| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007979413114165454, | |
| "eval_steps": 8, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.9897065570827266e-05, | |
| "eval_loss": 12.323113441467285, | |
| "eval_runtime": 1356.9725, | |
| "eval_samples_per_second": 7.778, | |
| "eval_steps_per_second": 3.889, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001196911967124818, | |
| "grad_norm": 50.16099548339844, | |
| "learning_rate": 6e-05, | |
| "loss": 12.493, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002393823934249636, | |
| "grad_norm": 49.719757080078125, | |
| "learning_rate": 0.00012, | |
| "loss": 6.1887, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003191765245666181, | |
| "eval_loss": 0.18965387344360352, | |
| "eval_runtime": 1364.5033, | |
| "eval_samples_per_second": 7.735, | |
| "eval_steps_per_second": 3.867, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003590735901374454, | |
| "grad_norm": 9.11028003692627, | |
| "learning_rate": 0.00018, | |
| "loss": 0.5088, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004787647868499272, | |
| "grad_norm": 8.212532997131348, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.2538, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005984559835624089, | |
| "grad_norm": 13.752412796020508, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.9378, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006383530491332362, | |
| "eval_loss": 0.10501638054847717, | |
| "eval_runtime": 1362.6122, | |
| "eval_samples_per_second": 7.745, | |
| "eval_steps_per_second": 3.873, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007181471802748908, | |
| "grad_norm": 0.37315019965171814, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.1223, | |
| "step": 18 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7418872835604480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |