Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7723d7c543d8111cde5b0d0c7d380625efc576826c33a65ac4f833b07aeb1078
+oid sha256:2d5614aa1af231902d4d5e3d77f5f3651b101e42cb96721c66a4e36c221825bc
 size 290403936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd87fc16d56b734cfeee5cb96b5f81c2c149684d9649cfa36228e731375678b9
+oid sha256:f7a91a83c5869579384befed17a65fdc01a4a1eeeb562808c9f16b986e7b270c
 size 574811514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1b89009b6eacb3b00e97174956b74b753d7bd2d21ca376db9636fe91a916011
+oid sha256:71100c749c3d328813d845f0d31f26307650b3fddf848738bea5a69ec145f95d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c51e96bf39df0dcf05159321d889a0250569d665b8a5872f89010f1c91dbc52
+oid sha256:79f86771e7e266279e59ca59b5466e514a509aded5e6a1886ec8e7d2af927a1c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94141d46d0db9b87a9f2673574f734412e500930d0c99d7e67d128e20b2e1714
+oid sha256:a2b3abdfc627eb6c58d7379b09121bd3c4b9730cfcbd091e8a4ca22eb117191b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 100,
   "best_metric": 22.84922534324222,
   "best_model_checkpoint": "whisper-base-synth-v2/checkpoint-100",
-  "epoch": 0.9584664536741214,
+  "epoch": 1.2779552715654952,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -122,6 +122,44 @@
       "eval_wer": 93.44165931897385,
       "eval_wer_ortho": 96.17588440458395,
       "step": 300
+    },
+    {
+      "epoch": 1.038338658146965,
+      "grad_norm": 3.464035749435425,
+      "learning_rate": 5.0958466453674125e-06,
+      "loss": 4.0785,
+      "step": 325
+    },
+    {
+      "epoch": 1.1182108626198084,
+      "grad_norm": 4.340151309967041,
+      "learning_rate": 5.49520766773163e-06,
+      "loss": 3.9435,
+      "step": 350
+    },
+    {
+      "epoch": 1.1980830670926517,
+      "grad_norm": 3.903965950012207,
+      "learning_rate": 5.894568690095847e-06,
+      "loss": 3.8291,
+      "step": 375
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "grad_norm": 3.497990369796753,
+      "learning_rate": 6.2939297124600645e-06,
+      "loss": 3.7216,
+      "step": 400
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "eval_loss": 1.0830340385437012,
+      "eval_runtime": 996.8493,
+      "eval_samples_per_second": 2.81,
+      "eval_steps_per_second": 0.044,
+      "eval_wer": 827.2872318092119,
+      "eval_wer_ortho": 818.5434313237004,
+      "step": 400
     }
   ],
   "logging_steps": 25,
@@ -141,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.245311926272e+18,
+  "total_flos": 1.65834038181888e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null