| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.999000999000999, | |
| "eval_steps": 500, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007992007992007992, | |
| "grad_norm": 4.625, | |
| "learning_rate": 1.5384615384615387e-06, | |
| "loss": 1.5402, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07992007992007992, | |
| "grad_norm": 1.890625, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 1.43, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15984015984015984, | |
| "grad_norm": 0.58984375, | |
| "learning_rate": 1.9807852804032306e-05, | |
| "loss": 1.2567, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23976023976023977, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 1.8884456359788725e-05, | |
| "loss": 1.1863, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3196803196803197, | |
| "grad_norm": 0.443359375, | |
| "learning_rate": 1.7266603220340273e-05, | |
| "loss": 1.1556, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3996003996003996, | |
| "grad_norm": 0.412109375, | |
| "learning_rate": 1.5080753452465296e-05, | |
| "loss": 1.1529, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.47952047952047955, | |
| "grad_norm": 0.400390625, | |
| "learning_rate": 1.249776478167227e-05, | |
| "loss": 1.1343, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5594405594405595, | |
| "grad_norm": 0.38671875, | |
| "learning_rate": 9.719537437241311e-06, | |
| "loss": 1.1321, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6393606393606394, | |
| "grad_norm": 0.375, | |
| "learning_rate": 6.963232548903853e-06, | |
| "loss": 1.1377, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7192807192807192, | |
| "grad_norm": 0.3671875, | |
| "learning_rate": 4.444297669803981e-06, | |
| "loss": 1.1334, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7992007992007992, | |
| "grad_norm": 0.369140625, | |
| "learning_rate": 2.3596262417839256e-06, | |
| "loss": 1.1197, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 0.412109375, | |
| "learning_rate": 8.721673493868111e-07, | |
| "loss": 1.1244, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9590409590409591, | |
| "grad_norm": 0.373046875, | |
| "learning_rate": 9.818874663554356e-08, | |
| "loss": 1.1274, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.999000999000999, | |
| "eval_loss": 1.1158442497253418, | |
| "eval_runtime": 10.5066, | |
| "eval_samples_per_second": 25.127, | |
| "eval_steps_per_second": 1.618, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.999000999000999, | |
| "step": 125, | |
| "total_flos": 1.2990581727276564e+18, | |
| "train_loss": 1.172668625831604, | |
| "train_runtime": 2523.6133, | |
| "train_samples_per_second": 6.341, | |
| "train_steps_per_second": 0.05 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 125, | |
| "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": 1.2990581727276564e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |