Training in progress, epoch 4

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wandb/run-20240923_004152-7jibscvo/run-7jibscvo.wandb filter=lfs diff=lfs merge=lfs -text

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d16899c96c3df71080ce0e7df58e2205dcfcf86c4e8331937636a0d9789723
+oid sha256:e289702a2b503dd7f03f3a1d16998f5906223eee0c021ac8095849d7fac813ad
 size 267832560

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

@@ -15,3 +15,8 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 {'loss': 0.08, 'grad_norm': 0.046891484409570694, 'learning_rate': 9.763275751759437e-06, 'epoch': 2.56}
 {'loss': 0.0893, 'grad_norm': 0.06083718314766884, 'learning_rate': 8.483685220729368e-06, 'epoch': 2.88}
 wandb: ERROR Error while calling W&B API: context deadline exceeded (<Response [500]>)
+{'eval_loss': 0.2804093658924103, 'eval_accuracy': 0.93296, 'eval_runtime': 1235.9411, 'eval_samples_per_second': 20.228, 'eval_steps_per_second': 1.265, 'epoch': 3.0}
+{'loss': 0.0667, 'grad_norm': 0.16060642898082733, 'learning_rate': 7.204094689699297e-06, 'epoch': 3.2}
+{'loss': 0.0535, 'grad_norm': 0.03821321576833725, 'learning_rate': 5.924504158669226e-06, 'epoch': 3.52}
+{'loss': 0.0489, 'grad_norm': 0.34995952248573303, 'learning_rate': 4.644913627639156e-06, 'epoch': 3.84}
+wandb: ERROR Error while calling W&B API: context deadline exceeded (<Response [500]>)

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

@@ -1 +1 @@
-{"train/loss": 0.0893, "train/grad_norm": 0.06083718314766884, "train/learning_rate": 8.483685220729368e-06, "train/epoch": 3.0, "train/global_step": 4689, "_timestamp": 1727098789.535688, "_runtime": 35877.417692899704, "_step": 11, "eval/loss": 0.2804093658924103, "eval/accuracy": 0.93296, "eval/runtime": 1235.9411, "eval/samples_per_second": 20.228, "eval/steps_per_second": 1.265}
+{"train/loss": 0.0489, "train/grad_norm": 0.34995952248573303, "train/learning_rate": 4.644913627639156e-06, "train/epoch": 4.0, "train/global_step": 6252, "_timestamp": 1727111455.571572, "_runtime": 48543.453577041626, "_step": 15, "eval/loss": 0.34566619992256165, "eval/accuracy": 0.93168, "eval/runtime": 847.1597, "eval/samples_per_second": 29.51, "eval/steps_per_second": 1.845}