Training in progress, epoch 48

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3335c1da6b2d61ae7ee30323d9e4f65bc16b91baaa8c2627dfcff66458e70e02
+oid sha256:50d3e8dd429c87a30f6e860779a46ed81d455044eff4dccb8c45934cecbf4115
 size 267832560

wandb/debug-internal.log

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5216d97e88268bfbb3d705abb9cd9a0273a69a774acc2aaf594e1cf29a9992
-size 14659586
+oid sha256:7a6ca1aac1e692bccbf9af51395a5ae7de6b739f51b4524495fe07f5998d0c15
+size 14773130

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

@@ -89,3 +89,5 @@ wandb: Network error (SSLError), entering retry loop.
 {'eval_loss': 0.6526206731796265, 'eval_accuracy': 0.917, 'eval_runtime': 37.8543, 'eval_samples_per_second': 26.417, 'eval_steps_per_second': 0.845, 'epoch': 44.0}
 {'eval_loss': 0.6948218941688538, 'eval_accuracy': 0.909, 'eval_runtime': 37.9107, 'eval_samples_per_second': 26.378, 'eval_steps_per_second': 0.844, 'epoch': 45.0}
 {'eval_loss': 0.7213398218154907, 'eval_accuracy': 0.907, 'eval_runtime': 38.4455, 'eval_samples_per_second': 26.011, 'eval_steps_per_second': 0.832, 'epoch': 46.0}
+{'eval_loss': 0.6751002669334412, 'eval_accuracy': 0.913, 'eval_runtime': 38.6152, 'eval_samples_per_second': 25.897, 'eval_steps_per_second': 0.829, 'epoch': 47.0}
+{'loss': 0.0058, 'grad_norm': 0.0415799506008625, 'learning_rate': 4.0000000000000003e-07, 'epoch': 48.0}

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

@@ -1 +1 @@
-{"eval/loss": 0.6751002669334412, "eval/accuracy": 0.913, "eval/runtime": 38.6152, "eval/samples_per_second": 25.897, "eval/steps_per_second": 0.829, "train/epoch": 47.0, "train/global_step": 5875, "_timestamp": 1727305060.453245, "_runtime": 95469.58033585548, "_step": 65, "train/loss": 0.0049, "train/grad_norm": 0.007690785452723503, "train/learning_rate": 1.2000000000000002e-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": 0.6941944360733032, "eval/accuracy": 0.911, "eval/runtime": 36.9414, "eval/samples_per_second": 27.07, "eval/steps_per_second": 0.866, "train/epoch": 48.0, "train/global_step": 6000, "_timestamp": 1727306724.396482, "_runtime": 97133.52357292175, "_step": 67, "train/loss": 0.0058, "train/grad_norm": 0.0415799506008625, "train/learning_rate": 4.0000000000000003e-07, "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/logs/debug-internal.log

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5216d97e88268bfbb3d705abb9cd9a0273a69a774acc2aaf594e1cf29a9992
-size 14659586
+oid sha256:7a6ca1aac1e692bccbf9af51395a5ae7de6b739f51b4524495fe07f5998d0c15
+size 14773130

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a52498c342f7cb3cb48ad2f5a25f3615353f63cc594a247e338f844424f16a8d
-size 2600614
+oid sha256:6bcc562aae3a4ad729d4c4e2bba1cd7240e54bc7c19bdd8875872f768a6af53f
+size 2646325