| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0020742584526031943, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020742584526031943, | |
| "grad_norm": 3.4374072551727295, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0603, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020742584526031943, | |
| "eval_loss": 1.2174626588821411, | |
| "eval_runtime": 25.3083, | |
| "eval_samples_per_second": 80.211, | |
| "eval_steps_per_second": 40.105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00041485169052063887, | |
| "grad_norm": 3.811847686767578, | |
| "learning_rate": 4e-05, | |
| "loss": 5.4685, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006222775357809583, | |
| "grad_norm": 3.329572916030884, | |
| "learning_rate": 6e-05, | |
| "loss": 3.3136, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006222775357809583, | |
| "eval_loss": 1.212876796722412, | |
| "eval_runtime": 24.3912, | |
| "eval_samples_per_second": 83.227, | |
| "eval_steps_per_second": 41.613, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008297033810412777, | |
| "grad_norm": 3.1321616172790527, | |
| "learning_rate": 8e-05, | |
| "loss": 3.8305, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010371292263015972, | |
| "grad_norm": 3.175114631652832, | |
| "learning_rate": 0.0001, | |
| "loss": 3.75, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012445550715619166, | |
| "grad_norm": 3.376704454421997, | |
| "learning_rate": 0.00012, | |
| "loss": 4.3884, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012445550715619166, | |
| "eval_loss": 1.180108666419983, | |
| "eval_runtime": 24.3034, | |
| "eval_samples_per_second": 83.527, | |
| "eval_steps_per_second": 41.764, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001451980916822236, | |
| "grad_norm": 2.4958813190460205, | |
| "learning_rate": 0.00014, | |
| "loss": 4.6986, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016594067620825555, | |
| "grad_norm": 2.969679594039917, | |
| "learning_rate": 0.00016, | |
| "loss": 4.756, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001866832607342875, | |
| "grad_norm": 2.7087903022766113, | |
| "learning_rate": 0.00018, | |
| "loss": 3.4187, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001866832607342875, | |
| "eval_loss": 1.1408360004425049, | |
| "eval_runtime": 24.5365, | |
| "eval_samples_per_second": 82.734, | |
| "eval_steps_per_second": 41.367, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0020742584526031943, | |
| "grad_norm": 2.522325038909912, | |
| "learning_rate": 0.0002, | |
| "loss": 3.2933, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 133886512201728.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |