| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 2000, | |
| "global_step": 6782, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.26570333235034e-06, | |
| "loss": 0.6511, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.529932173400177e-06, | |
| "loss": 0.6334, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.792686523149514e-06, | |
| "loss": 0.6255, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.05544087289885e-06, | |
| "loss": 0.616, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.6266611041779805, | |
| "eval_fscore": 0.6266318238581281, | |
| "eval_loss": 0.6498423218727112, | |
| "eval_precision": 0.6295307854237061, | |
| "eval_recall": 0.629852593471248, | |
| "eval_runtime": 927.8313, | |
| "eval_samples_per_second": 899.042, | |
| "eval_steps_per_second": 14.048, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.318195222648187e-06, | |
| "loss": 0.6115, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.580949572397524e-06, | |
| "loss": 0.6085, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.84370392214686e-06, | |
| "loss": 0.6009, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.106458271896196e-06, | |
| "loss": 0.6033, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.6227865430931033, | |
| "eval_fscore": 0.6227524751090208, | |
| "eval_loss": 0.6584447622299194, | |
| "eval_precision": 0.627835745995615, | |
| "eval_recall": 0.627405168660975, | |
| "eval_runtime": 922.5319, | |
| "eval_samples_per_second": 904.206, | |
| "eval_steps_per_second": 14.129, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.3692126216455325e-06, | |
| "loss": 0.5969, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.6334414626953703e-06, | |
| "loss": 0.5968, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.897670303745208e-06, | |
| "loss": 0.5922, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.1604246534945445e-06, | |
| "loss": 0.5896, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.6289963903764151, | |
| "eval_fscore": 0.6282163376402503, | |
| "eval_loss": 0.659950852394104, | |
| "eval_precision": 0.6285056225987752, | |
| "eval_recall": 0.6292816037736055, | |
| "eval_runtime": 919.1018, | |
| "eval_samples_per_second": 907.581, | |
| "eval_steps_per_second": 14.181, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.231790032438809e-07, | |
| "loss": 0.5894, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 6782, | |
| "total_flos": 5.709819056802048e+16, | |
| "train_loss": 0.6080337204928948, | |
| "train_runtime": 5529.9878, | |
| "train_samples_per_second": 156.971, | |
| "train_steps_per_second": 1.226 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6782, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 5.709819056802048e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |