| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08186469584991472, | |
| "eval_steps": 9, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022740193291642978, | |
| "eval_loss": 2.2858026027679443, | |
| "eval_runtime": 35.4041, | |
| "eval_samples_per_second": 20.93, | |
| "eval_steps_per_second": 2.627, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006822057987492893, | |
| "grad_norm": 0.60309898853302, | |
| "learning_rate": 3e-05, | |
| "loss": 2.083, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013644115974985787, | |
| "grad_norm": 0.683789074420929, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3169, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02046617396247868, | |
| "grad_norm": 0.8379518985748291, | |
| "learning_rate": 9e-05, | |
| "loss": 2.2734, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02046617396247868, | |
| "eval_loss": 2.204383373260498, | |
| "eval_runtime": 35.8511, | |
| "eval_samples_per_second": 20.669, | |
| "eval_steps_per_second": 2.594, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027288231949971573, | |
| "grad_norm": 0.6264774799346924, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.0739, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03411028993746447, | |
| "grad_norm": 0.5958771705627441, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.0297, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04093234792495736, | |
| "grad_norm": 1.1767833232879639, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.04, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04093234792495736, | |
| "eval_loss": 1.970629334449768, | |
| "eval_runtime": 35.8984, | |
| "eval_samples_per_second": 20.642, | |
| "eval_steps_per_second": 2.591, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.047754405912450254, | |
| "grad_norm": 0.9643926620483398, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.8702, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.054576463899943146, | |
| "grad_norm": 1.1769558191299438, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.8235, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.061398521887436046, | |
| "grad_norm": 1.374096393585205, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 1.647, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.061398521887436046, | |
| "eval_loss": 1.761104941368103, | |
| "eval_runtime": 35.916, | |
| "eval_samples_per_second": 20.631, | |
| "eval_steps_per_second": 2.589, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06822057987492894, | |
| "grad_norm": 0.7258775234222412, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.7701, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07504263786242182, | |
| "grad_norm": 0.5846672654151917, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 1.5202, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08186469584991472, | |
| "grad_norm": 0.7897035479545593, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.6917, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08186469584991472, | |
| "eval_loss": 1.7188748121261597, | |
| "eval_runtime": 35.9555, | |
| "eval_samples_per_second": 20.609, | |
| "eval_steps_per_second": 2.587, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.205711593373696e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |