| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020607934054611025, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010303967027305513, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010303967027305513, | |
| "eval_loss": NaN, | |
| "eval_runtime": 370.5125, | |
| "eval_samples_per_second": 4.413, | |
| "eval_steps_per_second": 2.208, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020607934054611026, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0030911901081916537, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004121586810922205, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3847, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005151983513652756, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005151983513652756, | |
| "eval_loss": NaN, | |
| "eval_runtime": 125.5004, | |
| "eval_samples_per_second": 13.028, | |
| "eval_steps_per_second": 6.518, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0061823802163833074, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0072127769191138585, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00824317362184441, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00927357032457496, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010303967027305513, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010303967027305513, | |
| "eval_loss": NaN, | |
| "eval_runtime": 118.5819, | |
| "eval_samples_per_second": 13.788, | |
| "eval_steps_per_second": 6.898, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011334363730036065, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012364760432766615, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013395157135497167, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014425553838227717, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015455950540958269, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015455950540958269, | |
| "eval_loss": NaN, | |
| "eval_runtime": 123.0732, | |
| "eval_samples_per_second": 13.285, | |
| "eval_steps_per_second": 6.646, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01648634724368882, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01751674394641937, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01854714064914992, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.019577537351880475, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.020607934054611025, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020607934054611025, | |
| "eval_loss": NaN, | |
| "eval_runtime": 140.2186, | |
| "eval_samples_per_second": 11.66, | |
| "eval_steps_per_second": 5.834, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.6179649667072e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |