marcelovidigal commited on
Commit
107a53b
1 Parent(s): 89eff64

Training in progress, epoch 24

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1834e52baaa43ec8f79f4ce6c7e66f44481932e5c737a1f3e511d89d0f9c973
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:736043bf76f3ab6365f7724d9b1ede0a15d45af690c9549129ba733cf32bc145
3
  size 267832560
wandb/debug-internal.log CHANGED
The diff for this file is too large to render. See raw diff
 
wandb/run-20240924_172630-x9iddikd/files/output.log CHANGED
@@ -58,3 +58,6 @@ You should probably TRAIN this model on a down-stream task to be able to use it
58
  {'eval_loss': 0.5195603966712952, 'eval_accuracy': 0.92, 'eval_runtime': 37.9909, 'eval_samples_per_second': 26.322, 'eval_steps_per_second': 0.842, 'epoch': 20.0}
59
  {'eval_loss': 0.8739770650863647, 'eval_accuracy': 0.617, 'eval_runtime': 213.6265, 'eval_samples_per_second': 4.681, 'eval_steps_per_second': 0.15, 'epoch': 21.0}
60
  {'eval_loss': 0.633865237236023, 'eval_accuracy': 0.901, 'eval_runtime': 38.1393, 'eval_samples_per_second': 26.22, 'eval_steps_per_second': 0.839, 'epoch': 22.0}
 
 
 
 
58
  {'eval_loss': 0.5195603966712952, 'eval_accuracy': 0.92, 'eval_runtime': 37.9909, 'eval_samples_per_second': 26.322, 'eval_steps_per_second': 0.842, 'epoch': 20.0}
59
  {'eval_loss': 0.8739770650863647, 'eval_accuracy': 0.617, 'eval_runtime': 213.6265, 'eval_samples_per_second': 4.681, 'eval_steps_per_second': 0.15, 'epoch': 21.0}
60
  {'eval_loss': 0.633865237236023, 'eval_accuracy': 0.901, 'eval_runtime': 38.1393, 'eval_samples_per_second': 26.22, 'eval_steps_per_second': 0.839, 'epoch': 22.0}
61
+ {'eval_loss': 0.5776236653327942, 'eval_accuracy': 0.92, 'eval_runtime': 38.5846, 'eval_samples_per_second': 25.917, 'eval_steps_per_second': 0.829, 'epoch': 23.0}
62
+ wandb: Network error (SSLError), entering retry loop.
63
+ {'loss': 0.0549, 'grad_norm': 0.032662052661180496, 'learning_rate': 5.2e-06, 'epoch': 24.0}
wandb/run-20240924_172630-x9iddikd/files/wandb-summary.json CHANGED
@@ -1 +1 @@
1
- {"eval/loss": 0.5776236653327942, "eval/accuracy": 0.92, "eval/runtime": 38.5846, "eval/samples_per_second": 25.917, "eval/steps_per_second": 0.829, "train/epoch": 23.0, "train/global_step": 2875, "_timestamp": 1727261356.326705, "_runtime": 51765.45379590988, "_step": 35, "train/loss": 0.0187, "train/grad_norm": 0.01947682909667492, "train/learning_rate": 6e-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}
 
1
+ {"eval/loss": 0.6649676561355591, "eval/accuracy": 0.907, "eval/runtime": 38.4215, "eval/samples_per_second": 26.027, "eval/steps_per_second": 0.833, "train/epoch": 24.0, "train/global_step": 3000, "_timestamp": 1727263161.486521, "_runtime": 53570.61361193657, "_step": 37, "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}
wandb/run-20240924_172630-x9iddikd/logs/debug-internal.log CHANGED
The diff for this file is too large to render. See raw diff
 
wandb/run-20240924_172630-x9iddikd/run-x9iddikd.wandb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2187cd64b9e2dfea48b82dc832a1b6b7e9eedfe310dc17475b42426309aed7d
3
- size 1417839
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a6f322c95eefea03b2775d4e915064670f7651f1d539964895ecfc818938631
3
+ size 1465912