Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e816fdda6bc8f7c7116b4bc7cf956f6e9b22468f07ff8a604a912b470a4d5b
+oid sha256:806bf53cb67d164eceb27c2bda7203b50c1bc8336ad79beead3992c948e3f3e0
 size 267832560

wandb/run-20240924_172630-x9iddikd/files/config.yaml

@@ -78,6 +78,18 @@ _wandb:
       5: 1
       6:
       - 1
+    - 1: train/loss
+      5: 1
+      6:
+      - 1
+    - 1: train/grad_norm
+      5: 1
+      6:
+      - 1
+    - 1: train/learning_rate
+      5: 1
+      6:
+      - 1
 vocab_size:
   desc: null
   value: 30522

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

@@ -19,3 +19,5 @@ dados_tokenizados:
   warnings.warn(
 Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert/distilbert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight', 'pre_classifier.bias', 'pre_classifier.weight']
 You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+{'eval_loss': 0.21834564208984375, 'eval_accuracy': 0.938, 'eval_runtime': 30.3683, 'eval_samples_per_second': 32.929, 'eval_steps_per_second': 2.075, 'epoch': 1.0}
+{'loss': 0.2031, 'grad_norm': 1.1480563879013062, 'learning_rate': 1.2e-05, 'epoch': 2.0}

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

@@ -1 +1 @@
-{"eval/loss": 0.21834564208984375, "eval/accuracy": 0.938, "eval/runtime": 30.3683, "eval/samples_per_second": 32.929, "eval/steps_per_second": 2.075, "train/epoch": 1.0, "train/global_step": 250, "_timestamp": 1727211087.91596, "_runtime": 1497.0430510044098, "_step": 0}
+{"eval/loss": 0.19427122175693512, "eval/accuracy": 0.938, "eval/runtime": 42.2287, "eval/samples_per_second": 23.681, "eval/steps_per_second": 1.492, "train/epoch": 2.0, "train/global_step": 500, "_timestamp": 1727212675.9347782, "_runtime": 3085.0618691444397, "_step": 2, "train/loss": 0.2031, "train/grad_norm": 1.1480563879013062, "train/learning_rate": 1.2e-05}