| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0011554415519890926, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.3108831039781854e-05, | |
| "eval_loss": 2.76418137550354, | |
| "eval_runtime": 342.1719, | |
| "eval_samples_per_second": 53.251, | |
| "eval_steps_per_second": 26.627, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011554415519890927, | |
| "grad_norm": 0.24371324479579926, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5374, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00023108831039781854, | |
| "grad_norm": 0.24418701231479645, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8559, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00023108831039781854, | |
| "eval_loss": 2.7627344131469727, | |
| "eval_runtime": 339.9478, | |
| "eval_samples_per_second": 53.599, | |
| "eval_steps_per_second": 26.801, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00034663246559672777, | |
| "grad_norm": 0.3409353196620941, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.7465, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004621766207956371, | |
| "grad_norm": 0.3355708122253418, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.7007, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004621766207956371, | |
| "eval_loss": 2.755866289138794, | |
| "eval_runtime": 343.8094, | |
| "eval_samples_per_second": 52.997, | |
| "eval_steps_per_second": 26.5, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005777207759945463, | |
| "grad_norm": 0.23547513782978058, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.828, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0006932649311934555, | |
| "grad_norm": 0.2757609188556671, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2824, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006932649311934555, | |
| "eval_loss": 2.750725507736206, | |
| "eval_runtime": 342.6113, | |
| "eval_samples_per_second": 53.183, | |
| "eval_steps_per_second": 26.593, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008088090863923648, | |
| "grad_norm": 0.27755308151245117, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.8928, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0009243532415912742, | |
| "grad_norm": 0.36021822690963745, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.6814, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0009243532415912742, | |
| "eval_loss": 2.7485904693603516, | |
| "eval_runtime": 341.8594, | |
| "eval_samples_per_second": 53.3, | |
| "eval_steps_per_second": 26.651, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0010398973967901833, | |
| "grad_norm": 0.2863467335700989, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.7984, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0011554415519890926, | |
| "grad_norm": 0.2972218096256256, | |
| "learning_rate": 0.0, | |
| "loss": 2.6367, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0011554415519890926, | |
| "eval_loss": 2.748222589492798, | |
| "eval_runtime": 341.7227, | |
| "eval_samples_per_second": 53.321, | |
| "eval_steps_per_second": 26.662, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 265768041185280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |