| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11080332409972299, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00221606648199446, | |
| "eval_loss": 7.328528881072998, | |
| "eval_runtime": 2.3225, | |
| "eval_samples_per_second": 81.808, | |
| "eval_steps_per_second": 40.904, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0110803324099723, | |
| "grad_norm": 2.707282543182373, | |
| "learning_rate": 5e-05, | |
| "loss": 7.5495, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0221606648199446, | |
| "grad_norm": 3.696916103363037, | |
| "learning_rate": 0.0001, | |
| "loss": 7.563, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0221606648199446, | |
| "eval_loss": 7.302117824554443, | |
| "eval_runtime": 2.3313, | |
| "eval_samples_per_second": 81.498, | |
| "eval_steps_per_second": 40.749, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0332409972299169, | |
| "grad_norm": 3.3045547008514404, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 7.5864, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0443213296398892, | |
| "grad_norm": 3.0436172485351562, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.2658, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0443213296398892, | |
| "eval_loss": 7.21406364440918, | |
| "eval_runtime": 2.4418, | |
| "eval_samples_per_second": 77.812, | |
| "eval_steps_per_second": 38.906, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.055401662049861494, | |
| "grad_norm": 2.5342953205108643, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 7.3682, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0664819944598338, | |
| "grad_norm": 3.4554083347320557, | |
| "learning_rate": 5e-05, | |
| "loss": 7.452, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0664819944598338, | |
| "eval_loss": 7.143843173980713, | |
| "eval_runtime": 2.5404, | |
| "eval_samples_per_second": 74.791, | |
| "eval_steps_per_second": 37.395, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07756232686980609, | |
| "grad_norm": 2.839083433151245, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 7.7212, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0886426592797784, | |
| "grad_norm": 3.4022929668426514, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 7.7581, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0886426592797784, | |
| "eval_loss": 7.109482765197754, | |
| "eval_runtime": 2.3967, | |
| "eval_samples_per_second": 79.276, | |
| "eval_steps_per_second": 39.638, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0997229916897507, | |
| "grad_norm": 3.1520068645477295, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 7.2416, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11080332409972299, | |
| "grad_norm": 2.7106244564056396, | |
| "learning_rate": 0.0, | |
| "loss": 7.1099, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11080332409972299, | |
| "eval_loss": 7.102914810180664, | |
| "eval_runtime": 2.3533, | |
| "eval_samples_per_second": 80.736, | |
| "eval_steps_per_second": 40.368, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3277927219200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |