| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019980267284282717, | |
| "loss": 1.8035, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 1.7043, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001982287250728689, | |
| "loss": 1.5984, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001968583161128631, | |
| "loss": 1.6024, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.4862, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00019297764858882514, | |
| "loss": 1.5183, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00019048270524660196, | |
| "loss": 1.396, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 1.5583, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00018443279255020152, | |
| "loss": 1.4023, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.4386, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00017705132427757895, | |
| "loss": 1.4218, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00017289686274214118, | |
| "loss": 1.4874, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00016845471059286887, | |
| "loss": 1.4279, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 1.4142, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 1.3489, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00015358267949789966, | |
| "loss": 1.4629, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00014817536741017152, | |
| "loss": 1.3914, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00014257792915650728, | |
| "loss": 1.407, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00013681245526846783, | |
| "loss": 1.3214, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.5119, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "total_flos": 1.404478652350464e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |