| { | |
| "best_metric": 1.103180170059204, | |
| "best_model_checkpoint": "./outputs/checkpoint-800", | |
| "epoch": 1.0666666666666667, | |
| "eval_steps": 100, | |
| "global_step": 800, | |
| "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": 1.1820014715194702, | |
| "eval_runtime": 212.2382, | |
| "eval_samples_per_second": 9.094, | |
| "eval_steps_per_second": 1.14, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0116, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.1465147733688354, | |
| "eval_runtime": 185.6672, | |
| "eval_samples_per_second": 10.395, | |
| "eval_steps_per_second": 1.303, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9916, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.1323238611221313, | |
| "eval_runtime": 186.616, | |
| "eval_samples_per_second": 10.342, | |
| "eval_steps_per_second": 1.297, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9798, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.1225333213806152, | |
| "eval_runtime": 187.7396, | |
| "eval_samples_per_second": 10.28, | |
| "eval_steps_per_second": 1.289, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9658, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.1167433261871338, | |
| "eval_runtime": 186.8716, | |
| "eval_samples_per_second": 10.328, | |
| "eval_steps_per_second": 1.295, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9675, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.1117215156555176, | |
| "eval_runtime": 187.1986, | |
| "eval_samples_per_second": 10.31, | |
| "eval_steps_per_second": 1.293, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9639, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.107673168182373, | |
| "eval_runtime": 238.8707, | |
| "eval_samples_per_second": 8.08, | |
| "eval_steps_per_second": 1.013, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9532, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.103180170059204, | |
| "eval_runtime": 531.86, | |
| "eval_samples_per_second": 3.629, | |
| "eval_steps_per_second": 0.455, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 1.130969014206382e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |