| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9989304812834225, | |
| "eval_steps": 500, | |
| "global_step": 2103, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.35650623885918004, | |
| "grad_norm": 0.21842770164299508, | |
| "learning_rate": 4.827671334325556e-05, | |
| "loss": 0.2187, | |
| "num_input_tokens_seen": 23116920, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7130124777183601, | |
| "grad_norm": 0.264628701688223, | |
| "learning_rate": 4.3344430725127315e-05, | |
| "loss": 0.1517, | |
| "num_input_tokens_seen": 46165368, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0695187165775402, | |
| "grad_norm": 0.2035976467945333, | |
| "learning_rate": 3.58831310914643e-05, | |
| "loss": 0.1431, | |
| "num_input_tokens_seen": 69151136, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.4260249554367201, | |
| "grad_norm": 0.22638119645171662, | |
| "learning_rate": 2.6921451090319603e-05, | |
| "loss": 0.1361, | |
| "num_input_tokens_seen": 92315440, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.7825311942959001, | |
| "grad_norm": 0.23172350553853155, | |
| "learning_rate": 1.7694874207132127e-05, | |
| "loss": 0.1325, | |
| "num_input_tokens_seen": 115310032, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.1390374331550803, | |
| "grad_norm": 0.2733589059411947, | |
| "learning_rate": 9.475403388319752e-06, | |
| "loss": 0.1285, | |
| "num_input_tokens_seen": 138399552, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.4955436720142603, | |
| "grad_norm": 0.26624980539216286, | |
| "learning_rate": 3.396198984887261e-06, | |
| "loss": 0.1234, | |
| "num_input_tokens_seen": 161536888, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.8520499108734403, | |
| "grad_norm": 0.2774171194895216, | |
| "learning_rate": 2.9535794339922984e-07, | |
| "loss": 0.1239, | |
| "num_input_tokens_seen": 184501880, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 2103, | |
| "num_input_tokens_seen": 194043256, | |
| "num_train_epochs": 3, | |
| "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": 1.7648473335660544e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |