| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09828009828009827, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003276003276003276, | |
| "eval_loss": 1.984810471534729, | |
| "eval_runtime": 17.0968, | |
| "eval_samples_per_second": 7.545, | |
| "eval_steps_per_second": 3.802, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009828009828009828, | |
| "grad_norm": 3.349700450897217, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0218, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.019656019656019656, | |
| "grad_norm": 3.5021376609802246, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7152, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02620802620802621, | |
| "eval_loss": 0.3697141408920288, | |
| "eval_runtime": 16.5145, | |
| "eval_samples_per_second": 7.811, | |
| "eval_steps_per_second": 3.936, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029484029484029485, | |
| "grad_norm": 2.7822227478027344, | |
| "learning_rate": 0.00018, | |
| "loss": 0.604, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03931203931203931, | |
| "grad_norm": 5.66183614730835, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.1702, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04914004914004914, | |
| "grad_norm": 0.7912327647209167, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.054, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05241605241605242, | |
| "eval_loss": 0.0304864551872015, | |
| "eval_runtime": 16.6335, | |
| "eval_samples_per_second": 7.755, | |
| "eval_steps_per_second": 3.908, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05896805896805897, | |
| "grad_norm": 0.7055149674415588, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0311, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0687960687960688, | |
| "grad_norm": 0.3252002000808716, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0158, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07862407862407862, | |
| "grad_norm": 0.6921682357788086, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0151, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07862407862407862, | |
| "eval_loss": 0.009541512466967106, | |
| "eval_runtime": 16.6876, | |
| "eval_samples_per_second": 7.73, | |
| "eval_steps_per_second": 3.895, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08845208845208845, | |
| "grad_norm": 0.18683640658855438, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.01, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09828009828009827, | |
| "grad_norm": 0.6869999170303345, | |
| "learning_rate": 0.0, | |
| "loss": 0.0159, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.109738548887552e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |