| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.78048780487805, | |
| "eval_steps": 500, | |
| "global_step": 90, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00019864823963335033, | |
| "loss": 2.6568, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00019428459070078416, | |
| "loss": 2.4777, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0001870370067496355, | |
| "loss": 2.3358, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00017712717364608328, | |
| "loss": 2.2961, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.0001648582089462756, | |
| "loss": 2.231, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.00015060539027168316, | |
| "loss": 2.1653, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 0.0001348046764845511, | |
| "loss": 2.0799, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 0.000117939372772616, | |
| "loss": 2.1272, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 0.00010052534752553063, | |
| "loss": 2.0387, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 8.309525318258826e-05, | |
| "loss": 1.9852, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 6.618223369742117e-05, | |
| "loss": 1.9507, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 5.030361696847705e-05, | |
| "loss": 1.9503, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 3.594509104393951e-05, | |
| "loss": 1.9554, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 2.3545848112279833e-05, | |
| "loss": 1.8693, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 1.3485150687433167e-05, | |
| "loss": 1.8875, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 6.070730896136479e-06, | |
| "loss": 1.8837, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 1.5293777048546509e-06, | |
| "loss": 1.889, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 0.0, | |
| "loss": 1.8582, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "step": 90, | |
| "total_flos": 1.573518009434112e+16, | |
| "train_loss": 2.090980339050293, | |
| "train_runtime": 141.8274, | |
| "train_samples_per_second": 2.602, | |
| "train_steps_per_second": 0.635 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 90, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9, | |
| "save_steps": 10, | |
| "total_flos": 1.573518009434112e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |