| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.23645320197044334, | |
| "eval_steps": 8, | |
| "global_step": 24, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009852216748768473, | |
| "grad_norm": 0.416106641292572, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7603, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009852216748768473, | |
| "eval_loss": 0.8975884318351746, | |
| "eval_runtime": 118.1684, | |
| "eval_samples_per_second": 1.447, | |
| "eval_steps_per_second": 0.728, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019704433497536946, | |
| "grad_norm": 0.5168540477752686, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0619, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.029556650246305417, | |
| "grad_norm": 0.3925149440765381, | |
| "learning_rate": 3e-05, | |
| "loss": 0.8452, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03940886699507389, | |
| "grad_norm": 0.4349324405193329, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0615, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04926108374384237, | |
| "grad_norm": 0.336223304271698, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9926, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.059113300492610835, | |
| "grad_norm": 0.3589650094509125, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6723, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 0.4258517920970917, | |
| "learning_rate": 7e-05, | |
| "loss": 0.7643, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07881773399014778, | |
| "grad_norm": 0.38350096344947815, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8629, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07881773399014778, | |
| "eval_loss": 0.7800611257553101, | |
| "eval_runtime": 29.2308, | |
| "eval_samples_per_second": 5.85, | |
| "eval_steps_per_second": 2.942, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08866995073891626, | |
| "grad_norm": 0.4130725860595703, | |
| "learning_rate": 9e-05, | |
| "loss": 0.9186, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09852216748768473, | |
| "grad_norm": 0.4786558151245117, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6656, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10837438423645321, | |
| "grad_norm": 0.45567965507507324, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.8369, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11822660098522167, | |
| "grad_norm": 0.44564610719680786, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.6533, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12807881773399016, | |
| "grad_norm": 0.4153067469596863, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 0.7473, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 0.4901822805404663, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.42, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1477832512315271, | |
| "grad_norm": 0.4641437828540802, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6957, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15763546798029557, | |
| "grad_norm": 0.5527058243751526, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.9599, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15763546798029557, | |
| "eval_loss": 0.6261801719665527, | |
| "eval_runtime": 29.3343, | |
| "eval_samples_per_second": 5.829, | |
| "eval_steps_per_second": 2.932, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16748768472906403, | |
| "grad_norm": 0.44595250487327576, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.5655, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17733990147783252, | |
| "grad_norm": 0.3530769646167755, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.3349, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18719211822660098, | |
| "grad_norm": 0.3304716944694519, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 0.4219, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19704433497536947, | |
| "grad_norm": 0.32741332054138184, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5405, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "grad_norm": 0.32143503427505493, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.5708, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21674876847290642, | |
| "grad_norm": 0.369148850440979, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.8169, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.22660098522167488, | |
| "grad_norm": 0.27789416909217834, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.3423, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.23645320197044334, | |
| "grad_norm": 0.32239577174186707, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.4614, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23645320197044334, | |
| "eval_loss": 0.6010122895240784, | |
| "eval_runtime": 29.4041, | |
| "eval_samples_per_second": 5.816, | |
| "eval_steps_per_second": 2.925, | |
| "step": 24 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 8, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3421542911875482e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |