| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.17777777777777778, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005925925925925926, | |
| "eval_loss": 15.123552322387695, | |
| "eval_runtime": 5.185, | |
| "eval_samples_per_second": 13.693, | |
| "eval_steps_per_second": 6.943, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017777777777777778, | |
| "grad_norm": 12.838861465454102, | |
| "learning_rate": 6e-05, | |
| "loss": 15.0509, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.035555555555555556, | |
| "grad_norm": 23.51093101501465, | |
| "learning_rate": 0.00012, | |
| "loss": 13.5938, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.047407407407407405, | |
| "eval_loss": 7.749448299407959, | |
| "eval_runtime": 4.1079, | |
| "eval_samples_per_second": 17.284, | |
| "eval_steps_per_second": 8.764, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05333333333333334, | |
| "grad_norm": 27.35287094116211, | |
| "learning_rate": 0.00018, | |
| "loss": 9.4733, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07111111111111111, | |
| "grad_norm": 9.790633201599121, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 5.7596, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 9.129799842834473, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 4.5963, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09481481481481481, | |
| "eval_loss": 4.215736389160156, | |
| "eval_runtime": 4.1228, | |
| "eval_samples_per_second": 17.221, | |
| "eval_steps_per_second": 8.732, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10666666666666667, | |
| "grad_norm": 5.937270164489746, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.2429, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12444444444444444, | |
| "grad_norm": 6.120875358581543, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 4.2063, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14222222222222222, | |
| "grad_norm": 8.228800773620605, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 4.0636, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14222222222222222, | |
| "eval_loss": 3.98516583442688, | |
| "eval_runtime": 4.121, | |
| "eval_samples_per_second": 17.229, | |
| "eval_steps_per_second": 8.736, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 6.264423847198486, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 3.9926, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 6.0742387771606445, | |
| "learning_rate": 0.0, | |
| "loss": 3.9825, | |
| "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": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |