| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005446771426237098, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010893542852474196, | |
| "eval_loss": 4.965454578399658, | |
| "eval_runtime": 146.1989, | |
| "eval_samples_per_second": 26.443, | |
| "eval_steps_per_second": 13.222, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005446771426237097, | |
| "grad_norm": 2.617262125015259, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4074, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010893542852474195, | |
| "grad_norm": 3.2852272987365723, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7221, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010893542852474195, | |
| "eval_loss": 4.596639633178711, | |
| "eval_runtime": 146.8778, | |
| "eval_samples_per_second": 26.321, | |
| "eval_steps_per_second": 13.161, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016340314278711294, | |
| "grad_norm": 1.9587860107421875, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.1211, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002178708570494839, | |
| "grad_norm": 3.960905075073242, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.1157, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002178708570494839, | |
| "eval_loss": 3.9367244243621826, | |
| "eval_runtime": 147.1567, | |
| "eval_samples_per_second": 26.271, | |
| "eval_steps_per_second": 13.136, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002723385713118549, | |
| "grad_norm": 2.2079458236694336, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.8274, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0032680628557422587, | |
| "grad_norm": 2.1029868125915527, | |
| "learning_rate": 5e-05, | |
| "loss": 3.572, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0032680628557422587, | |
| "eval_loss": 3.6732211112976074, | |
| "eval_runtime": 147.1822, | |
| "eval_samples_per_second": 26.267, | |
| "eval_steps_per_second": 13.133, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0038127399983659688, | |
| "grad_norm": 3.5215439796447754, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.7833, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004357417140989678, | |
| "grad_norm": 1.7290146350860596, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.5714, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004357417140989678, | |
| "eval_loss": 3.5499491691589355, | |
| "eval_runtime": 147.1354, | |
| "eval_samples_per_second": 26.275, | |
| "eval_steps_per_second": 13.138, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004902094283613388, | |
| "grad_norm": 1.980006456375122, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.6728, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005446771426237098, | |
| "grad_norm": 2.2260336875915527, | |
| "learning_rate": 0.0, | |
| "loss": 3.2603, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005446771426237098, | |
| "eval_loss": 3.5256547927856445, | |
| "eval_runtime": 149.9294, | |
| "eval_samples_per_second": 25.785, | |
| "eval_steps_per_second": 12.893, | |
| "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": 4120744541552640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |