| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001505253334136135, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0105066682722702e-05, | |
| "eval_loss": 2.0711593627929688, | |
| "eval_runtime": 528.8979, | |
| "eval_samples_per_second": 26.446, | |
| "eval_steps_per_second": 13.224, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015052533341361352, | |
| "grad_norm": 0.18690688908100128, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0801, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00030105066682722703, | |
| "grad_norm": 0.18453490734100342, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0853, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00030105066682722703, | |
| "eval_loss": 2.0662031173706055, | |
| "eval_runtime": 521.92, | |
| "eval_samples_per_second": 26.799, | |
| "eval_steps_per_second": 13.401, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004515760002408405, | |
| "grad_norm": 0.2420434206724167, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0589, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006021013336544541, | |
| "grad_norm": 0.2056291550397873, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.0933, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006021013336544541, | |
| "eval_loss": 2.048297882080078, | |
| "eval_runtime": 522.1362, | |
| "eval_samples_per_second": 26.788, | |
| "eval_steps_per_second": 13.395, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007526266670680675, | |
| "grad_norm": 0.24101394414901733, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0368, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.000903152000481681, | |
| "grad_norm": 0.2567429542541504, | |
| "learning_rate": 5e-05, | |
| "loss": 2.095, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.000903152000481681, | |
| "eval_loss": 2.038041830062866, | |
| "eval_runtime": 520.5502, | |
| "eval_samples_per_second": 26.87, | |
| "eval_steps_per_second": 13.436, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0010536773338952945, | |
| "grad_norm": 0.22794471681118011, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9769, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0012042026673089081, | |
| "grad_norm": 0.2649514973163605, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.0423, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0012042026673089081, | |
| "eval_loss": 2.0345399379730225, | |
| "eval_runtime": 520.2716, | |
| "eval_samples_per_second": 26.884, | |
| "eval_steps_per_second": 13.443, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0013547280007225216, | |
| "grad_norm": 0.2631724774837494, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.0381, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.001505253334136135, | |
| "grad_norm": 0.2650676965713501, | |
| "learning_rate": 0.0, | |
| "loss": 2.0805, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.001505253334136135, | |
| "eval_loss": 2.0340166091918945, | |
| "eval_runtime": 519.8158, | |
| "eval_samples_per_second": 26.908, | |
| "eval_steps_per_second": 13.455, | |
| "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": 3124324152115200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |