| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.96, | |
| "eval_steps": 500, | |
| "global_step": 111, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 5.1298956871032715, | |
| "learning_rate": 4.9005367134442235e-05, | |
| "loss": 1.9494, | |
| "num_input_tokens_seen": 23248, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 2.1342523097991943, | |
| "learning_rate": 4.6100612100748765e-05, | |
| "loss": 0.3681, | |
| "num_input_tokens_seen": 45888, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 3.410982370376587, | |
| "learning_rate": 4.151686808475204e-05, | |
| "loss": 0.4155, | |
| "num_input_tokens_seen": 68496, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 3.2357637882232666, | |
| "learning_rate": 3.56188664821012e-05, | |
| "loss": 0.3174, | |
| "num_input_tokens_seen": 90720, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 6.79920768737793, | |
| "learning_rate": 2.8875914991604948e-05, | |
| "loss": 0.2294, | |
| "num_input_tokens_seen": 113392, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 3.9913346767425537, | |
| "learning_rate": 2.182455450632803e-05, | |
| "loss": 0.2442, | |
| "num_input_tokens_seen": 136208, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 4.0106706619262695, | |
| "learning_rate": 1.5025866217114592e-05, | |
| "loss": 0.3141, | |
| "num_input_tokens_seen": 159024, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 1.7849068641662598, | |
| "learning_rate": 9.020826029175384e-06, | |
| "loss": 0.1918, | |
| "num_input_tokens_seen": 181776, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.6430880427360535, | |
| "learning_rate": 4.2872587689039484e-06, | |
| "loss": 0.1719, | |
| "num_input_tokens_seen": 204320, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 1.5287659168243408, | |
| "learning_rate": 1.201817361771837e-06, | |
| "loss": 0.1387, | |
| "num_input_tokens_seen": 227376, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.9333333333333336, | |
| "grad_norm": 2.4531781673431396, | |
| "learning_rate": 1.0012322041960676e-08, | |
| "loss": 0.1394, | |
| "num_input_tokens_seen": 249856, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "num_input_tokens_seen": 252064, | |
| "step": 111, | |
| "total_flos": 1.2630237909123072e+16, | |
| "train_loss": 0.40682300817859063, | |
| "train_runtime": 7468.1424, | |
| "train_samples_per_second": 0.121, | |
| "train_steps_per_second": 0.015 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 111, | |
| "num_input_tokens_seen": 252064, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2630237909123072e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |