| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00409626216077829, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.19252432155658e-05, | |
| "eval_loss": 9.919251441955566, | |
| "eval_runtime": 3088.7028, | |
| "eval_samples_per_second": 6.656, | |
| "eval_steps_per_second": 0.832, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002457757296466974, | |
| "grad_norm": 104.41869354248047, | |
| "learning_rate": 3e-05, | |
| "loss": 39.972, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000409626216077829, | |
| "eval_loss": 6.850073337554932, | |
| "eval_runtime": 3102.4941, | |
| "eval_samples_per_second": 6.626, | |
| "eval_steps_per_second": 0.828, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004915514592933948, | |
| "grad_norm": 52.84882736206055, | |
| "learning_rate": 6e-05, | |
| "loss": 30.9229, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007373271889400922, | |
| "grad_norm": 23.667661666870117, | |
| "learning_rate": 9e-05, | |
| "loss": 12.2992, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000819252432155658, | |
| "eval_loss": 0.9615960717201233, | |
| "eval_runtime": 3102.4484, | |
| "eval_samples_per_second": 6.626, | |
| "eval_steps_per_second": 0.828, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009831029185867896, | |
| "grad_norm": 6.548802852630615, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 2.6153, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001228878648233487, | |
| "grad_norm": 2.684576988220215, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5974, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001228878648233487, | |
| "eval_loss": 0.5547358393669128, | |
| "eval_runtime": 3103.0768, | |
| "eval_samples_per_second": 6.625, | |
| "eval_steps_per_second": 0.828, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014746543778801843, | |
| "grad_norm": 4.335230350494385, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.9918, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001638504864311316, | |
| "eval_loss": 0.35476309061050415, | |
| "eval_runtime": 3104.0065, | |
| "eval_samples_per_second": 6.623, | |
| "eval_steps_per_second": 0.828, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017204301075268817, | |
| "grad_norm": 3.807943105697632, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 1.8718, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001966205837173579, | |
| "grad_norm": 1.5921235084533691, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 1.3015, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002048131080389145, | |
| "eval_loss": 0.14903762936592102, | |
| "eval_runtime": 3105.7501, | |
| "eval_samples_per_second": 6.619, | |
| "eval_steps_per_second": 0.827, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022119815668202765, | |
| "grad_norm": 1.5769877433776855, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.1538, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002457757296466974, | |
| "grad_norm": 0.612311840057373, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8344, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002457757296466974, | |
| "eval_loss": 0.1540408730506897, | |
| "eval_runtime": 3106.4735, | |
| "eval_samples_per_second": 6.618, | |
| "eval_steps_per_second": 0.827, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0027035330261136713, | |
| "grad_norm": 8.35338020324707, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 1.0426, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.002867383512544803, | |
| "eval_loss": 0.1486940234899521, | |
| "eval_runtime": 3109.1764, | |
| "eval_samples_per_second": 6.612, | |
| "eval_steps_per_second": 0.827, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0029493087557603687, | |
| "grad_norm": 0.0876259133219719, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.3718, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.003195084485407066, | |
| "grad_norm": 0.07274000346660614, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0031, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.003277009728622632, | |
| "eval_loss": 0.14395955204963684, | |
| "eval_runtime": 3106.4956, | |
| "eval_samples_per_second": 6.618, | |
| "eval_steps_per_second": 0.827, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0034408602150537634, | |
| "grad_norm": 0.05236983299255371, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0026, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.003686635944700461, | |
| "grad_norm": 0.055042464286088943, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3431, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003686635944700461, | |
| "eval_loss": 0.14288893342018127, | |
| "eval_runtime": 3104.0602, | |
| "eval_samples_per_second": 6.623, | |
| "eval_steps_per_second": 0.828, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003932411674347158, | |
| "grad_norm": 0.033429473638534546, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.3096, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.00409626216077829, | |
| "eval_loss": 0.1423790454864502, | |
| "eval_runtime": 3106.6278, | |
| "eval_samples_per_second": 6.617, | |
| "eval_steps_per_second": 0.827, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.28802361442304e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |