Training in progress, step 16060

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccde7dcbe6e25cdd0c618ccbadaa82a004cc2e139e8990a1ed95973e15de90fb
+oid sha256:ae5d5f2467be1e0f32383e0f24718a2027023a02821399a4ab911c4727fe071e
 size 667849236

runs/May06_08-32-58_ip-10-192-12-5/events.out.tfevents.1746520379.ip-10-192-12-5.1614.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333d6fe335443bca75bb171cad5174ecb32002e6f3ed041aff8451bf09175c6b
-size 8120
+oid sha256:2bf97edebecbae8fc943eb5835585041af0dec87a18f100369ec0e37270d0603
+size 9423

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 14454,
-  "best_metric": 0.7064455694431908,
-  "best_model_checkpoint": "checkpoints/checkpoint-14454",
-  "epoch": 2.2499902712378876,
+  "best_global_step": 16060,
+  "best_metric": 0.7061941356307186,
+  "best_model_checkpoint": "checkpoints/checkpoint-16060",
+  "epoch": 2.4999805424757753,
   "eval_steps": 1606,
-  "global_step": 14454,
+  "global_step": 16060,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,46 @@
       "eval_steps_per_second": 1.743,
       "eval_wer": 0.6715486374633808,
       "step": 14454
+    },
+    {
+      "epoch": 2.257150640152547,
+      "grad_norm": 0.03818966820836067,
+      "learning_rate": 4.6558358407185946e-05,
+      "loss": 0.0402,
+      "step": 14500
+    },
+    {
+      "epoch": 2.3349807370510174,
+      "grad_norm": 0.029628828167915344,
+      "learning_rate": 4.5456179713031586e-05,
+      "loss": 0.0395,
+      "step": 15000
+    },
+    {
+      "epoch": 2.4128108339494885,
+      "grad_norm": 0.02792350761592388,
+      "learning_rate": 4.4218178973329804e-05,
+      "loss": 0.0392,
+      "step": 15500
+    },
+    {
+      "epoch": 2.4906409308479587,
+      "grad_norm": 0.03364017978310585,
+      "learning_rate": 4.2852576090096216e-05,
+      "loss": 0.0384,
+      "step": 16000
+    },
+    {
+      "epoch": 2.4999805424757753,
+      "eval_avg": 0.7061941356307186,
+      "eval_cer": 0.6537081045699137,
+      "eval_der": 0.7939727975362082,
+      "eval_loss": 0.031167298555374146,
+      "eval_runtime": 303.0246,
+      "eval_samples_per_second": 447.894,
+      "eval_steps_per_second": 1.752,
+      "eval_wer": 0.670901504786034,
+      "step": 16060
     }
   ],
   "logging_steps": 500,
@@ -331,7 +371,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1281347889956127e+18,
+  "total_flos": 1.253480973209174e+18,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null