| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.639344262295082, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08196721311475409, | |
| "grad_norm": 8.290995597839355, | |
| "learning_rate": 4.990795908619189e-05, | |
| "loss": 6.3211, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16393442622950818, | |
| "grad_norm": 10.25100040435791, | |
| "learning_rate": 4.9632514067152726e-05, | |
| "loss": 5.8414, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2459016393442623, | |
| "grad_norm": 9.911712646484375, | |
| "learning_rate": 4.928142498664579e-05, | |
| "loss": 6.2669, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32786885245901637, | |
| "grad_norm": 12.882040977478027, | |
| "learning_rate": 4.868186180746792e-05, | |
| "loss": 4.3475, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4098360655737705, | |
| "grad_norm": 9.486019134521484, | |
| "learning_rate": 4.790792261217512e-05, | |
| "loss": 3.6657, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4918032786885246, | |
| "grad_norm": 4.90289306640625, | |
| "learning_rate": 4.696530612642871e-05, | |
| "loss": 2.6512, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5737704918032787, | |
| "grad_norm": 2.928373336791992, | |
| "learning_rate": 4.586095309284618e-05, | |
| "loss": 2.1788, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 5.331892967224121, | |
| "learning_rate": 4.460299516441777e-05, | |
| "loss": 2.0556, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7377049180327869, | |
| "grad_norm": 3.0905227661132812, | |
| "learning_rate": 4.320069502892462e-05, | |
| "loss": 2.0827, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "grad_norm": 3.840454339981079, | |
| "learning_rate": 4.1664378205239085e-05, | |
| "loss": 1.9863, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9016393442622951, | |
| "grad_norm": 2.925448179244995, | |
| "learning_rate": 4.000535701370921e-05, | |
| "loss": 2.0797, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9836065573770492, | |
| "grad_norm": 4.124454498291016, | |
| "learning_rate": 3.823584728045463e-05, | |
| "loss": 1.9855, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0655737704918034, | |
| "grad_norm": 2.905304431915283, | |
| "learning_rate": 3.636887838890265e-05, | |
| "loss": 1.8565, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.1475409836065573, | |
| "grad_norm": 2.937238931655884, | |
| "learning_rate": 3.4418197340879635e-05, | |
| "loss": 1.7846, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.2295081967213115, | |
| "grad_norm": 2.9058425426483154, | |
| "learning_rate": 3.239816753368223e-05, | |
| "loss": 1.8977, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "grad_norm": 3.247345447540283, | |
| "learning_rate": 3.0323662998460393e-05, | |
| "loss": 1.6528, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3934426229508197, | |
| "grad_norm": 3.5700137615203857, | |
| "learning_rate": 2.8209958878663778e-05, | |
| "loss": 1.7865, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.4754098360655736, | |
| "grad_norm": 3.3404250144958496, | |
| "learning_rate": 2.6072618954988866e-05, | |
| "loss": 1.6595, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.5573770491803278, | |
| "grad_norm": 2.9976389408111572, | |
| "learning_rate": 2.3927381045011136e-05, | |
| "loss": 1.795, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.639344262295082, | |
| "grad_norm": 2.907928943634033, | |
| "learning_rate": 2.1790041121336225e-05, | |
| "loss": 1.6754, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 183, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 5218424960974848.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |