| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06666666666666667, | |
| "grad_norm": 98.21472515172992, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.8595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 30.799283162433554, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3856, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 7.8774399080468624, | |
| "learning_rate": 1.9238795325112867e-05, | |
| "loss": 0.8251, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 4.085781086210361, | |
| "learning_rate": 1.7071067811865477e-05, | |
| "loss": 0.6043, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5420283079147339, | |
| "eval_runtime": 4.2361, | |
| "eval_samples_per_second": 46.977, | |
| "eval_steps_per_second": 0.944, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 2.0713099775720534, | |
| "learning_rate": 1.3826834323650899e-05, | |
| "loss": 0.4794, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 1.3136102966664787, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4248, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.1912342263078068, | |
| "learning_rate": 6.173165676349103e-06, | |
| "loss": 0.3922, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.4156629145145416, | |
| "eval_runtime": 4.0917, | |
| "eval_samples_per_second": 48.635, | |
| "eval_steps_per_second": 0.978, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.3333333333333335, | |
| "grad_norm": 1.1730848362574522, | |
| "learning_rate": 2.9289321881345257e-06, | |
| "loss": 0.3075, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.9598398180975349, | |
| "learning_rate": 7.612046748871327e-07, | |
| "loss": 0.2917, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.3661284541735195, | |
| "learning_rate": 0.0, | |
| "loss": 0.2791, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.40715718269348145, | |
| "eval_runtime": 4.0987, | |
| "eval_samples_per_second": 48.552, | |
| "eval_steps_per_second": 0.976, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 45, | |
| "total_flos": 18844169011200.0, | |
| "train_loss": 0.5649417373869154, | |
| "train_runtime": 363.236, | |
| "train_samples_per_second": 14.85, | |
| "train_steps_per_second": 0.124 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 45, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 18844169011200.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |