| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015432098765432098, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00051440329218107, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.1905, | |
| "eval_samples_per_second": 14.84, | |
| "eval_steps_per_second": 7.429, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015432098765432098, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00257201646090535, | |
| "eval_loss": NaN, | |
| "eval_runtime": 54.6584, | |
| "eval_samples_per_second": 14.984, | |
| "eval_steps_per_second": 7.501, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0030864197530864196, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004629629629629629, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0051440329218107, | |
| "eval_loss": NaN, | |
| "eval_runtime": 54.6298, | |
| "eval_samples_per_second": 14.992, | |
| "eval_steps_per_second": 7.505, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006172839506172839, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007716049382716049, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007716049382716049, | |
| "eval_loss": NaN, | |
| "eval_runtime": 54.7497, | |
| "eval_samples_per_second": 14.959, | |
| "eval_steps_per_second": 7.489, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009259259259259259, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0102880658436214, | |
| "eval_loss": NaN, | |
| "eval_runtime": 54.7078, | |
| "eval_samples_per_second": 14.97, | |
| "eval_steps_per_second": 7.494, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010802469135802469, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012345679012345678, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01286008230452675, | |
| "eval_loss": NaN, | |
| "eval_runtime": 54.7188, | |
| "eval_samples_per_second": 14.967, | |
| "eval_steps_per_second": 7.493, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013888888888888888, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.015432098765432098, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015432098765432098, | |
| "eval_loss": NaN, | |
| "eval_runtime": 54.7004, | |
| "eval_samples_per_second": 14.972, | |
| "eval_steps_per_second": 7.495, | |
| "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": 1.2612083820527616e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |