Training in progress, epoch 1

logging.jsonl

@@ -1,2 +1,4 @@
 {"loss": 0.32817921, "grad_norm": 0.15581589, "learning_rate": 1e-05, "token_acc": 0.92229585, "epoch": 1.0, "global_step/max_steps": "1/1", "percentage": "100.00%", "elapsed_time": "11s", "remaining_time": "0s", "memory(GiB)": 22.22, "train_speed(iter/s)": 0.086502}
 {"eval_loss": 0.22503923, "eval_runtime": 3.86, "eval_samples_per_second": 0.518, "eval_steps_per_second": 0.259, "eval_token_acc": 0.94509159, "epoch": 1.0, "global_step/max_steps": "1/1", "percentage": "100.00%", "elapsed_time": "15s", "remaining_time": "0s", "memory(GiB)": 39.15, "train_speed(iter/s)": 0.064698}
+{"eval_loss": 0.22503923, "eval_runtime": 3.7326, "eval_samples_per_second": 0.536, "eval_steps_per_second": 0.268, "eval_token_acc": 0.94509159, "epoch": 1.0, "global_step/max_steps": "1/1", "percentage": "100.00%", "elapsed_time": "21s", "remaining_time": "0s", "memory(GiB)": 39.15, "train_speed(iter/s)": 0.046011}
+{"train_runtime": 26.378, "train_samples_per_second": 0.341, "train_steps_per_second": 0.038, "total_flos": 10981327503360.0, "train_loss": 0.32817921, "epoch": 1.0, "global_step/max_steps": "1/1", "percentage": "100.00%", "elapsed_time": "24s", "remaining_time": "0s", "memory(GiB)": 39.15, "train_speed(iter/s)": 0.041489}