| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0707070707070705, | |
| "eval_steps": 25, | |
| "global_step": 19, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16161616161616163, | |
| "grad_norm": 0.0967363566160202, | |
| "learning_rate": 9.938625865312251e-05, | |
| "loss": 11.9178, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "eval_loss": 11.918783187866211, | |
| "eval_runtime": 0.1748, | |
| "eval_samples_per_second": 285.959, | |
| "eval_steps_per_second": 74.349, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.32323232323232326, | |
| "grad_norm": 0.10190389305353165, | |
| "learning_rate": 9.756177587652856e-05, | |
| "loss": 11.9332, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 0.10864829272031784, | |
| "learning_rate": 9.4576318804292e-05, | |
| "loss": 11.9287, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.6464646464646465, | |
| "grad_norm": 0.09459173679351807, | |
| "learning_rate": 9.051132292283771e-05, | |
| "loss": 11.9246, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.8080808080808081, | |
| "grad_norm": 0.10379225760698318, | |
| "learning_rate": 8.547767072315835e-05, | |
| "loss": 11.9267, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.10869208723306656, | |
| "learning_rate": 7.961266711550922e-05, | |
| "loss": 11.9281, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.1313131313131313, | |
| "grad_norm": 0.19784802198410034, | |
| "learning_rate": 7.307629410938363e-05, | |
| "loss": 21.6069, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.2929292929292928, | |
| "grad_norm": 0.12443363666534424, | |
| "learning_rate": 6.604684692133597e-05, | |
| "loss": 11.9245, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 0.12149053066968918, | |
| "learning_rate": 5.8716070546254966e-05, | |
| "loss": 11.9259, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.6161616161616161, | |
| "grad_norm": 0.10425221920013428, | |
| "learning_rate": 5.128392945374505e-05, | |
| "loss": 11.9235, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.13434052467346191, | |
| "learning_rate": 4.395315307866405e-05, | |
| "loss": 11.9287, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.9393939393939394, | |
| "grad_norm": 0.13136471807956696, | |
| "learning_rate": 3.692370589061639e-05, | |
| "loss": 11.9275, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.101010101010101, | |
| "grad_norm": 0.2050371766090393, | |
| "learning_rate": 3.0387332884490805e-05, | |
| "loss": 21.6043, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.2626262626262625, | |
| "grad_norm": 0.12863951921463013, | |
| "learning_rate": 2.4522329276841663e-05, | |
| "loss": 11.9181, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.4242424242424243, | |
| "grad_norm": 0.12978294491767883, | |
| "learning_rate": 1.9488677077162295e-05, | |
| "loss": 11.9248, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.5858585858585856, | |
| "grad_norm": 0.11834482103586197, | |
| "learning_rate": 1.5423681195707997e-05, | |
| "loss": 11.923, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.7474747474747474, | |
| "grad_norm": 0.1345292627811432, | |
| "learning_rate": 1.2438224123471442e-05, | |
| "loss": 11.923, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": 0.14777104556560516, | |
| "learning_rate": 1.0613741346877497e-05, | |
| "loss": 11.9256, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.0707070707070705, | |
| "grad_norm": 0.23815593123435974, | |
| "learning_rate": 1e-05, | |
| "loss": 21.6084, | |
| "step": 19 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 19, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 396147818496.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |