9de5fcb77ae848e4ced4e0ee2e87d
+oid sha256:52d892b0d38f04ef62cc89aabaa03d55447e3a9c0b3878a8dd9be38b5a4c5433
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be693887ab268fef1b2a4ac85d14acb908b9ba7b6d150718a85d227f055394a8
+oid sha256:887c9ba23b35d52f7d9ec04d9717eb1e05e155aaf6ef15078b7968f60c8f51be
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01bb6c0bd39168ba3e617f645d356e6f5a0f2faf5a8d66225a0993c8e3755d43
+oid sha256:0930051c8643f83c104fb653cb7c51b35919ee5fd0154c43b4ca0dc5de1c8c3d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1600,
-  "best_metric": 0.26760978485116416,
-  "best_model_checkpoint": "./distil-whisper/checkpoint-1600",
-  "epoch": 1.1396757527169072,
+  "best_global_step": 2000,
+  "best_metric": 0.2625994694960212,
+  "best_model_checkpoint": "./distil-whisper/checkpoint-2000",
+  "epoch": 1.424728309282024,
   "eval_steps": 400,
-  "global_step": 1600,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -156,6 +156,43 @@
       "eval_steps_per_second": 0.405,
       "eval_wer": 0.26760978485116416,
       "step": 1600
+    },
+    {
+      "epoch": 1.2109388918581863,
+      "grad_norm": 66.07127380371094,
+      "learning_rate": 6.80506875168509e-05,
+      "loss": 7.4023,
+      "step": 1700
+    },
+    {
+      "epoch": 1.2822020309994655,
+      "grad_norm": 94.31819915771484,
+      "learning_rate": 6.535454300350499e-05,
+      "loss": 7.4671,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3534651701407447,
+      "grad_norm": 133.11798095703125,
+      "learning_rate": 6.265839849015908e-05,
+      "loss": 7.167,
+      "step": 1900
+    },
+    {
+      "epoch": 1.424728309282024,
+      "grad_norm": 73.86894989013672,
+      "learning_rate": 5.9962253976813165e-05,
+      "loss": 6.2069,
+      "step": 2000
+    },
+    {
+      "epoch": 1.424728309282024,
+      "eval_loss": 0.11881361156702042,
+      "eval_runtime": 158.2803,
+      "eval_samples_per_second": 3.159,
+      "eval_steps_per_second": 0.398,
+      "eval_wer": 0.2625994694960212,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -175,7 +212,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.08013543866368e+18,
+  "total_flos": 2.60046401568768e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null