Training in progress, step 11242

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6432e5d4dbcf96f5f64c6469ce31b0d5b3c9f01110150b82ee9cdadc1010e989
+oid sha256:c5fd5f2647fde284fadd8fe1b84d2385e1d8557c192a97d1bcb3b84b535022e3
 size 667849236

runs/May05_22-15-18_ip-10-192-11-107/events.out.tfevents.1746483320.ip-10-192-11-107.1742.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc24c92646c4300934b8e42a0af0a9a570793e89cf4cb7a4bf4d6430ecf6297
-size 8333
+oid sha256:5c0c1ed8c78331621c33d91080f46daa3bfc44db1cd7f7208e0e1b80939a9db4
+size 9425

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 9636,
-  "best_metric": 0.7073388677263619,
-  "best_model_checkpoint": "checkpoints/checkpoint-9636",
-  "epoch": 1.4999805424757753,
+  "best_global_step": 11242,
+  "best_metric": 0.7068964281422255,
+  "best_model_checkpoint": "checkpoints/checkpoint-11242",
+  "epoch": 1.749970813713663,
   "eval_steps": 1606,
-  "global_step": 9636,
+  "global_step": 11242,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,39 @@
       "eval_steps_per_second": 1.728,
       "eval_wer": 0.6740765765448399,
       "step": 9636
+    },
+    {
+      "epoch": 1.556640853017862,
+      "grad_norm": 0.031485334038734436,
+      "learning_rate": 4.587349950536374e-05,
+      "loss": 0.0492,
+      "step": 10000
+    },
+    {
+      "epoch": 1.6344709499163326,
+      "grad_norm": 0.031592607498168945,
+      "learning_rate": 4.46840328658421e-05,
+      "loss": 0.0481,
+      "step": 10500
+    },
+    {
+      "epoch": 1.7123010468148032,
+      "grad_norm": 0.031952131539583206,
+      "learning_rate": 4.336387097207617e-05,
+      "loss": 0.0468,
+      "step": 11000
+    },
+    {
+      "epoch": 1.749970813713663,
+      "eval_avg": 0.7068964281422255,
+      "eval_cer": 0.6539495257646198,
+      "eval_der": 0.7937636951733035,
+      "eval_loss": 0.036437951028347015,
+      "eval_runtime": 308.1694,
+      "eval_samples_per_second": 440.417,
+      "eval_steps_per_second": 1.723,
+      "eval_wer": 0.6729760634887532,
+      "step": 11242
     }
   ],
   "logging_steps": 500,
@@ -232,7 +265,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.52077105281368e+17,
+  "total_flos": 8.774232894949294e+17,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null