| { | |
| "best_metric": 0.7995160818099976, | |
| "best_model_checkpoint": "ctllama13bnsem/checkpoint-18", | |
| "epoch": 5.085714285714285, | |
| "eval_steps": 500, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.0205086469650269, | |
| "eval_runtime": 15.9897, | |
| "eval_samples_per_second": 5.378, | |
| "eval_steps_per_second": 0.563, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 0.9894978404045105, | |
| "eval_runtime": 15.9229, | |
| "eval_samples_per_second": 5.401, | |
| "eval_steps_per_second": 0.565, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 7.61904761904762e-06, | |
| "loss": 0.9836, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 0.9659651517868042, | |
| "eval_runtime": 15.9785, | |
| "eval_samples_per_second": 5.382, | |
| "eval_steps_per_second": 0.563, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "eval_loss": 0.9247913360595703, | |
| "eval_runtime": 15.9478, | |
| "eval_samples_per_second": 5.393, | |
| "eval_steps_per_second": 0.564, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_loss": 0.8596590757369995, | |
| "eval_runtime": 15.9282, | |
| "eval_samples_per_second": 5.399, | |
| "eval_steps_per_second": 0.565, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1.523809523809524e-05, | |
| "loss": 0.9024, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "eval_loss": 0.7995160818099976, | |
| "eval_runtime": 15.9408, | |
| "eval_samples_per_second": 5.395, | |
| "eval_steps_per_second": 0.565, | |
| "step": 18 | |
| } | |
| ], | |
| "logging_steps": 8, | |
| "max_steps": 210, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "total_flos": 2.890598298995917e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |