Training in progress, epoch 28

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:091c5a022a123f68446ecd7ed7eee21c04ee771b3b22d5395bc1e8ef3b1704c7
+oid sha256:d943a8ac647d684911f22651743e177a88bc2674f477b81e1be402a194a9877c
 size 267832560

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

@@ -64,3 +64,5 @@ wandb: Network error (SSLError), entering retry loop.
 {'eval_loss': 0.6649676561355591, 'eval_accuracy': 0.907, 'eval_runtime': 38.4215, 'eval_samples_per_second': 26.027, 'eval_steps_per_second': 0.833, 'epoch': 24.0}
 {'eval_loss': 0.6898632645606995, 'eval_accuracy': 0.9, 'eval_runtime': 38.2884, 'eval_samples_per_second': 26.118, 'eval_steps_per_second': 0.836, 'epoch': 25.0}
 {'eval_loss': 0.7331468462944031, 'eval_accuracy': 0.9, 'eval_runtime': 37.8445, 'eval_samples_per_second': 26.424, 'eval_steps_per_second': 0.846, 'epoch': 26.0}
+{'eval_loss': 0.8004008531570435, 'eval_accuracy': 0.891, 'eval_runtime': 37.8178, 'eval_samples_per_second': 26.443, 'eval_steps_per_second': 0.846, 'epoch': 27.0}
+{'loss': 0.0101, 'grad_norm': 0.0740148276090622, 'learning_rate': 4.4e-06, 'epoch': 28.0}

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

@@ -1 +1 @@
-{"eval/loss": 0.8004008531570435, "eval/accuracy": 0.891, "eval/runtime": 37.8178, "eval/samples_per_second": 26.443, "eval/steps_per_second": 0.846, "train/epoch": 27.0, "train/global_step": 3375, "_timestamp": 1727268785.055989, "_runtime": 59194.18307995796, "_step": 40, "train/loss": 0.0549, "train/grad_norm": 0.032662052661180496, "train/learning_rate": 5.2e-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}
+{"eval/loss": 0.7997801303863525, "eval/accuracy": 0.897, "eval/runtime": 38.1717, "eval/samples_per_second": 26.197, "eval/steps_per_second": 0.838, "train/epoch": 28.0, "train/global_step": 3500, "_timestamp": 1727270709.652195, "_runtime": 61118.779285907745, "_step": 42, "train/loss": 0.0101, "train/grad_norm": 0.0740148276090622, "train/learning_rate": 4.4e-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}

wandb/run-20240924_172630-x9iddikd/run-x9iddikd.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07cbb23f2b3426e59df7b95c480bb127d776dd8bcd8efd96e25ca736e2541d15
-size 1618004
+oid sha256:8aa86af247729fd956c4d628d7adbf3c015a2ac7e6db826b4752b9c618fb09e5
+size 1671225