| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0004925481568437514, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.6418271894791713e-05, | |
| "eval_loss": 10.377076148986816, | |
| "eval_runtime": 76.1052, | |
| "eval_samples_per_second": 336.981, | |
| "eval_steps_per_second": 168.491, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.925481568437514e-05, | |
| "grad_norm": 0.07869064807891846, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3759, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.850963136875028e-05, | |
| "grad_norm": 0.07274885475635529, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3801, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001313461751583337, | |
| "eval_loss": 10.376413345336914, | |
| "eval_runtime": 76.952, | |
| "eval_samples_per_second": 333.273, | |
| "eval_steps_per_second": 166.636, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001477644470531254, | |
| "grad_norm": 0.05130927637219429, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3795, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00019701926273750056, | |
| "grad_norm": 0.05146366357803345, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.3772, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002462740784218757, | |
| "grad_norm": 0.043234650045633316, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.3795, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002626923503166674, | |
| "eval_loss": 10.374665260314941, | |
| "eval_runtime": 77.3691, | |
| "eval_samples_per_second": 331.476, | |
| "eval_steps_per_second": 165.738, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0002955288941062508, | |
| "grad_norm": 0.04625086858868599, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.3782, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.000344783709790626, | |
| "grad_norm": 0.09610570222139359, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.3811, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0003940385254750011, | |
| "grad_norm": 0.0615416057407856, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.3827, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0003940385254750011, | |
| "eval_loss": 10.373649597167969, | |
| "eval_runtime": 76.3786, | |
| "eval_samples_per_second": 335.774, | |
| "eval_steps_per_second": 167.887, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0004432933411593763, | |
| "grad_norm": 0.05280403047800064, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.3698, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0004925481568437514, | |
| "grad_norm": 0.05877093970775604, | |
| "learning_rate": 0.0, | |
| "loss": 10.3763, | |
| "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": 784536698880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |