Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:136937f6dad5e75e8e11acf162368f776cdd7abcecd0a3bc3bc37f4462684486
+oid sha256:35bafb5e83a3063e2dfad84b3a78a8ef6c9ddbc53e561168a8fa12665aa5041d
 size 290403936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:410ff0ae73e0b7c981eeedd678e0397e6d173eee1a9ab6f2305c4ed3e2ac871b
+oid sha256:ea7497d6e6cc7bd241adf2b7d099f04e9d3377eaee0c9f4584cac44b60c7d8aa
 size 574811514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a422ce389ada244797b4b8e5f1b7ce29ae4fd49fe539b27e3cecb00dec5b6e34
+oid sha256:16f26b50bb43502b9ab2dbc60e6fcb7633cd99505b55155c4aea00ec5d808efa
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3c04ee422adff524b4efd8d1f2e54a96579cbb15dbab300b57694e56517037
+oid sha256:9d039589e7ee750c48310fc37e762db323bd19c07aaa98fd7655cfb5b1fc38d2
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0573451ef51fd7f1d8e1e74e80618d08a61cb1447a1e05ab95f804c1ee4734e
+oid sha256:9323e2532910e61327d035a7f8d8ab20531e8864442888c44c2445e0861b73bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 22.81983457194441,
-  "best_model_checkpoint": "whisper-base-cv20-v2/checkpoint-1400",
-  "epoch": 1.7948717948717947,
+  "best_metric": 21.52664063484066,
+  "best_model_checkpoint": "whisper-base-cv20-v2/checkpoint-1500",
+  "epoch": 1.9230769230769231,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -539,6 +539,44 @@
       "eval_wer": 22.81983457194441,
       "eval_wer_ortho": 25.631124397940543,
       "step": 1400
+    },
+    {
+      "epoch": 1.8269230769230769,
+      "grad_norm": 4.014779567718506,
+      "learning_rate": 2.177113010446344e-05,
+      "loss": 0.2671,
+      "step": 1425
+    },
+    {
+      "epoch": 1.858974358974359,
+      "grad_norm": 4.284206867218018,
+      "learning_rate": 2.1177587844254513e-05,
+      "loss": 0.2781,
+      "step": 1450
+    },
+    {
+      "epoch": 1.891025641025641,
+      "grad_norm": 4.6536712646484375,
+      "learning_rate": 2.0584045584045586e-05,
+      "loss": 0.27,
+      "step": 1475
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 4.077584266662598,
+      "learning_rate": 1.9990503323836657e-05,
+      "loss": 0.2574,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "eval_loss": 0.1773137003183365,
+      "eval_runtime": 649.5214,
+      "eval_samples_per_second": 4.312,
+      "eval_steps_per_second": 0.068,
+      "eval_wer": 21.52664063484066,
+      "eval_wer_ortho": 23.95781431655871,
+      "step": 1500
     }
   ],
   "logging_steps": 25,
@@ -558,7 +596,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.81054761598976e+18,
+  "total_flos": 6.22565159141376e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null