| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.24539877300613497, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0049079754601227, | |
| "eval_loss": 0.8831464052200317, | |
| "eval_runtime": 3.5626, | |
| "eval_samples_per_second": 96.559, | |
| "eval_steps_per_second": 12.07, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.024539877300613498, | |
| "grad_norm": 1.9525963068008423, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8828, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.049079754601226995, | |
| "grad_norm": 1.056400179862976, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5868, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.049079754601226995, | |
| "eval_loss": 0.3824578523635864, | |
| "eval_runtime": 3.5277, | |
| "eval_samples_per_second": 97.513, | |
| "eval_steps_per_second": 12.189, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0736196319018405, | |
| "grad_norm": 0.42027580738067627, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.2738, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09815950920245399, | |
| "grad_norm": 0.4585525095462799, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2077, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09815950920245399, | |
| "eval_loss": 0.17031320929527283, | |
| "eval_runtime": 3.5289, | |
| "eval_samples_per_second": 97.482, | |
| "eval_steps_per_second": 12.185, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12269938650306748, | |
| "grad_norm": 0.2879241108894348, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.168, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.147239263803681, | |
| "grad_norm": 0.3040122985839844, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1382, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.147239263803681, | |
| "eval_loss": 0.13343578577041626, | |
| "eval_runtime": 3.5301, | |
| "eval_samples_per_second": 97.447, | |
| "eval_steps_per_second": 12.181, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17177914110429449, | |
| "grad_norm": 0.3485158085823059, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.135, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.19631901840490798, | |
| "grad_norm": 0.2362179160118103, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1101, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19631901840490798, | |
| "eval_loss": 0.11932237446308136, | |
| "eval_runtime": 3.5166, | |
| "eval_samples_per_second": 97.822, | |
| "eval_steps_per_second": 12.228, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22085889570552147, | |
| "grad_norm": 0.29413965344429016, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1268, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.24539877300613497, | |
| "grad_norm": 0.2792154550552368, | |
| "learning_rate": 0.0, | |
| "loss": 0.1279, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24539877300613497, | |
| "eval_loss": 0.1175348162651062, | |
| "eval_runtime": 3.5071, | |
| "eval_samples_per_second": 98.087, | |
| "eval_steps_per_second": 12.261, | |
| "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": 1.6190651443970048e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |