| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03508771929824561, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011695906432748538, | |
| "eval_loss": 1.654053807258606, | |
| "eval_runtime": 47.1678, | |
| "eval_samples_per_second": 7.654, | |
| "eval_steps_per_second": 3.837, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0035087719298245615, | |
| "grad_norm": 28.21607780456543, | |
| "learning_rate": 6e-05, | |
| "loss": 6.539, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007017543859649123, | |
| "grad_norm": 22.482254028320312, | |
| "learning_rate": 0.00012, | |
| "loss": 6.0581, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00935672514619883, | |
| "eval_loss": 1.4714726209640503, | |
| "eval_runtime": 46.7851, | |
| "eval_samples_per_second": 7.716, | |
| "eval_steps_per_second": 3.869, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "grad_norm": 26.200159072875977, | |
| "learning_rate": 0.00018, | |
| "loss": 7.2017, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 26.442575454711914, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 6.3222, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": 22.6745662689209, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 5.8747, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01871345029239766, | |
| "eval_loss": 1.3965755701065063, | |
| "eval_runtime": 47.1502, | |
| "eval_samples_per_second": 7.656, | |
| "eval_steps_per_second": 3.839, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021052631578947368, | |
| "grad_norm": 55.49920654296875, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.2658, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02456140350877193, | |
| "grad_norm": 19.801729202270508, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 5.8051, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "grad_norm": 11.800546646118164, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 4.6452, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "eval_loss": 1.369209885597229, | |
| "eval_runtime": 47.1617, | |
| "eval_samples_per_second": 7.655, | |
| "eval_steps_per_second": 3.838, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031578947368421054, | |
| "grad_norm": 25.74355125427246, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 4.8135, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 11.279029846191406, | |
| "learning_rate": 0.0, | |
| "loss": 4.4618, | |
| "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": 1.0722737135812608e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |