| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0036527456471447703, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00012175818823815901, | |
| "eval_loss": NaN, | |
| "eval_runtime": 75.1275, | |
| "eval_samples_per_second": 46.042, | |
| "eval_steps_per_second": 23.028, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00036527456471447707, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 10.0115, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006087909411907951, | |
| "eval_loss": NaN, | |
| "eval_runtime": 74.8658, | |
| "eval_samples_per_second": 46.203, | |
| "eval_steps_per_second": 23.108, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007305491294289541, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010958236941434312, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0012175818823815902, | |
| "eval_loss": NaN, | |
| "eval_runtime": 74.8689, | |
| "eval_samples_per_second": 46.201, | |
| "eval_steps_per_second": 23.107, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0014610982588579083, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0018263728235723851, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0018263728235723851, | |
| "eval_loss": NaN, | |
| "eval_runtime": 75.0397, | |
| "eval_samples_per_second": 46.096, | |
| "eval_steps_per_second": 23.054, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0021916473882868624, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0024351637647631805, | |
| "eval_loss": NaN, | |
| "eval_runtime": 75.3071, | |
| "eval_samples_per_second": 45.932, | |
| "eval_steps_per_second": 22.973, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0025569219530013395, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0029221965177158166, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0030439547059539756, | |
| "eval_loss": NaN, | |
| "eval_runtime": 74.6521, | |
| "eval_samples_per_second": 46.335, | |
| "eval_steps_per_second": 23.174, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0032874710824302936, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0036527456471447703, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0036527456471447703, | |
| "eval_loss": NaN, | |
| "eval_runtime": 74.9324, | |
| "eval_samples_per_second": 46.162, | |
| "eval_steps_per_second": 23.087, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 775025873387520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |