| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005316862873675769, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.7722876245585897e-05, | |
| "eval_loss": 2.3748350143432617, | |
| "eval_runtime": 1997.5262, | |
| "eval_samples_per_second": 11.894, | |
| "eval_steps_per_second": 5.947, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.316862873675769e-05, | |
| "grad_norm": 0.9981592297554016, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1914, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010633725747351538, | |
| "grad_norm": 1.1429567337036133, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4293, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00014178300996468718, | |
| "eval_loss": 1.9845657348632812, | |
| "eval_runtime": 2004.6184, | |
| "eval_samples_per_second": 11.852, | |
| "eval_steps_per_second": 5.926, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00015950588621027308, | |
| "grad_norm": 0.9357064366340637, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0415, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00021267451494703075, | |
| "grad_norm": 0.9889318346977234, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.9318, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00026584314368378843, | |
| "grad_norm": 0.954679548740387, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.7932, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00028356601992937436, | |
| "eval_loss": 1.6526117324829102, | |
| "eval_runtime": 2008.4677, | |
| "eval_samples_per_second": 11.829, | |
| "eval_steps_per_second": 5.914, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00031901177242054616, | |
| "grad_norm": 0.6018568277359009, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6869, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00037218040115730383, | |
| "grad_norm": 0.7580921649932861, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.6636, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0004253490298940615, | |
| "grad_norm": 0.5212671756744385, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.5364, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0004253490298940615, | |
| "eval_loss": 1.564977765083313, | |
| "eval_runtime": 2005.6696, | |
| "eval_samples_per_second": 11.845, | |
| "eval_steps_per_second": 5.923, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0004785176586308192, | |
| "grad_norm": 0.7111144065856934, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.5786, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0005316862873675769, | |
| "grad_norm": 0.7312278747558594, | |
| "learning_rate": 0.0, | |
| "loss": 1.5883, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.016432204709888e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |