| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0029563932002956393, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.9127864005912786e-05, | |
| "eval_loss": 1.9941140413284302, | |
| "eval_runtime": 208.864, | |
| "eval_samples_per_second": 34.099, | |
| "eval_steps_per_second": 17.049, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005912786400591279, | |
| "grad_norm": 0.6663184762001038, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8674, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007686622320768662, | |
| "eval_loss": 1.7656859159469604, | |
| "eval_runtime": 207.7038, | |
| "eval_samples_per_second": 34.289, | |
| "eval_steps_per_second": 17.145, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0011825572801182557, | |
| "grad_norm": 0.7885698676109314, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.7289, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015373244641537324, | |
| "eval_loss": 1.5676556825637817, | |
| "eval_runtime": 207.9079, | |
| "eval_samples_per_second": 34.256, | |
| "eval_steps_per_second": 17.128, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0017738359201773836, | |
| "grad_norm": 1.013671875, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5153, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0023059866962305987, | |
| "eval_loss": 1.515963077545166, | |
| "eval_runtime": 207.967, | |
| "eval_samples_per_second": 34.246, | |
| "eval_steps_per_second": 17.123, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0023651145602365115, | |
| "grad_norm": 0.7077562808990479, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.4753, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0029563932002956393, | |
| "grad_norm": 1.0900564193725586, | |
| "learning_rate": 0.0, | |
| "loss": 1.501, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 8306538993156096.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |