Training in progress, step 7815

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219166d066075e6987533778fd740cc6de866e1ed31000ae1c80a30ceebe58dd
+oid sha256:63eea8c40b61bba355a0097c91aec36f1d47d21024da7a0b696a224d7f332070
 size 1470068592

runs/Jul15_18-11-15_ip-10-192-10-50/events.out.tfevents.1752603076.ip-10-192-10-50.2305.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f60ff32cfe77e4a59ebf598d26835f4846110aeef15a82dc59e9113b9c4b51
-size 6793
+oid sha256:efc0a192a526494d1f1cf092073b8b87cb913e3de391dd764496d8d79f76f989
+size 8307

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 5210,
-  "best_metric": 0.04867361780589206,
-  "best_model_checkpoint": "checkpoints/checkpoint-5210",
-  "epoch": 0.3998925432705223,
+  "best_global_step": 7815,
+  "best_metric": 0.047643108039959726,
+  "best_model_checkpoint": "checkpoints/checkpoint-7815",
+  "epoch": 0.5998388149057835,
   "eval_steps": 2605,
-  "global_step": 5210,
+  "global_step": 7815,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -90,6 +90,53 @@
       "eval_steps_per_second": 0.382,
       "eval_wer": 0.07245120284895432,
       "step": 5210
+    },
+    {
+      "epoch": 0.42215143723375675,
+      "grad_norm": 0.11749344319105148,
+      "learning_rate": 4.700749788170293e-05,
+      "loss": 0.1409,
+      "step": 5500
+    },
+    {
+      "epoch": 0.46052884061864374,
+      "grad_norm": 0.17759008705615997,
+      "learning_rate": 4.651321975590966e-05,
+      "loss": 0.1407,
+      "step": 6000
+    },
+    {
+      "epoch": 0.49890624400353073,
+      "grad_norm": 0.11128637939691544,
+      "learning_rate": 4.598420225197139e-05,
+      "loss": 0.1403,
+      "step": 6500
+    },
+    {
+      "epoch": 0.5372836473884177,
+      "grad_norm": 0.10760766267776489,
+      "learning_rate": 4.542245865061001e-05,
+      "loss": 0.1389,
+      "step": 7000
+    },
+    {
+      "epoch": 0.5756610507733047,
+      "grad_norm": 0.10907711833715439,
+      "learning_rate": 4.482664487724415e-05,
+      "loss": 0.1396,
+      "step": 7500
+    },
+    {
+      "epoch": 0.5998388149057835,
+      "eval_avg": 0.047643108039959726,
+      "eval_cer": 0.031145497115735506,
+      "eval_der": 0.04097053994011138,
+      "eval_loss": 0.12629394233226776,
+      "eval_runtime": 1720.873,
+      "eval_samples_per_second": 30.081,
+      "eval_steps_per_second": 0.377,
+      "eval_wer": 0.07081328706403231,
+      "step": 7815
     }
   ],
   "logging_steps": 500,
@@ -109,7 +156,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.621871895445504e+17,
+  "total_flos": 5.432807843168256e+17,
   "train_batch_size": 80,
   "trial_name": null,
   "trial_params": null