| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004, | |
| "grad_norm": 7.629522800445557, | |
| "learning_rate": 0.0, | |
| "loss": 5.0189, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 8.722882270812988, | |
| "learning_rate": 4e-05, | |
| "loss": 5.2523, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012, | |
| "grad_norm": 8.752768516540527, | |
| "learning_rate": 8e-05, | |
| "loss": 5.1972, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 6.982276916503906, | |
| "learning_rate": 0.00012, | |
| "loss": 4.8765, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 5.417596340179443, | |
| "learning_rate": 0.00016, | |
| "loss": 4.4329, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024, | |
| "grad_norm": 4.1424407958984375, | |
| "learning_rate": 0.0002, | |
| "loss": 4.0462, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028, | |
| "grad_norm": 3.573214530944824, | |
| "learning_rate": 0.000192, | |
| "loss": 3.7134, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 3.7948458194732666, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 3.4275, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.036, | |
| "grad_norm": 3.8757693767547607, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 3.2261, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 3.330172300338745, | |
| "learning_rate": 0.000168, | |
| "loss": 2.8046, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.044, | |
| "grad_norm": 1.4923571348190308, | |
| "learning_rate": 0.00016, | |
| "loss": 2.603, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 1.6870243549346924, | |
| "learning_rate": 0.000152, | |
| "loss": 2.4551, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.052, | |
| "grad_norm": 1.5385361909866333, | |
| "learning_rate": 0.000144, | |
| "loss": 2.385, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.056, | |
| "grad_norm": 1.472366213798523, | |
| "learning_rate": 0.00013600000000000003, | |
| "loss": 2.3659, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 1.119588851928711, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 2.2592, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 1.0506559610366821, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2838, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.068, | |
| "grad_norm": 0.9235564470291138, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 2.2292, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.072, | |
| "grad_norm": 1.0015490055084229, | |
| "learning_rate": 0.00010400000000000001, | |
| "loss": 2.3251, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.076, | |
| "grad_norm": 0.907470166683197, | |
| "learning_rate": 9.6e-05, | |
| "loss": 2.1134, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.8798445463180542, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 2.1059, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.084, | |
| "grad_norm": 0.877160370349884, | |
| "learning_rate": 8e-05, | |
| "loss": 2.0301, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.088, | |
| "grad_norm": 0.9122564196586609, | |
| "learning_rate": 7.2e-05, | |
| "loss": 2.0231, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.092, | |
| "grad_norm": 0.888214647769928, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 1.9709, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 0.9268164038658142, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 1.969, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.9201606512069702, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.9435, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.104, | |
| "grad_norm": 0.9429304003715515, | |
| "learning_rate": 4e-05, | |
| "loss": 1.915, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.108, | |
| "grad_norm": 0.9146043658256531, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.9392, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 0.9299567937850952, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.8892, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.116, | |
| "grad_norm": 0.8835386633872986, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.8819, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.9411348700523376, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.9189, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4810578434804096e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |