| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 692, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1447178002894356, | |
| "grad_norm": 0.5892243385314941, | |
| "learning_rate": 0.00019977600780563863, | |
| "loss": 1.3906, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2894356005788712, | |
| "grad_norm": 0.36873894929885864, | |
| "learning_rate": 0.00019535370438781766, | |
| "loss": 0.1788, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4341534008683068, | |
| "grad_norm": 0.19239167869091034, | |
| "learning_rate": 0.00018550668718999872, | |
| "loss": 0.1467, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5788712011577424, | |
| "grad_norm": 0.2375071942806244, | |
| "learning_rate": 0.00017079515731006085, | |
| "loss": 0.153, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.723589001447178, | |
| "grad_norm": 0.3418053090572357, | |
| "learning_rate": 0.0001520560600914168, | |
| "loss": 0.203, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.8683068017366136, | |
| "grad_norm": 0.39986488223075867, | |
| "learning_rate": 0.00013035547093784186, | |
| "loss": 0.1199, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0115774240231548, | |
| "grad_norm": 0.26972511410713196, | |
| "learning_rate": 0.00010692794581935566, | |
| "loss": 0.1214, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.1562952243125904, | |
| "grad_norm": 0.2016027271747589, | |
| "learning_rate": 8.310628684529856e-05, | |
| "loss": 0.1151, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.301013024602026, | |
| "grad_norm": 0.19475121796131134, | |
| "learning_rate": 6.024571857174443e-05, | |
| "loss": 0.1138, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.4457308248914615, | |
| "grad_norm": 0.3025433421134949, | |
| "learning_rate": 3.964678868615134e-05, | |
| "loss": 0.1001, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5904486251808971, | |
| "grad_norm": 0.27158206701278687, | |
| "learning_rate": 2.248137928288564e-05, | |
| "loss": 0.1104, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.7351664254703327, | |
| "grad_norm": 0.27117523550987244, | |
| "learning_rate": 9.726037980385738e-06, | |
| "loss": 0.1087, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8798842257597683, | |
| "grad_norm": 0.23554663360118866, | |
| "learning_rate": 2.1064217017516152e-06, | |
| "loss": 0.1021, | |
| "step": 650 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 692, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 3.115369814450381e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |