Training in progress, step 34000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cfc2369854afc94fdfa5a772fefa0c2c28012dcdc0bc0ea80f23b73f346c34a
+oid sha256:396a29a5a4787dbf082bfc1745fc5d4dbaf49c674cf87663f742af78ff889ac4
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a0c5737e43b8c351af0642dc5e297ba4cfc310d2333fb3515ae84242ec7206
+oid sha256:2a681bae809c2c7355b83c2ba73ac835d0bd5c7c190fd2e0484e22164316f803
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:576380a256a4340c462ffc82306c52abbab7f38e65a7b12e9ab2634163e0fae7
+oid sha256:ce2c6e00c180a2aec543a6c39f38b41238eae7e450c89c57b59b23abde749eed
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5680c8a2f1d27c25e08e493d045a3f651f13f689a05908b8e76432cb1f7ace3b
+oid sha256:d82f68a924bc6f264caa5b5167990f1fdb3b2c8f9254156d8c0f9ccc3c5489db
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb6ef00c1c865d5fe6826f62f53b17ea0c3488cfae31fdb4898bd3e20b4343e
+oid sha256:122a12c57bcb396697297c9c6111a0a8854f31fea532275de745584ad3eee2c3
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 28000,
   "best_metric": 0.18110816386678455,
   "best_model_checkpoint": "./distil-whisper/checkpoint-28000",
-  "epoch": 19.332161687170476,
+  "epoch": 19.917984768599883,
   "eval_steps": 1000,
-  "global_step": 33000,
+  "global_step": 34000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2615,6 +2615,85 @@
       "eval_steps_per_second": 0.426,
       "eval_wer": 0.18641320365458297,
       "step": 33000
+    },
+    {
+      "epoch": 19.390743995313414,
+      "grad_norm": 7.711204528808594,
+      "learning_rate": 1.206617369244886e-05,
+      "loss": 0.7326,
+      "step": 33100
+    },
+    {
+      "epoch": 19.449326303456356,
+      "grad_norm": 6.137068271636963,
+      "learning_rate": 1.1796297295838508e-05,
+      "loss": 0.6976,
+      "step": 33200
+    },
+    {
+      "epoch": 19.507908611599298,
+      "grad_norm": 6.798486709594727,
+      "learning_rate": 1.1526420899228154e-05,
+      "loss": 0.7118,
+      "step": 33300
+    },
+    {
+      "epoch": 19.566490919742236,
+      "grad_norm": 6.276034355163574,
+      "learning_rate": 1.12565445026178e-05,
+      "loss": 0.7112,
+      "step": 33400
+    },
+    {
+      "epoch": 19.625073227885178,
+      "grad_norm": 7.021731853485107,
+      "learning_rate": 1.0986668106007449e-05,
+      "loss": 0.6984,
+      "step": 33500
+    },
+    {
+      "epoch": 19.68365553602812,
+      "grad_norm": 5.709362983703613,
+      "learning_rate": 1.0716791709397096e-05,
+      "loss": 0.7376,
+      "step": 33600
+    },
+    {
+      "epoch": 19.74223784417106,
+      "grad_norm": 7.312982559204102,
+      "learning_rate": 1.0446915312786744e-05,
+      "loss": 0.7448,
+      "step": 33700
+    },
+    {
+      "epoch": 19.800820152314,
+      "grad_norm": 5.710330486297607,
+      "learning_rate": 1.0177038916176392e-05,
+      "loss": 0.7524,
+      "step": 33800
+    },
+    {
+      "epoch": 19.85940246045694,
+      "grad_norm": 6.241232395172119,
+      "learning_rate": 9.907162519566039e-06,
+      "loss": 0.6942,
+      "step": 33900
+    },
+    {
+      "epoch": 19.917984768599883,
+      "grad_norm": 6.5843024253845215,
+      "learning_rate": 9.637286122955687e-06,
+      "loss": 0.707,
+      "step": 34000
+    },
+    {
+      "epoch": 19.917984768599883,
+      "eval_loss": 0.08329460024833679,
+      "eval_runtime": 148.0997,
+      "eval_samples_per_second": 3.376,
+      "eval_steps_per_second": 0.425,
+      "eval_wer": 0.18715001473622164,
+      "step": 34000
     }
   ],
   "logging_steps": 100,
@@ -2634,7 +2713,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.292401815355392e+19,
+  "total_flos": 4.422483959611392e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null