Training in progress, step 2400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb04c63682b4786c42d9e8bcd69c2b68a0037931f97a599af7cbf1129ff15e31
+oid sha256:b3b114ec9aae5f56c896dc809331fe15ed8ccb9c22a63d8091cf763b49c85e3d
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:108be5a941549c57ad5b41aeea576ba2ac85a3d6695d48c5bb5811e64b3badba
+oid sha256:edcd52e16b677aaaa2c66be498a66202ce1cc335af39cbbad43ce8a2ad734b75
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d892b0d38f04ef62cc89aabaa03d55447e3a9c0b3878a8dd9be38b5a4c5433
+oid sha256:87f3e0f4d936e870e79e3be44a85542644bf76c70c4bbcaa7cf95399760c586a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887c9ba23b35d52f7d9ec04d9717eb1e05e155aaf6ef15078b7968f60c8f51be
+oid sha256:df198c0270152417dac5be430450a9752660b128bc2ee48e34c53ddc72b40e6e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0930051c8643f83c104fb653cb7c51b35919ee5fd0154c43b4ca0dc5de1c8c3d
+oid sha256:d75303d12b74496ad035c93f7f537a1c9eccd4f5cc765415d2bf1655e9477134
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 2000,
-  "best_metric": 0.2625994694960212,
-  "best_model_checkpoint": "./distil-whisper/checkpoint-2000",
-  "epoch": 1.424728309282024,
+  "best_global_step": 2400,
+  "best_metric": 0.2371058060713233,
+  "best_model_checkpoint": "./distil-whisper/checkpoint-2400",
+  "epoch": 1.7097808658471405,
   "eval_steps": 400,
-  "global_step": 2000,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -193,6 +193,43 @@
       "eval_steps_per_second": 0.398,
       "eval_wer": 0.2625994694960212,
       "step": 2000
+    },
+    {
+      "epoch": 1.495991448423303,
+      "grad_norm": 60.051639556884766,
+      "learning_rate": 5.7266109463467245e-05,
+      "loss": 6.4429,
+      "step": 2100
+    },
+    {
+      "epoch": 1.5672545875645822,
+      "grad_norm": 107.0939712524414,
+      "learning_rate": 5.456996495012133e-05,
+      "loss": 6.7403,
+      "step": 2200
+    },
+    {
+      "epoch": 1.6385177267058615,
+      "grad_norm": 52.28662109375,
+      "learning_rate": 5.187382043677541e-05,
+      "loss": 6.4136,
+      "step": 2300
+    },
+    {
+      "epoch": 1.7097808658471405,
+      "grad_norm": 115.394287109375,
+      "learning_rate": 4.91776759234295e-05,
+      "loss": 5.6497,
+      "step": 2400
+    },
+    {
+      "epoch": 1.7097808658471405,
+      "eval_loss": 0.11455892771482468,
+      "eval_runtime": 156.1161,
+      "eval_samples_per_second": 3.203,
+      "eval_steps_per_second": 0.404,
+      "eval_wer": 0.2371058060713233,
+      "step": 2400
     }
   ],
   "logging_steps": 100,
@@ -212,7 +249,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.60046401568768e+18,
+  "total_flos": 3.12079259271168e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null