Training in progress, step 3600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c42fb89ca5e7eeacd8dee347614384694d8e88a850be6f81c4be67614baaea
+oid sha256:69193aaf7ea71a75c6a53dabfa0a65ddf34dc8a499a127bc128b2aa53579f9fa
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33bb8913e40252c03691681597e0dda6da0e5d3ecd015fac2bf0734e9edc3fd
+oid sha256:8b8a538434890bc9b555c3d707ff536182a1ce9e72fd2075b1e4b25a5bfb7b54
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b9074bf4ad76d06be1f1774df5d1b38e357952bea3c631cc895318d367b54d
+oid sha256:d30d045d4139d3f55dfce92596184610f9efa25b6cf0587ae9fb8624b44b114d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:124d751b7518ff7dfcb4911295c0150ebaf171d8ca363a18657a8580b6e7df96
+oid sha256:d8dfdc3004aaa3171852de1590839deeeabef4dbb22c233c90f7014a88b5dd61
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0560bb7d987b0d9f7026aea630b8dd8d632a86b445987fc463b416ee149d3af2
+oid sha256:93bedcf8402af55b095bf6d5c557a90f995c7c5096c156990bbf9a11e0c8faf9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 3200,
   "best_metric": 0.22575891541408782,
   "best_model_checkpoint": "./distil-whisper/checkpoint-3200",
-  "epoch": 2.2793515054338145,
+  "epoch": 2.564404061998931,
   "eval_steps": 400,
-  "global_step": 3200,
+  "global_step": 3600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -304,6 +304,43 @@
       "eval_steps_per_second": 0.407,
       "eval_wer": 0.22575891541408782,
       "step": 3200
+    },
+    {
+      "epoch": 2.3506146445750935,
+      "grad_norm": 39.37460708618164,
+      "learning_rate": 2.491237530331626e-05,
+      "loss": 4.4,
+      "step": 3300
+    },
+    {
+      "epoch": 2.4218777837163725,
+      "grad_norm": 81.92980194091797,
+      "learning_rate": 2.2216230789970345e-05,
+      "loss": 4.5424,
+      "step": 3400
+    },
+    {
+      "epoch": 2.493140922857652,
+      "grad_norm": 69.34239959716797,
+      "learning_rate": 1.9520086276624428e-05,
+      "loss": 4.3866,
+      "step": 3500
+    },
+    {
+      "epoch": 2.564404061998931,
+      "grad_norm": 42.60212326049805,
+      "learning_rate": 1.682394176327851e-05,
+      "loss": 4.1488,
+      "step": 3600
+    },
+    {
+      "epoch": 2.564404061998931,
+      "eval_loss": 0.11083566397428513,
+      "eval_runtime": 157.7821,
+      "eval_samples_per_second": 3.169,
+      "eval_steps_per_second": 0.399,
+      "eval_wer": 0.23887415266725612,
+      "step": 3600
     }
   ],
   "logging_steps": 100,
@@ -323,7 +360,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.16027087732736e+18,
+  "total_flos": 4.68059945435136e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null