| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.049714143673875215, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009942828734775043, | |
| "eval_loss": 1.4713083505630493, | |
| "eval_runtime": 41.0881, | |
| "eval_samples_per_second": 10.319, | |
| "eval_steps_per_second": 5.16, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004971414367387522, | |
| "grad_norm": 0.21608084440231323, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3856, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009942828734775044, | |
| "grad_norm": 0.31701576709747314, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4978, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009942828734775044, | |
| "eval_loss": 1.4501210451126099, | |
| "eval_runtime": 41.5997, | |
| "eval_samples_per_second": 10.192, | |
| "eval_steps_per_second": 5.096, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014914243102162566, | |
| "grad_norm": 0.31124842166900635, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4985, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019885657469550087, | |
| "grad_norm": 0.3525506258010864, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4762, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019885657469550087, | |
| "eval_loss": 1.3944728374481201, | |
| "eval_runtime": 41.6537, | |
| "eval_samples_per_second": 10.179, | |
| "eval_steps_per_second": 5.09, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024857071836937607, | |
| "grad_norm": 0.35662373900413513, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3472, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02982848620432513, | |
| "grad_norm": 0.37102416157722473, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4188, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02982848620432513, | |
| "eval_loss": 1.3662049770355225, | |
| "eval_runtime": 41.773, | |
| "eval_samples_per_second": 10.15, | |
| "eval_steps_per_second": 5.075, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03479990057171265, | |
| "grad_norm": 0.3638223707675934, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3827, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.039771314939100175, | |
| "grad_norm": 0.3954694867134094, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3236, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.039771314939100175, | |
| "eval_loss": 1.3565930128097534, | |
| "eval_runtime": 41.8602, | |
| "eval_samples_per_second": 10.129, | |
| "eval_steps_per_second": 5.064, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0447427293064877, | |
| "grad_norm": 0.3389461934566498, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1909, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.049714143673875215, | |
| "grad_norm": 0.37343329191207886, | |
| "learning_rate": 0.0, | |
| "loss": 1.3179, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.049714143673875215, | |
| "eval_loss": 1.3546466827392578, | |
| "eval_runtime": 41.7489, | |
| "eval_samples_per_second": 10.156, | |
| "eval_steps_per_second": 5.078, | |
| "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": 1.4706319822946304e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |