| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010260707475780455, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.4202358252601517e-05, | |
| "eval_loss": 4.13474178314209, | |
| "eval_runtime": 2829.6563, | |
| "eval_samples_per_second": 4.351, | |
| "eval_steps_per_second": 2.176, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010260707475780455, | |
| "grad_norm": 6.082716941833496, | |
| "learning_rate": 6e-05, | |
| "loss": 14.4969, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002052141495156091, | |
| "grad_norm": 12.60313606262207, | |
| "learning_rate": 0.00012, | |
| "loss": 16.5664, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00027361886602081213, | |
| "eval_loss": 2.4411087036132812, | |
| "eval_runtime": 2841.6707, | |
| "eval_samples_per_second": 4.332, | |
| "eval_steps_per_second": 2.166, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00030782122427341365, | |
| "grad_norm": 10.238665580749512, | |
| "learning_rate": 0.00018, | |
| "loss": 11.5776, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004104282990312182, | |
| "grad_norm": 13.370744705200195, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 7.1852, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005130353737890227, | |
| "grad_norm": 58.836299896240234, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 5.3901, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005472377320416243, | |
| "eval_loss": 0.7767243981361389, | |
| "eval_runtime": 2839.8774, | |
| "eval_samples_per_second": 4.335, | |
| "eval_steps_per_second": 2.168, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006156424485468273, | |
| "grad_norm": 10.903257369995117, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.3249, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007182495233046318, | |
| "grad_norm": 10.55489444732666, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.9147, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0008208565980624364, | |
| "grad_norm": 13.148904800415039, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.861, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0008208565980624364, | |
| "eval_loss": 0.5136088728904724, | |
| "eval_runtime": 2840.6459, | |
| "eval_samples_per_second": 4.334, | |
| "eval_steps_per_second": 2.167, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0009234636728202409, | |
| "grad_norm": 13.213101387023926, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.8719, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0010260707475780455, | |
| "grad_norm": 6.490150451660156, | |
| "learning_rate": 0.0, | |
| "loss": 1.5265, | |
| "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": 1.90434898870272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |