Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69193aaf7ea71a75c6a53dabfa0a65ddf34dc8a499a127bc128b2aa53579f9fa
+oid sha256:03e9251a067bed69b21bc9690ad088ddf17d9ac223235998288adb3c1c31e717
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b8a538434890bc9b555c3d707ff536182a1ce9e72fd2075b1e4b25a5bfb7b54
+oid sha256:4dd56076323262e092e8fb333e8cf217ac4791a1b18c896b25c674975daab33b
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30d045d4139d3f55dfce92596184610f9efa25b6cf0587ae9fb8624b44b114d
+oid sha256:1fca3a6c28d869556336316e3c340a17810e0e98c5f965a843b6c555529cd4e4
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8dfdc3004aaa3171852de1590839deeeabef4dbb22c233c90f7014a88b5dd61
+oid sha256:b18eb86bc2b5eae896b5ecef9def5e77dce376ad484fc085505ee2339d389cbd
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93bedcf8402af55b095bf6d5c557a90f995c7c5096c156990bbf9a11e0c8faf9
+oid sha256:63b1d9922aa71edcb1afa04ca1f0f8d6e132dcc1b7ce072f4614fb8854bdfe62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 3200,
-  "best_metric": 0.22575891541408782,
-  "best_model_checkpoint": "./distil-whisper/checkpoint-3200",
-  "epoch": 2.564404061998931,
+  "best_global_step": 4000,
+  "best_metric": 0.22192749778956675,
+  "best_model_checkpoint": "./distil-whisper/checkpoint-4000",
+  "epoch": 2.849456618564048,
   "eval_steps": 400,
-  "global_step": 3600,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -341,6 +341,43 @@
       "eval_steps_per_second": 0.399,
       "eval_wer": 0.23887415266725612,
       "step": 3600
+    },
+    {
+      "epoch": 2.63566720114021,
+      "grad_norm": 30.755069732666016,
+      "learning_rate": 1.4127797249932598e-05,
+      "loss": 4.1464,
+      "step": 3700
+    },
+    {
+      "epoch": 2.7069303402814895,
+      "grad_norm": 39.35337829589844,
+      "learning_rate": 1.1431652736586681e-05,
+      "loss": 4.0822,
+      "step": 3800
+    },
+    {
+      "epoch": 2.7781934794227685,
+      "grad_norm": 59.027923583984375,
+      "learning_rate": 8.735508223240766e-06,
+      "loss": 4.0861,
+      "step": 3900
+    },
+    {
+      "epoch": 2.849456618564048,
+      "grad_norm": 42.845191955566406,
+      "learning_rate": 6.03936370989485e-06,
+      "loss": 4.0903,
+      "step": 4000
+    },
+    {
+      "epoch": 2.849456618564048,
+      "eval_loss": 0.1093602254986763,
+      "eval_runtime": 154.6964,
+      "eval_samples_per_second": 3.232,
+      "eval_steps_per_second": 0.407,
+      "eval_wer": 0.22192749778956675,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
@@ -360,7 +397,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.68059945435136e+18,
+  "total_flos": 5.20092803137536e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null