| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4988, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9302, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.8645, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6333, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00019375000000000002, | |
| "loss": 2.8102, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0001875, | |
| "loss": 2.5731, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00018125000000000001, | |
| "loss": 2.6083, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.000175, | |
| "loss": 2.7983, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00016875, | |
| "loss": 2.6725, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.00016250000000000002, | |
| "loss": 2.5018, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.00015625, | |
| "loss": 2.7047, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.5548, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.00014375, | |
| "loss": 2.5345, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 0.0001375, | |
| "loss": 2.4148, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 0.00013125000000000002, | |
| "loss": 2.6075, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.000125, | |
| "loss": 2.5263, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.00011875, | |
| "loss": 2.4238, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 0.00011250000000000001, | |
| "loss": 2.4985, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 0.00010625000000000001, | |
| "loss": 2.4527, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4415, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 9.375e-05, | |
| "loss": 2.4565, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 8.75e-05, | |
| "loss": 2.2245, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 8.125000000000001e-05, | |
| "loss": 2.5175, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.4022, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 6.875e-05, | |
| "loss": 2.4127, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 6.25e-05, | |
| "loss": 2.452, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 5.6250000000000005e-05, | |
| "loss": 2.3324, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2148, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 4.375e-05, | |
| "loss": 2.381, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 2.4005, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 3.125e-05, | |
| "loss": 2.3215, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.1712, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 2.3326, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 1.25e-05, | |
| "loss": 2.2245, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 6.25e-06, | |
| "loss": 2.4096, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.2489, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 36, | |
| "num_train_epochs": 9, | |
| "save_steps": 500, | |
| "total_flos": 3548728019386368.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |