| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.8213166144200628, | |
| "eval_steps": 100, | |
| "global_step": 900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7896, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_runtime": 511.2401, | |
| "eval_samples_per_second": 1.76, | |
| "eval_steps_per_second": 0.221, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6216, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_runtime": 512.8833, | |
| "eval_samples_per_second": 1.755, | |
| "eval_steps_per_second": 0.22, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5863, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_runtime": 513.6336, | |
| "eval_samples_per_second": 1.752, | |
| "eval_steps_per_second": 0.22, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5528, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_runtime": 512.1927, | |
| "eval_samples_per_second": 1.757, | |
| "eval_steps_per_second": 0.221, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0002, | |
| "loss": 0.561, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_runtime": 512.2603, | |
| "eval_samples_per_second": 1.757, | |
| "eval_steps_per_second": 0.221, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5462, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_runtime": 512.6885, | |
| "eval_samples_per_second": 1.755, | |
| "eval_steps_per_second": 0.22, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5059, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_runtime": 512.3973, | |
| "eval_samples_per_second": 1.756, | |
| "eval_steps_per_second": 0.221, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4752, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_runtime": 513.4451, | |
| "eval_samples_per_second": 1.753, | |
| "eval_steps_per_second": 0.22, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 0.0002, | |
| "loss": 0.493, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_runtime": 512.3415, | |
| "eval_samples_per_second": 1.757, | |
| "eval_steps_per_second": 0.221, | |
| "step": 900 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 957, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 1.4940792341869363e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |