| { | |
| "best_metric": 1.0012787580490112, | |
| "best_model_checkpoint": "./outputs/checkpoint-800", | |
| "epoch": 1.1363636363636362, | |
| "eval_steps": 100, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5808, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.0812042951583862, | |
| "eval_runtime": 127.4925, | |
| "eval_samples_per_second": 11.703, | |
| "eval_steps_per_second": 1.467, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2145, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.0592867136001587, | |
| "eval_runtime": 124.4418, | |
| "eval_samples_per_second": 11.99, | |
| "eval_steps_per_second": 1.503, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0002, | |
| "loss": 1.201, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.0460368394851685, | |
| "eval_runtime": 124.1855, | |
| "eval_samples_per_second": 12.014, | |
| "eval_steps_per_second": 1.506, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1833, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.0355255603790283, | |
| "eval_runtime": 124.2488, | |
| "eval_samples_per_second": 12.008, | |
| "eval_steps_per_second": 1.505, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1733, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.0230828523635864, | |
| "eval_runtime": 124.322, | |
| "eval_samples_per_second": 12.001, | |
| "eval_steps_per_second": 1.504, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1612, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.0142004489898682, | |
| "eval_runtime": 124.2613, | |
| "eval_samples_per_second": 12.007, | |
| "eval_steps_per_second": 1.505, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1492, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.0080314874649048, | |
| "eval_runtime": 124.2662, | |
| "eval_samples_per_second": 12.006, | |
| "eval_steps_per_second": 1.505, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1391, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 1.0012787580490112, | |
| "eval_runtime": 124.3175, | |
| "eval_samples_per_second": 12.002, | |
| "eval_steps_per_second": 1.504, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2112, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 4.49771803278336e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |