Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f6f578221e0bc9ac0da38636e645d07c0956e59852e6210dbc6f3501b9aee5
+oid sha256:8934bd46cb1d211e89a648589db21b00b2653c8a5559c6f8554ead0dd889558e
 size 267832560

wandb/run-20240923_004152-7jibscvo/files/output.log

@@ -6,3 +6,7 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 {'loss': 0.3343, 'grad_norm': 13.296141624450684, 'learning_rate': 1.872040946896993e-05, 'epoch': 0.32}
 {'loss': 0.2518, 'grad_norm': 9.50092887878418, 'learning_rate': 1.744081893793986e-05, 'epoch': 0.64}
 {'loss': 0.2252, 'grad_norm': 15.53085994720459, 'learning_rate': 1.616122840690979e-05, 'epoch': 0.96}
+{'eval_loss': 0.23595260083675385, 'eval_accuracy': 0.90616, 'eval_runtime': 870.3291, 'eval_samples_per_second': 28.725, 'eval_steps_per_second': 1.796, 'epoch': 1.0}
+{'loss': 0.1689, 'grad_norm': 7.930511474609375, 'learning_rate': 1.488163787587972e-05, 'epoch': 1.28}
+{'loss': 0.1504, 'grad_norm': 36.72976303100586, 'learning_rate': 1.3602047344849649e-05, 'epoch': 1.6}
+{'loss': 0.1526, 'grad_norm': 0.9081774353981018, 'learning_rate': 1.2322456813819578e-05, 'epoch': 1.92}

wandb/run-20240923_004152-7jibscvo/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 0.2252, "train/grad_norm": 15.53085994720459, "train/learning_rate": 1.616122840690979e-05, "train/epoch": 1.0, "train/global_step": 1563, "_timestamp": 1727074257.6513228, "_runtime": 11345.533327817917, "_step": 3, "eval/loss": 0.23595260083675385, "eval/accuracy": 0.90616, "eval/runtime": 870.3291, "eval/samples_per_second": 28.725, "eval/steps_per_second": 1.796}
+{"train/loss": 0.1526, "train/grad_norm": 0.9081774353981018, "train/learning_rate": 1.2322456813819578e-05, "train/epoch": 2.0, "train/global_step": 3126, "_timestamp": 1727085575.407219, "_runtime": 22663.289223909378, "_step": 7, "eval/loss": 0.2298162430524826, "eval/accuracy": 0.92924, "eval/runtime": 898.8856, "eval/samples_per_second": 27.812, "eval/steps_per_second": 1.739}