Training in progress, step 3342

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:460494fca0f4acea2091375e6de05c014dcf0bfb165313b31bb5e67f778c2fd7
+oid sha256:7fdb2b53096835a5a02597fbcbbb8b279b8398b05f1bdb4f9983b9ef5737b1fe
 size 558937304

runs/Apr27_12-02-54_ip-10-192-12-76/events.out.tfevents.1745755375.ip-10-192-12-76.2375.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2dce00904eb8a9eb57a26917dfd445c1295c0016e266de1444f683965cf0bb
+size 6679

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 2228,
-  "best_metric": 0.7726060406484112,
-  "best_model_checkpoint": "./checkpoints/checkpoint-2228",
-  "epoch": 0.39987436622246153,
+  "best_global_step": 3342,
+  "best_metric": 0.7720533296293449,
+  "best_model_checkpoint": "./checkpoints/checkpoint-3342",
+  "epoch": 0.5998115493336923,
   "eval_steps": 1114,
-  "global_step": 2228,
+  "global_step": 3342,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -54,6 +54,29 @@
       "eval_samples_per_second": 405.3,
       "eval_steps_per_second": 1.057,
       "step": 2228
+    },
+    {
+      "epoch": 0.44869206263741196,
+      "grad_norm": 0.04356146231293678,
+      "learning_rate": 4.970863550514242e-05,
+      "loss": 0.0398,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5384304751648943,
+      "grad_norm": 0.03718848526477814,
+      "learning_rate": 4.767405209364289e-05,
+      "loss": 0.0348,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5998115493336923,
+      "eval_cer": 0.7720533296293449,
+      "eval_loss": 0.022723019123077393,
+      "eval_runtime": 439.0491,
+      "eval_samples_per_second": 403.306,
+      "eval_steps_per_second": 1.052,
+      "step": 3342
     }
   ],
   "logging_steps": 500,
@@ -73,7 +96,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.608386971617198e+17,
+  "total_flos": 3.912580457425797e+17,
   "train_batch_size": 384,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d196aaedfdfd5bf4cdd22a7af058a95539d2d015355bfb0a175769535634028
-size 5905
+oid sha256:4bce4c2a570e5406234205443c86622d09135dc71fc8963eb2e85ed7f5af2b7c
+size 5841