| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0638297872340425, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0425531914893617, | |
| "grad_norm": 2.0995755195617676, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.1063, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0425531914893617, | |
| "eval_loss": 3.8875327110290527, | |
| "eval_runtime": 0.6786, | |
| "eval_samples_per_second": 29.471, | |
| "eval_steps_per_second": 14.735, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 3.263718605041504, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.4322, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "grad_norm": 3.820951223373413, | |
| "learning_rate": 0.0001, | |
| "loss": 3.645, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 5.33889627456665, | |
| "learning_rate": 9.994664874011863e-05, | |
| "loss": 4.513, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2127659574468085, | |
| "grad_norm": 7.883951663970947, | |
| "learning_rate": 9.978670881475172e-05, | |
| "loss": 5.0264, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 2.583144187927246, | |
| "learning_rate": 9.952052154376026e-05, | |
| "loss": 3.26, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2978723404255319, | |
| "grad_norm": 3.3901255130767822, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 3.2384, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 4.286656856536865, | |
| "learning_rate": 9.867190271803465e-05, | |
| "loss": 3.4462, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3829787234042553, | |
| "grad_norm": 4.722428321838379, | |
| "learning_rate": 9.809128215864097e-05, | |
| "loss": 3.7113, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": 6.825965404510498, | |
| "learning_rate": 9.74080323795483e-05, | |
| "loss": 4.5429, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.46808510638297873, | |
| "grad_norm": 3.327223777770996, | |
| "learning_rate": 9.662361147021779e-05, | |
| "loss": 3.0301, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 3.6547610759735107, | |
| "learning_rate": 9.573969342440106e-05, | |
| "loss": 2.9293, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5531914893617021, | |
| "grad_norm": 4.506838798522949, | |
| "learning_rate": 9.475816456775313e-05, | |
| "loss": 3.4406, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": 5.095069408416748, | |
| "learning_rate": 9.368111953231848e-05, | |
| "loss": 3.5664, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6382978723404256, | |
| "grad_norm": 5.679275989532471, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 3.443, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 2.384618043899536, | |
| "learning_rate": 9.124987372991511e-05, | |
| "loss": 3.0016, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.723404255319149, | |
| "grad_norm": 3.2170469760894775, | |
| "learning_rate": 8.9900861364012e-05, | |
| "loss": 2.9207, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 4.741713523864746, | |
| "learning_rate": 8.846669854914396e-05, | |
| "loss": 3.2638, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8085106382978723, | |
| "grad_norm": 4.597310543060303, | |
| "learning_rate": 8.695044586103296e-05, | |
| "loss": 3.119, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 6.106940746307373, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.196, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8936170212765957, | |
| "grad_norm": 3.007261037826538, | |
| "learning_rate": 8.368478218232787e-05, | |
| "loss": 2.7263, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": 3.8679449558258057, | |
| "learning_rate": 8.194234028259806e-05, | |
| "loss": 3.2128, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.9787234042553191, | |
| "grad_norm": 5.008350372314453, | |
| "learning_rate": 8.013173181896283e-05, | |
| "loss": 3.1513, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0212765957446808, | |
| "grad_norm": 8.066261291503906, | |
| "learning_rate": 7.82568207211296e-05, | |
| "loss": 5.1511, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "grad_norm": 2.237522840499878, | |
| "learning_rate": 7.63216081438678e-05, | |
| "loss": 2.0345, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "eval_loss": 2.8090415000915527, | |
| "eval_runtime": 0.6742, | |
| "eval_samples_per_second": 29.666, | |
| "eval_steps_per_second": 14.833, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 71, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4894017925939200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |