| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002333495381623724, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.778317938745747e-05, | |
| "eval_loss": 4.1108784675598145, | |
| "eval_runtime": 313.3219, | |
| "eval_samples_per_second": 17.279, | |
| "eval_steps_per_second": 8.64, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023334953816237238, | |
| "grad_norm": 2.194282054901123, | |
| "learning_rate": 6e-05, | |
| "loss": 4.0209, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00046669907632474475, | |
| "grad_norm": 2.6679859161376953, | |
| "learning_rate": 0.00012, | |
| "loss": 3.8277, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006222654350996597, | |
| "eval_loss": 3.1946327686309814, | |
| "eval_runtime": 312.5781, | |
| "eval_samples_per_second": 17.32, | |
| "eval_steps_per_second": 8.66, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007000486144871172, | |
| "grad_norm": 3.270036458969116, | |
| "learning_rate": 0.00018, | |
| "loss": 3.4381, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009333981526494895, | |
| "grad_norm": 3.049503803253174, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.7467, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001166747690811862, | |
| "grad_norm": 3.1581685543060303, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.6757, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012445308701993195, | |
| "eval_loss": 2.4906089305877686, | |
| "eval_runtime": 312.6477, | |
| "eval_samples_per_second": 17.317, | |
| "eval_steps_per_second": 8.658, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0014000972289742344, | |
| "grad_norm": 2.7577967643737793, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.5934, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016334467671366066, | |
| "grad_norm": 2.3414273262023926, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.3222, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001866796305298979, | |
| "grad_norm": 3.0098507404327393, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.3274, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001866796305298979, | |
| "eval_loss": 2.291135549545288, | |
| "eval_runtime": 312.7717, | |
| "eval_samples_per_second": 17.31, | |
| "eval_steps_per_second": 8.655, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0021001458434613514, | |
| "grad_norm": 2.405668020248413, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.455, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002333495381623724, | |
| "grad_norm": 2.5914838314056396, | |
| "learning_rate": 0.0, | |
| "loss": 2.5107, | |
| "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": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |