| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008147967082212987, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016295934164425977, | |
| "eval_loss": 2.0260169506073, | |
| "eval_runtime": 94.9594, | |
| "eval_samples_per_second": 27.212, | |
| "eval_steps_per_second": 13.606, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016295934164425976, | |
| "grad_norm": 0.6981315016746521, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 1.8912, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002118471441375377, | |
| "eval_loss": 1.6084959506988525, | |
| "eval_runtime": 94.0227, | |
| "eval_samples_per_second": 27.483, | |
| "eval_steps_per_second": 13.741, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003259186832885195, | |
| "grad_norm": 0.8355132341384888, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.4406, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004236942882750754, | |
| "eval_loss": 1.5320667028427124, | |
| "eval_runtime": 94.0645, | |
| "eval_samples_per_second": 27.471, | |
| "eval_steps_per_second": 13.735, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0048887802493277925, | |
| "grad_norm": 0.6931689381599426, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.4291, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006355414324126131, | |
| "eval_loss": 1.5109944343566895, | |
| "eval_runtime": 94.0023, | |
| "eval_samples_per_second": 27.489, | |
| "eval_steps_per_second": 13.744, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00651837366577039, | |
| "grad_norm": 0.7098925709724426, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 1.3539, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008147967082212987, | |
| "grad_norm": 0.685785710811615, | |
| "learning_rate": 0.0, | |
| "loss": 1.4113, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 1.054606670954496e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |