| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0029027997503592215, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.805599500718443e-05, | |
| "eval_loss": 11.049264907836914, | |
| "eval_runtime": 700.7925, | |
| "eval_samples_per_second": 10.35, | |
| "eval_steps_per_second": 5.176, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002902799750359221, | |
| "grad_norm": 11.501642227172852, | |
| "learning_rate": 5e-05, | |
| "loss": 11.2858, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005805599500718442, | |
| "grad_norm": 17.796802520751953, | |
| "learning_rate": 0.0001, | |
| "loss": 8.6548, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005805599500718442, | |
| "eval_loss": 4.853416919708252, | |
| "eval_runtime": 713.834, | |
| "eval_samples_per_second": 10.161, | |
| "eval_steps_per_second": 5.081, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008708399251077664, | |
| "grad_norm": 8.471663475036621, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3761, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011611199001436885, | |
| "grad_norm": 2.556199550628662, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5293, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011611199001436885, | |
| "eval_loss": 0.24717071652412415, | |
| "eval_runtime": 713.0601, | |
| "eval_samples_per_second": 10.172, | |
| "eval_steps_per_second": 5.087, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014513998751796108, | |
| "grad_norm": 9.092192649841309, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2606, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0017416798502155328, | |
| "grad_norm": 0.8398322463035583, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3312, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0017416798502155328, | |
| "eval_loss": 0.13162466883659363, | |
| "eval_runtime": 712.9775, | |
| "eval_samples_per_second": 10.173, | |
| "eval_steps_per_second": 5.087, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002031959825251455, | |
| "grad_norm": 1.0676698684692383, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1444, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.002322239800287377, | |
| "grad_norm": 1.540916919708252, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1318, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002322239800287377, | |
| "eval_loss": 0.12594906985759735, | |
| "eval_runtime": 713.5602, | |
| "eval_samples_per_second": 10.165, | |
| "eval_steps_per_second": 5.083, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0026125197753232993, | |
| "grad_norm": 3.769254684448242, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1904, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0029027997503592215, | |
| "grad_norm": 1.2325090169906616, | |
| "learning_rate": 0.0, | |
| "loss": 0.1386, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0029027997503592215, | |
| "eval_loss": 0.12809544801712036, | |
| "eval_runtime": 713.8918, | |
| "eval_samples_per_second": 10.16, | |
| "eval_steps_per_second": 5.081, | |
| "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": 1.0542516214431744e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |