Training in progress, step 2100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e99427d68f8233aa1f1c5bb73907e5d9681f9991acb722d5d8f0825832c2f791
+oid sha256:44dc2faa43ac5a3436dfa3b3bed4aa7c966e4ea4f657d4e6dfca9280a68205ed
 size 290403936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f61c7abc74279095f7ed91d83ceb4ef17ae8f88cda63034464aa1242afbd199a
+oid sha256:1a48debe5a827e29a4f0cc6af4177c358b9b7475853d96668a3332a6bcf5927e
 size 574811514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c0cd479201fbb3ddf3b97d0708b8cd4b54efb5dd7439ed8dc16f0f7519ee85
+oid sha256:04493c60d37ce82f60a8454f7936d5c5083c1013f2dc35a3da96b38580130f41
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba7673f5d0f1631494ad72f8f050fc150ee4f9e1b527943111bb3dd31bbe4f29
+oid sha256:1d9f44034f20488b71439652353f4af422345160519981213e36f7e2d9306983
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a091a177a6000f85d9e8e7d6c3f964e3dfd92da03bfd940a7c2ea7974b6392
+oid sha256:c28781354eb93a174ad9fc8e149ed54169a6a66d39d32994acc35f88e6241d9e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 21.52664063484066,
   "best_model_checkpoint": "whisper-base-cv20-v2/checkpoint-1500",
-  "epoch": 2.564102564102564,
+  "epoch": 2.6923076923076925,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -767,6 +767,44 @@
       "eval_wer": 146.00495444430447,
       "eval_wer_ortho": 145.57382494602226,
       "step": 2000
+    },
+    {
+      "epoch": 2.5961538461538463,
+      "grad_norm": 4.9953694343566895,
+      "learning_rate": 7.573599240265908e-06,
+      "loss": 3.138,
+      "step": 2025
+    },
+    {
+      "epoch": 2.628205128205128,
+      "grad_norm": 5.183081150054932,
+      "learning_rate": 6.9800569800569804e-06,
+      "loss": 3.0988,
+      "step": 2050
+    },
+    {
+      "epoch": 2.66025641025641,
+      "grad_norm": 5.423998832702637,
+      "learning_rate": 6.386514719848054e-06,
+      "loss": 3.1566,
+      "step": 2075
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 5.148243427276611,
+      "learning_rate": 5.792972459639127e-06,
+      "loss": 3.0998,
+      "step": 2100
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "eval_loss": 1.8170723915100098,
+      "eval_runtime": 730.5921,
+      "eval_samples_per_second": 3.834,
+      "eval_steps_per_second": 0.06,
+      "eval_wer": 129.82743418566568,
+      "eval_wer_ortho": 130.33549244311575,
+      "step": 2100
     }
   ],
   "logging_steps": 25,
@@ -786,7 +824,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.30026342858752e+18,
+  "total_flos": 8.71536740401152e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null