| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015594541910331383, | |
| "eval_steps": 8, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007797270955165692, | |
| "eval_loss": 1.7115399837493896, | |
| "eval_runtime": 56.2296, | |
| "eval_samples_per_second": 9.603, | |
| "eval_steps_per_second": 4.802, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023391812865497076, | |
| "grad_norm": 2.6122512817382812, | |
| "learning_rate": 6e-05, | |
| "loss": 7.0366, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004678362573099415, | |
| "grad_norm": 1.5163193941116333, | |
| "learning_rate": 0.00012, | |
| "loss": 6.5892, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006237816764132553, | |
| "eval_loss": 1.5814731121063232, | |
| "eval_runtime": 56.7645, | |
| "eval_samples_per_second": 9.513, | |
| "eval_steps_per_second": 4.756, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007017543859649123, | |
| "grad_norm": 0.9659629464149475, | |
| "learning_rate": 0.00018, | |
| "loss": 6.6057, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00935672514619883, | |
| "grad_norm": 1.0121257305145264, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 6.6128, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011695906432748537, | |
| "grad_norm": 0.9788318872451782, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.1365, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012475633528265107, | |
| "eval_loss": 1.501676082611084, | |
| "eval_runtime": 57.0453, | |
| "eval_samples_per_second": 9.466, | |
| "eval_steps_per_second": 4.733, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 1.0046123266220093, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.0462, | |
| "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": 3684183016734720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |