| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00020355529681415606, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.071105936283121e-06, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4407.1661, | |
| "eval_samples_per_second": 23.467, | |
| "eval_steps_per_second": 11.734, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0355529681415605e-05, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.071105936283121e-05, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.071105936283121e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4392.4822, | |
| "eval_samples_per_second": 23.546, | |
| "eval_steps_per_second": 11.773, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.106658904424681e-05, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 8.142211872566242e-05, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 8.142211872566242e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4418.0183, | |
| "eval_samples_per_second": 23.41, | |
| "eval_steps_per_second": 11.705, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00010177764840707803, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00012213317808849362, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00012213317808849362, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4412.3446, | |
| "eval_samples_per_second": 23.44, | |
| "eval_steps_per_second": 11.72, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00014248870776990924, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00016284423745132484, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00016284423745132484, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4463.5545, | |
| "eval_samples_per_second": 23.171, | |
| "eval_steps_per_second": 11.586, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00018319976713274043, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00020355529681415606, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00020355529681415606, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4395.7779, | |
| "eval_samples_per_second": 23.528, | |
| "eval_steps_per_second": 11.764, | |
| "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": 3478615228416000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |