| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.8910505836575875, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.19455252918287938, |
| "grad_norm": 9.538981437683105, |
| "learning_rate": 2.45e-05, |
| "loss": 3.3846, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.38910505836575876, |
| "grad_norm": 13.612791061401367, |
| "learning_rate": 4.9500000000000004e-05, |
| "loss": 2.703, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.5836575875486382, |
| "grad_norm": 7.535803318023682, |
| "learning_rate": 4.727777777777778e-05, |
| "loss": 1.3435, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.7782101167315175, |
| "grad_norm": 6.333610534667969, |
| "learning_rate": 4.4500000000000004e-05, |
| "loss": 0.482, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9727626459143969, |
| "grad_norm": 0.8552870154380798, |
| "learning_rate": 4.172222222222222e-05, |
| "loss": 0.1632, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.1673151750972763, |
| "grad_norm": 0.27692699432373047, |
| "learning_rate": 3.894444444444444e-05, |
| "loss": 0.0482, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.3618677042801557, |
| "grad_norm": 0.21171456575393677, |
| "learning_rate": 3.6166666666666674e-05, |
| "loss": 0.023, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.556420233463035, |
| "grad_norm": 0.08165864646434784, |
| "learning_rate": 3.338888888888889e-05, |
| "loss": 0.0145, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.7509727626459144, |
| "grad_norm": 0.14636413753032684, |
| "learning_rate": 3.061111111111111e-05, |
| "loss": 0.0111, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.9455252918287937, |
| "grad_norm": 0.07805858552455902, |
| "learning_rate": 2.7833333333333333e-05, |
| "loss": 0.0095, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.140077821011673, |
| "grad_norm": 0.0630631297826767, |
| "learning_rate": 2.5055555555555555e-05, |
| "loss": 0.0085, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.3346303501945527, |
| "grad_norm": 0.06998426467180252, |
| "learning_rate": 2.2277777777777778e-05, |
| "loss": 0.0074, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.529182879377432, |
| "grad_norm": 0.06766045093536377, |
| "learning_rate": 1.9500000000000003e-05, |
| "loss": 0.0065, |
| "step": 650 |
| }, |
| { |
| "epoch": 2.7237354085603114, |
| "grad_norm": 0.0542900487780571, |
| "learning_rate": 1.6722222222222222e-05, |
| "loss": 0.0061, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.9182879377431905, |
| "grad_norm": 0.03667410835623741, |
| "learning_rate": 1.3944444444444446e-05, |
| "loss": 0.0055, |
| "step": 750 |
| }, |
| { |
| "epoch": 3.11284046692607, |
| "grad_norm": 0.05161047354340553, |
| "learning_rate": 1.1166666666666668e-05, |
| "loss": 0.0053, |
| "step": 800 |
| }, |
| { |
| "epoch": 3.307392996108949, |
| "grad_norm": 0.03813894838094711, |
| "learning_rate": 8.38888888888889e-06, |
| "loss": 0.0053, |
| "step": 850 |
| }, |
| { |
| "epoch": 3.501945525291829, |
| "grad_norm": 0.03649824857711792, |
| "learning_rate": 5.611111111111112e-06, |
| "loss": 0.0049, |
| "step": 900 |
| }, |
| { |
| "epoch": 3.6964980544747084, |
| "grad_norm": 0.06335698813199997, |
| "learning_rate": 2.8333333333333335e-06, |
| "loss": 0.0046, |
| "step": 950 |
| }, |
| { |
| "epoch": 3.8910505836575875, |
| "grad_norm": 0.050193868577480316, |
| "learning_rate": 5.555555555555556e-08, |
| "loss": 0.0048, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.8910505836575875, |
| "step": 1000, |
| "total_flos": 2103876319641600.0, |
| "train_loss": 0.41208870258927344, |
| "train_runtime": 93.7422, |
| "train_samples_per_second": 85.34, |
| "train_steps_per_second": 10.668 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2103876319641600.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
