Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9db619b5890ee02e32aa5b3b4461ed2b1be4ee2f6b5b4c3bf3c45d0e47385936
+oid sha256:3dbd12cee44083ef051774cc071d72302ab54e3242ec6c5ff3af01d7d77d34db
 size 267832560

wandb/run-20240924_172630-x9iddikd/files/output.log

@@ -24,3 +24,5 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 {'eval_loss': 0.19427122175693512, 'eval_accuracy': 0.938, 'eval_runtime': 42.2287, 'eval_samples_per_second': 23.681, 'eval_steps_per_second': 1.492, 'epoch': 2.0}
 {'eval_loss': 0.3195326626300812, 'eval_accuracy': 0.921, 'eval_runtime': 26.5577, 'eval_samples_per_second': 37.654, 'eval_steps_per_second': 2.372, 'epoch': 3.0}
 {'loss': 0.0672, 'grad_norm': 1.1029362678527832, 'learning_rate': 4.000000000000001e-06, 'epoch': 4.0}
+{'eval_loss': 0.36123067140579224, 'eval_accuracy': 0.925, 'eval_runtime': 26.675, 'eval_samples_per_second': 37.488, 'eval_steps_per_second': 2.362, 'epoch': 4.0}
+{'eval_loss': 0.3963741362094879, 'eval_accuracy': 0.926, 'eval_runtime': 25.9784, 'eval_samples_per_second': 38.493, 'eval_steps_per_second': 2.425, 'epoch': 5.0}

wandb/run-20240924_172630-x9iddikd/files/wandb-summary.json

@@ -1 +1 @@
-{"eval/loss": 0.36123067140579224, "eval/accuracy": 0.925, "eval/runtime": 26.675, "eval/samples_per_second": 37.488, "eval/steps_per_second": 2.362, "train/epoch": 4.0, "train/global_step": 1000, "_timestamp": 1727215983.911635, "_runtime": 6393.038725852966, "_step": 5, "train/loss": 0.0672, "train/grad_norm": 1.1029362678527832, "train/learning_rate": 4.000000000000001e-06}
+{"eval/loss": 0.3963741362094879, "eval/accuracy": 0.926, "eval/runtime": 25.9784, "eval/samples_per_second": 38.493, "eval/steps_per_second": 2.425, "train/epoch": 5.0, "train/global_step": 1250, "_timestamp": 1727217637.607487, "_runtime": 8046.734577894211, "_step": 7, "train/loss": 0.0672, "train/grad_norm": 1.1029362678527832, "train/learning_rate": 4.000000000000001e-06, "train_runtime": 8026.8642, "train_samples_per_second": 2.492, "train_steps_per_second": 0.156, "total_flos": 2396475988298112.0, "train_loss": 0.11480112991333008}