| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07111111111111111, | |
| "eval_steps": 8, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0035555555555555557, | |
| "eval_loss": 4.701450824737549, | |
| "eval_runtime": 7.1119, | |
| "eval_samples_per_second": 16.732, | |
| "eval_steps_per_second": 8.437, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010666666666666666, | |
| "grad_norm": 8.527983665466309, | |
| "learning_rate": 6e-05, | |
| "loss": 4.5862, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.021333333333333333, | |
| "grad_norm": 6.9240522384643555, | |
| "learning_rate": 0.00012, | |
| "loss": 3.9541, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028444444444444446, | |
| "eval_loss": 1.967842698097229, | |
| "eval_runtime": 7.0506, | |
| "eval_samples_per_second": 16.878, | |
| "eval_steps_per_second": 8.51, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 4.608461856842041, | |
| "learning_rate": 0.00018, | |
| "loss": 2.5516, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.042666666666666665, | |
| "grad_norm": 4.794651985168457, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.9364, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05333333333333334, | |
| "grad_norm": 2.363208055496216, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.2801, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05688888888888889, | |
| "eval_loss": 0.507258415222168, | |
| "eval_runtime": 7.0775, | |
| "eval_samples_per_second": 16.814, | |
| "eval_steps_per_second": 8.478, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 5.319071292877197, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.4827, | |
| "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": 3292692008140800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |