| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010684902233144567, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021369804466289135, | |
| "eval_loss": 1.5773454904556274, | |
| "eval_runtime": 118.2523, | |
| "eval_samples_per_second": 16.668, | |
| "eval_steps_per_second": 8.338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010684902233144566, | |
| "grad_norm": 0.4827723801136017, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5668, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0021369804466289132, | |
| "grad_norm": 0.6160764694213867, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5552, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0021369804466289132, | |
| "eval_loss": 1.4876762628555298, | |
| "eval_runtime": 119.0975, | |
| "eval_samples_per_second": 16.549, | |
| "eval_steps_per_second": 8.279, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00320547066994337, | |
| "grad_norm": 0.6216351389884949, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3548, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0042739608932578265, | |
| "grad_norm": 0.7345758080482483, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.2795, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0042739608932578265, | |
| "eval_loss": 1.193414330482483, | |
| "eval_runtime": 119.3404, | |
| "eval_samples_per_second": 16.516, | |
| "eval_steps_per_second": 8.262, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005342451116572284, | |
| "grad_norm": 0.9429499506950378, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.107, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00641094133988674, | |
| "grad_norm": 1.3308780193328857, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0876, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00641094133988674, | |
| "eval_loss": 1.0294039249420166, | |
| "eval_runtime": 119.5672, | |
| "eval_samples_per_second": 16.484, | |
| "eval_steps_per_second": 8.246, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0074794315632011965, | |
| "grad_norm": 0.9884252548217773, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9636, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008547921786515653, | |
| "grad_norm": 1.1601450443267822, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0531, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008547921786515653, | |
| "eval_loss": 0.9861201047897339, | |
| "eval_runtime": 122.6743, | |
| "eval_samples_per_second": 16.067, | |
| "eval_steps_per_second": 8.038, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00961641200983011, | |
| "grad_norm": 1.0654785633087158, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0357, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.010684902233144567, | |
| "grad_norm": 1.1575531959533691, | |
| "learning_rate": 0.0, | |
| "loss": 1.036, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010684902233144567, | |
| "eval_loss": 0.9808083176612854, | |
| "eval_runtime": 118.7678, | |
| "eval_samples_per_second": 16.595, | |
| "eval_steps_per_second": 8.302, | |
| "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": 8215821130137600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |