| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9991993594875901, | |
| "eval_steps": 4, | |
| "global_step": 78, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.051240992794235385, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.3607, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10248198558847077, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.3651, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15372297838270615, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.3502, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.20496397117694154, | |
| "grad_norm": 0.31328025460243225, | |
| "learning_rate": 0.001414213562373095, | |
| "loss": 2.2356, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2562049639711769, | |
| "grad_norm": 3.1803669929504395, | |
| "learning_rate": 0.001, | |
| "loss": 2.6229, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3074459567654123, | |
| "grad_norm": 1.0720810890197754, | |
| "learning_rate": 0.0007071067811865475, | |
| "loss": 2.6229, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3586869495596477, | |
| "grad_norm": 0.9110113978385925, | |
| "learning_rate": 0.0005773502691896259, | |
| "loss": 1.9729, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4099279423538831, | |
| "grad_norm": 0.6526729464530945, | |
| "learning_rate": 0.0005, | |
| "loss": 1.8264, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4611689351481185, | |
| "grad_norm": 0.5115967392921448, | |
| "learning_rate": 0.00044721359549995795, | |
| "loss": 1.7511, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5124099279423538, | |
| "grad_norm": 0.40264543890953064, | |
| "learning_rate": 0.0004082482904638631, | |
| "loss": 1.6792, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5636509207365893, | |
| "grad_norm": 0.41392064094543457, | |
| "learning_rate": 0.0003779644730092272, | |
| "loss": 1.681, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6148919135308246, | |
| "grad_norm": 0.42952096462249756, | |
| "learning_rate": 0.00035355339059327376, | |
| "loss": 1.614, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6661329063250601, | |
| "grad_norm": 0.4605095386505127, | |
| "learning_rate": 0.0003333333333333333, | |
| "loss": 1.5879, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.7173738991192954, | |
| "grad_norm": 0.4642864763736725, | |
| "learning_rate": 0.00031622776601683794, | |
| "loss": 1.5134, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7686148919135308, | |
| "grad_norm": 0.528487503528595, | |
| "learning_rate": 0.00030151134457776364, | |
| "loss": 1.5332, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8198558847077662, | |
| "grad_norm": 0.4958159327507019, | |
| "learning_rate": 0.00028867513459481295, | |
| "loss": 1.4743, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8710968775020016, | |
| "grad_norm": 0.5096175074577332, | |
| "learning_rate": 0.0002773500981126146, | |
| "loss": 1.4847, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.922337870296237, | |
| "grad_norm": 0.5336413979530334, | |
| "learning_rate": 0.0002672612419124244, | |
| "loss": 1.4188, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.9735788630904724, | |
| "grad_norm": 0.563066840171814, | |
| "learning_rate": 0.0002581988897471611, | |
| "loss": 1.4082, | |
| "step": 76 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 78, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.922041751265608e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |