| { | |
| "best_metric": 0.40839770436286926, | |
| "best_model_checkpoint": "/content/drive/MyDrive/colab/checkpoint-1700", | |
| "epoch": 1.6346153846153846, | |
| "global_step": 1700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.7596153846153844e-05, | |
| "loss": 1.033, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.6874200105667114, | |
| "eval_runtime": 57.2656, | |
| "eval_samples_per_second": 16.153, | |
| "eval_steps_per_second": 2.026, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.519230769230769e-05, | |
| "loss": 0.6703, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 0.5938639044761658, | |
| "eval_runtime": 57.2626, | |
| "eval_samples_per_second": 16.154, | |
| "eval_steps_per_second": 2.026, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.278846153846154e-05, | |
| "loss": 0.6579, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 0.49521076679229736, | |
| "eval_runtime": 57.2701, | |
| "eval_samples_per_second": 16.152, | |
| "eval_steps_per_second": 2.025, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.038461538461539e-05, | |
| "loss": 0.5068, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.5416558384895325, | |
| "eval_runtime": 57.2833, | |
| "eval_samples_per_second": 16.148, | |
| "eval_steps_per_second": 2.025, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 3.798076923076923e-05, | |
| "loss": 0.5439, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.5001481175422668, | |
| "eval_runtime": 57.2802, | |
| "eval_samples_per_second": 16.149, | |
| "eval_steps_per_second": 2.025, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.557692307692308e-05, | |
| "loss": 0.5429, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.47204354405403137, | |
| "eval_runtime": 57.2593, | |
| "eval_samples_per_second": 16.155, | |
| "eval_steps_per_second": 2.026, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.3173076923076926e-05, | |
| "loss": 0.4817, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.5970540642738342, | |
| "eval_runtime": 57.2593, | |
| "eval_samples_per_second": 16.155, | |
| "eval_steps_per_second": 2.026, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.5023, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.44290876388549805, | |
| "eval_runtime": 57.2393, | |
| "eval_samples_per_second": 16.16, | |
| "eval_steps_per_second": 2.027, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 2.8365384615384616e-05, | |
| "loss": 0.4756, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.49230891466140747, | |
| "eval_runtime": 57.0994, | |
| "eval_samples_per_second": 16.2, | |
| "eval_steps_per_second": 2.032, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.5961538461538464e-05, | |
| "loss": 0.4772, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.4519612491130829, | |
| "eval_runtime": 57.1095, | |
| "eval_samples_per_second": 16.197, | |
| "eval_steps_per_second": 2.031, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 2.355769230769231e-05, | |
| "loss": 0.336, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 0.41091373562812805, | |
| "eval_runtime": 57.1093, | |
| "eval_samples_per_second": 16.197, | |
| "eval_steps_per_second": 2.031, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 2.1153846153846154e-05, | |
| "loss": 0.2225, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 0.4540548324584961, | |
| "eval_runtime": 57.116, | |
| "eval_samples_per_second": 16.195, | |
| "eval_steps_per_second": 2.031, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.2296, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.4974042475223541, | |
| "eval_runtime": 57.1073, | |
| "eval_samples_per_second": 16.198, | |
| "eval_steps_per_second": 2.031, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.6346153846153847e-05, | |
| "loss": 0.2511, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 0.48081809282302856, | |
| "eval_runtime": 57.1059, | |
| "eval_samples_per_second": 16.198, | |
| "eval_steps_per_second": 2.031, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.3942307692307693e-05, | |
| "loss": 0.3349, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 0.4536380171775818, | |
| "eval_runtime": 57.096, | |
| "eval_samples_per_second": 16.201, | |
| "eval_steps_per_second": 2.032, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.153846153846154e-05, | |
| "loss": 0.2529, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 0.4738934636116028, | |
| "eval_runtime": 57.1337, | |
| "eval_samples_per_second": 16.19, | |
| "eval_steps_per_second": 2.03, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.134615384615384e-06, | |
| "loss": 0.2064, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 0.40839770436286926, | |
| "eval_runtime": 57.1173, | |
| "eval_samples_per_second": 16.195, | |
| "eval_steps_per_second": 2.031, | |
| "step": 1700 | |
| } | |
| ], | |
| "max_steps": 2080, | |
| "num_train_epochs": 2, | |
| "total_flos": 3578535250329600.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |