| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9913544668587897, | |
| "eval_steps": 500, | |
| "global_step": 86, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.23054755043227665, | |
| "grad_norm": 5.7781262400474365, | |
| "learning_rate": 9.995838996722916e-06, | |
| "loss": 1.2239, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4610951008645533, | |
| "grad_norm": 2.6146058820763804, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": 0.6363, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.69164265129683, | |
| "grad_norm": 2.265051651383221, | |
| "learning_rate": 8.274303669726427e-06, | |
| "loss": 0.5501, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9221902017291066, | |
| "grad_norm": 2.2234867710255806, | |
| "learning_rate": 6.5062309476861714e-06, | |
| "loss": 0.53, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1613832853025936, | |
| "grad_norm": 1.806488960466616, | |
| "learning_rate": 4.4908850664808245e-06, | |
| "loss": 0.4646, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3919308357348703, | |
| "grad_norm": 1.8739304014379334, | |
| "learning_rate": 2.559118969758595e-06, | |
| "loss": 0.419, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.622478386167147, | |
| "grad_norm": 1.8148175523236398, | |
| "learning_rate": 1.0280645729394368e-06, | |
| "loss": 0.4033, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.8530259365994235, | |
| "grad_norm": 1.7551273067746895, | |
| "learning_rate": 1.4907022212967803e-07, | |
| "loss": 0.4118, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.9913544668587897, | |
| "step": 86, | |
| "total_flos": 11761684054016.0, | |
| "train_loss": 0.5666664145713629, | |
| "train_runtime": 1148.6514, | |
| "train_samples_per_second": 2.413, | |
| "train_steps_per_second": 0.075 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 86, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 11761684054016.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |