| { | |
| "best_metric": 1.1068408489227295, | |
| "best_model_checkpoint": "./outputs/checkpoint-700", | |
| "epoch": 0.9333333333333333, | |
| "eval_steps": 100, | |
| "global_step": 700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2967, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.1817998886108398, | |
| "eval_runtime": 187.6804, | |
| "eval_samples_per_second": 10.283, | |
| "eval_steps_per_second": 1.289, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0115, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.1461560726165771, | |
| "eval_runtime": 186.2762, | |
| "eval_samples_per_second": 10.361, | |
| "eval_steps_per_second": 1.299, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9918, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.1315025091171265, | |
| "eval_runtime": 186.4761, | |
| "eval_samples_per_second": 10.35, | |
| "eval_steps_per_second": 1.298, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9798, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.1221688985824585, | |
| "eval_runtime": 186.7425, | |
| "eval_samples_per_second": 10.335, | |
| "eval_steps_per_second": 1.296, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9657, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.1161261796951294, | |
| "eval_runtime": 186.7488, | |
| "eval_samples_per_second": 10.335, | |
| "eval_steps_per_second": 1.296, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9675, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.111202597618103, | |
| "eval_runtime": 186.3885, | |
| "eval_samples_per_second": 10.355, | |
| "eval_steps_per_second": 1.298, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9638, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.1068408489227295, | |
| "eval_runtime": 186.3328, | |
| "eval_samples_per_second": 10.358, | |
| "eval_steps_per_second": 1.299, | |
| "step": 700 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 9.898653051450163e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |