| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13793103448275862, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0035366931918656055, | |
| "eval_loss": 7.848944664001465, | |
| "eval_runtime": 13.8388, | |
| "eval_samples_per_second": 8.671, | |
| "eval_steps_per_second": 4.336, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01768346595932803, | |
| "grad_norm": 4.622712135314941, | |
| "learning_rate": 5e-05, | |
| "loss": 8.1335, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03536693191865606, | |
| "grad_norm": 9.629229545593262, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2117, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03536693191865606, | |
| "eval_loss": 5.49931526184082, | |
| "eval_runtime": 14.0899, | |
| "eval_samples_per_second": 8.517, | |
| "eval_steps_per_second": 4.258, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05305039787798409, | |
| "grad_norm": 9.621377944946289, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.1185, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07073386383731212, | |
| "grad_norm": 2.8658766746520996, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4235, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07073386383731212, | |
| "eval_loss": 0.8843831419944763, | |
| "eval_runtime": 14.1818, | |
| "eval_samples_per_second": 8.462, | |
| "eval_steps_per_second": 4.231, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08841732979664015, | |
| "grad_norm": 2.0114266872406006, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.842, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10610079575596817, | |
| "grad_norm": 4.434057712554932, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0252, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10610079575596817, | |
| "eval_loss": 0.8172988891601562, | |
| "eval_runtime": 14.1194, | |
| "eval_samples_per_second": 8.499, | |
| "eval_steps_per_second": 4.249, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1237842617152962, | |
| "grad_norm": 4.096339225769043, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6784, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6550096120381440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |