| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.20312817387771684, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019076305220883533, | |
| "loss": 1.5978, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00018072289156626507, | |
| "loss": 1.4283, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00017068273092369477, | |
| "loss": 1.292, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001606425702811245, | |
| "loss": 1.3651, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00015060240963855423, | |
| "loss": 1.4043, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00014056224899598393, | |
| "loss": 1.2977, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00013052208835341366, | |
| "loss": 1.3784, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001204819277108434, | |
| "loss": 1.3583, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001104417670682731, | |
| "loss": 1.3814, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00010040160642570282, | |
| "loss": 1.2614, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.036144578313253e-05, | |
| "loss": 1.3198, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.032128514056225e-05, | |
| "loss": 1.3631, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 7.028112449799197e-05, | |
| "loss": 1.3766, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 6.02409638554217e-05, | |
| "loss": 1.3293, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 5.020080321285141e-05, | |
| "loss": 1.2684, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.0160642570281125e-05, | |
| "loss": 1.3215, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.012048192771085e-05, | |
| "loss": 1.3013, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.0080321285140562e-05, | |
| "loss": 1.3356, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.0040160642570281e-05, | |
| "loss": 1.352, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0, | |
| "loss": 1.3319, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 2.762902175485133e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |