| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005420054200542005, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005420054200542005, | |
| "grad_norm": 20.638986587524414, | |
| "learning_rate": 2e-05, | |
| "loss": 8.8305, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005420054200542005, | |
| "eval_loss": 2.5999093055725098, | |
| "eval_runtime": 9.9883, | |
| "eval_samples_per_second": 77.791, | |
| "eval_steps_per_second": 38.945, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001084010840108401, | |
| "grad_norm": 20.828245162963867, | |
| "learning_rate": 4e-05, | |
| "loss": 11.8743, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016260162601626016, | |
| "grad_norm": 21.3616943359375, | |
| "learning_rate": 6e-05, | |
| "loss": 8.0715, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016260162601626016, | |
| "eval_loss": 2.598226547241211, | |
| "eval_runtime": 9.0741, | |
| "eval_samples_per_second": 85.628, | |
| "eval_steps_per_second": 42.869, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002168021680216802, | |
| "grad_norm": 30.179210662841797, | |
| "learning_rate": 8e-05, | |
| "loss": 12.2142, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0027100271002710027, | |
| "grad_norm": 40.070980072021484, | |
| "learning_rate": 0.0001, | |
| "loss": 12.3063, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0032520325203252032, | |
| "grad_norm": 21.60882568359375, | |
| "learning_rate": 0.00012, | |
| "loss": 9.539, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032520325203252032, | |
| "eval_loss": 2.581399440765381, | |
| "eval_runtime": 9.102, | |
| "eval_samples_per_second": 85.366, | |
| "eval_steps_per_second": 42.738, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003794037940379404, | |
| "grad_norm": 31.21387481689453, | |
| "learning_rate": 0.00014, | |
| "loss": 11.0102, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004336043360433604, | |
| "grad_norm": 30.954225540161133, | |
| "learning_rate": 0.00016, | |
| "loss": 10.0577, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004878048780487805, | |
| "grad_norm": 19.75678062438965, | |
| "learning_rate": 0.00018, | |
| "loss": 9.7382, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004878048780487805, | |
| "eval_loss": 2.542026996612549, | |
| "eval_runtime": 8.9486, | |
| "eval_samples_per_second": 86.829, | |
| "eval_steps_per_second": 43.471, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005420054200542005, | |
| "grad_norm": 27.73800277709961, | |
| "learning_rate": 0.0002, | |
| "loss": 8.7905, | |
| "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": 118433563803648.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |