| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002, | |
| "loss": 1.798, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 1.809, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 1.5909, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 1.5283, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 1.4646, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 1.4358, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 1.3902, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 1.3732, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 1.3089, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 1.3257, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 1.3331, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 1.3088, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 1.3281, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 1.3205, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 1.2873, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.1085949060360654e-05, | |
| "loss": 1.2785, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.2052624879351104e-05, | |
| "loss": 1.2857, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.418275829936537e-06, | |
| "loss": 1.2266, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.3638696597277679e-06, | |
| "loss": 1.2558, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.2191, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 20, | |
| "total_flos": 4228427022336.0, | |
| "train_loss": 1.3933977484703064, | |
| "train_runtime": 203.1559, | |
| "train_samples_per_second": 12.281, | |
| "train_steps_per_second": 0.098 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50000, | |
| "total_flos": 4228427022336.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |