Training in progress, step 14454

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b68629a4e7fbfde0f1b640d08dd2775f2c2f532f4da2add4ee14e34b66f168
+oid sha256:ccde7dcbe6e25cdd0c618ccbadaa82a004cc2e139e8990a1ed95973e15de90fb
 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 sha256:15f75329ed85e5259d9f5137f58b6204f020a8aea0824b5596178ecc4190cfab
-size 7028
+oid sha256:333d6fe335443bca75bb171cad5174ecb32002e6f3ed041aff8451bf09175c6b
+size 8120

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 12848,
-  "best_metric": 0.706664474285978,
-  "best_model_checkpoint": "checkpoints/checkpoint-12848",
-  "epoch": 1.9999610849515508,
+  "best_global_step": 14454,
+  "best_metric": 0.7064455694431908,
+  "best_model_checkpoint": "checkpoints/checkpoint-14454",
+  "epoch": 2.2499902712378876,
   "eval_steps": 1606,
-  "global_step": 12848,
+  "global_step": 14454,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -279,6 +279,39 @@
       "eval_steps_per_second": 1.746,
       "eval_wer": 0.6722098612169899,
       "step": 12848
+    },
+    {
+      "epoch": 2.0236603494571352,
+      "grad_norm": 0.028502434492111206,
+      "learning_rate": 4.898157560336646e-05,
+      "loss": 0.043,
+      "step": 13000
+    },
+    {
+      "epoch": 2.101490446355606,
+      "grad_norm": 0.030778545886278152,
+      "learning_rate": 4.832692770033863e-05,
+      "loss": 0.0417,
+      "step": 13500
+    },
+    {
+      "epoch": 2.1793205432540765,
+      "grad_norm": 0.0269626472145319,
+      "learning_rate": 4.7517396965763394e-05,
+      "loss": 0.041,
+      "step": 14000
+    },
+    {
+      "epoch": 2.2499902712378876,
+      "eval_avg": 0.7064455694431908,
+      "eval_cer": 0.6538135050224774,
+      "eval_der": 0.7939745658437141,
+      "eval_loss": 0.032875534147024155,
+      "eval_runtime": 304.6489,
+      "eval_samples_per_second": 445.506,
+      "eval_steps_per_second": 1.743,
+      "eval_wer": 0.6715486374633808,
+      "step": 14454
     }
   ],
   "logging_steps": 500,
@@ -298,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0027694737084908e+18,
+  "total_flos": 1.1281347889956127e+18,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null