Training in progress, step 3200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07cc1e0dffcd80eac14f87d0d9619540d3f5cf1771ecd556cf377b27a876168c
+oid sha256:77c42fb89ca5e7eeacd8dee347614384694d8e88a850be6f81c4be67614baaea
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4654516b018d8c1d8ee7f380300e2cfab5a3d33f9a966babd44885140fecda5d
+oid sha256:d33bb8913e40252c03691681597e0dda6da0e5d3ecd015fac2bf0734e9edc3fd
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9590931db28029d3072811ed01a2ef3a2eb67fd96a33277147916dc1a126b69f
+oid sha256:a0b9074bf4ad76d06be1f1774df5d1b38e357952bea3c631cc895318d367b54d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a378d0eab4cd862a8b75ae52dc72877722c788e485acf876520c8995544ef8d
+oid sha256:124d751b7518ff7dfcb4911295c0150ebaf171d8ca363a18657a8580b6e7df96
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0d22202ff71180e976c20ff3356dc9e86ce8ae5966c95daf7b725e761a03663
+oid sha256:0560bb7d987b0d9f7026aea630b8dd8d632a86b445987fc463b416ee149d3af2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 2400,
-  "best_metric": 0.2371058060713233,
-  "best_model_checkpoint": "./distil-whisper/checkpoint-2400",
-  "epoch": 1.9948334224122573,
+  "best_global_step": 3200,
+  "best_metric": 0.22575891541408782,
+  "best_model_checkpoint": "./distil-whisper/checkpoint-3200",
+  "epoch": 2.2793515054338145,
   "eval_steps": 400,
-  "global_step": 2800,
+  "global_step": 3200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,43 @@
       "eval_steps_per_second": 0.401,
       "eval_wer": 0.23946360153256704,
       "step": 2800
+    },
+    {
+      "epoch": 2.065562088009977,
+      "grad_norm": 41.731910705566406,
+      "learning_rate": 3.569695335669992e-05,
+      "loss": 4.2295,
+      "step": 2900
+    },
+    {
+      "epoch": 2.136825227151256,
+      "grad_norm": 67.33615112304688,
+      "learning_rate": 3.3000808843354005e-05,
+      "loss": 4.2595,
+      "step": 3000
+    },
+    {
+      "epoch": 2.208088366292535,
+      "grad_norm": 94.42093658447266,
+      "learning_rate": 3.030466433000809e-05,
+      "loss": 4.8801,
+      "step": 3100
+    },
+    {
+      "epoch": 2.2793515054338145,
+      "grad_norm": 31.315675735473633,
+      "learning_rate": 2.7608519816662175e-05,
+      "loss": 4.7207,
+      "step": 3200
+    },
+    {
+      "epoch": 2.2793515054338145,
+      "eval_loss": 0.11118239909410477,
+      "eval_runtime": 154.6651,
+      "eval_samples_per_second": 3.233,
+      "eval_steps_per_second": 0.407,
+      "eval_wer": 0.22575891541408782,
+      "step": 3200
     }
   ],
   "logging_steps": 100,
@@ -286,7 +323,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.64112116973568e+18,
+  "total_flos": 4.16027087732736e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null