| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008861438122792948, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.7722876245585897e-05, | |
| "eval_loss": 1.7361408472061157, | |
| "eval_runtime": 1985.431, | |
| "eval_samples_per_second": 11.966, | |
| "eval_steps_per_second": 5.983, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.861438122792948e-05, | |
| "grad_norm": 0.8715835809707642, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6216, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00017722876245585895, | |
| "grad_norm": 1.0856618881225586, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3852, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00017722876245585895, | |
| "eval_loss": 1.437419056892395, | |
| "eval_runtime": 2011.3717, | |
| "eval_samples_per_second": 11.812, | |
| "eval_steps_per_second": 5.906, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00026584314368378843, | |
| "grad_norm": 1.6904109716415405, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2922, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003544575249117179, | |
| "grad_norm": 1.2493869066238403, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8623, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003544575249117179, | |
| "eval_loss": 0.7036842107772827, | |
| "eval_runtime": 2008.721, | |
| "eval_samples_per_second": 11.827, | |
| "eval_steps_per_second": 5.914, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004430719061396474, | |
| "grad_norm": 1.8683321475982666, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7287, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005316862873675769, | |
| "grad_norm": 1.5432759523391724, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6118, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005316862873675769, | |
| "eval_loss": 0.5978233218193054, | |
| "eval_runtime": 2010.9302, | |
| "eval_samples_per_second": 11.814, | |
| "eval_steps_per_second": 5.907, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006203006685955064, | |
| "grad_norm": 1.030396819114685, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6266, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0007089150498234358, | |
| "grad_norm": 0.6566690802574158, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5257, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0007089150498234358, | |
| "eval_loss": 0.5642721056938171, | |
| "eval_runtime": 2008.0741, | |
| "eval_samples_per_second": 11.831, | |
| "eval_steps_per_second": 5.916, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0007975294310513653, | |
| "grad_norm": 0.8434397578239441, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.586, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0008861438122792948, | |
| "grad_norm": 1.120571255683899, | |
| "learning_rate": 0.0, | |
| "loss": 0.5317, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0008861438122792948, | |
| "eval_loss": 0.5591886043548584, | |
| "eval_runtime": 2006.7277, | |
| "eval_samples_per_second": 11.839, | |
| "eval_steps_per_second": 5.92, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8980634932346880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |