phi3m0128-wds-0.7-kendall-onof-ofif-corr-max-2-simpo-max1500-default
/
checkpoint-100
/trainer_state.json
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0918800964741013, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00918800964741013, | |
| "grad_norm": 0.036612071096897125, | |
| "learning_rate": 4.999451708687114e-06, | |
| "logits/chosen": 15.01579761505127, | |
| "logits/rejected": 15.359031677246094, | |
| "logps/chosen": -0.2681262791156769, | |
| "logps/rejected": -0.31947994232177734, | |
| "loss": 0.9551, | |
| "rewards/accuracies": 0.4749999940395355, | |
| "rewards/chosen": -0.40218934416770935, | |
| "rewards/margins": 0.07703053951263428, | |
| "rewards/rejected": -0.479219913482666, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01837601929482026, | |
| "grad_norm": 0.05575725808739662, | |
| "learning_rate": 4.997807075247147e-06, | |
| "logits/chosen": 14.570712089538574, | |
| "logits/rejected": 15.321355819702148, | |
| "logps/chosen": -0.2867889404296875, | |
| "logps/rejected": -0.3514837622642517, | |
| "loss": 0.923, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/chosen": -0.43018341064453125, | |
| "rewards/margins": 0.09704220294952393, | |
| "rewards/rejected": -0.5272256135940552, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02756402894223039, | |
| "grad_norm": 0.0492466576397419, | |
| "learning_rate": 4.9950668210706795e-06, | |
| "logits/chosen": 14.748420715332031, | |
| "logits/rejected": 14.969354629516602, | |
| "logps/chosen": -0.28405922651290894, | |
| "logps/rejected": -0.32855403423309326, | |
| "loss": 0.9357, | |
| "rewards/accuracies": 0.5, | |
| "rewards/chosen": -0.426088809967041, | |
| "rewards/margins": 0.06674225628376007, | |
| "rewards/rejected": -0.4928310811519623, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03675203858964052, | |
| "grad_norm": 0.05719422921538353, | |
| "learning_rate": 4.9912321481237616e-06, | |
| "logits/chosen": 14.28278923034668, | |
| "logits/rejected": 14.76964282989502, | |
| "logps/chosen": -0.27940627932548523, | |
| "logps/rejected": -0.3408831059932709, | |
| "loss": 0.9215, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -0.41910940408706665, | |
| "rewards/margins": 0.09221524000167847, | |
| "rewards/rejected": -0.5113246440887451, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04594004823705065, | |
| "grad_norm": 0.06247895210981369, | |
| "learning_rate": 4.986304738420684e-06, | |
| "logits/chosen": 14.943578720092773, | |
| "logits/rejected": 14.936178207397461, | |
| "logps/chosen": -0.2819541394710541, | |
| "logps/rejected": -0.3245392441749573, | |
| "loss": 0.9464, | |
| "rewards/accuracies": 0.4749999940395355, | |
| "rewards/chosen": -0.4229312539100647, | |
| "rewards/margins": 0.06387762725353241, | |
| "rewards/rejected": -0.4868088662624359, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04594004823705065, | |
| "eval_logits/chosen": 14.7594575881958, | |
| "eval_logits/rejected": 15.193694114685059, | |
| "eval_logps/chosen": -0.2807807922363281, | |
| "eval_logps/rejected": -0.36209535598754883, | |
| "eval_loss": 0.9397181868553162, | |
| "eval_rewards/accuracies": 0.5681818127632141, | |
| "eval_rewards/chosen": -0.4211711883544922, | |
| "eval_rewards/margins": 0.12197184562683105, | |
| "eval_rewards/rejected": -0.5431429743766785, | |
| "eval_runtime": 24.9762, | |
| "eval_samples_per_second": 28.187, | |
| "eval_steps_per_second": 3.523, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05512805788446078, | |
| "grad_norm": 0.11519577354192734, | |
| "learning_rate": 4.980286753286196e-06, | |
| "logits/chosen": 14.996228218078613, | |
| "logits/rejected": 15.37781810760498, | |
| "logps/chosen": -0.2809831202030182, | |
| "logps/rejected": -0.35486167669296265, | |
| "loss": 0.9318, | |
| "rewards/accuracies": 0.5625, | |
| "rewards/chosen": -0.4214746952056885, | |
| "rewards/margins": 0.1108178049325943, | |
| "rewards/rejected": -0.5322924852371216, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06431606753187091, | |
| "grad_norm": 0.06691388040781021, | |
| "learning_rate": 4.973180832407471e-06, | |
| "logits/chosen": 14.612454414367676, | |
| "logits/rejected": 15.678136825561523, | |
| "logps/chosen": -0.2569667100906372, | |
| "logps/rejected": -0.40047627687454224, | |
| "loss": 0.9158, | |
| "rewards/accuracies": 0.75, | |
| "rewards/chosen": -0.3854501247406006, | |
| "rewards/margins": 0.21526429057121277, | |
| "rewards/rejected": -0.600714385509491, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07350407717928104, | |
| "grad_norm": 0.05976058170199394, | |
| "learning_rate": 4.964990092676263e-06, | |
| "logits/chosen": 14.873895645141602, | |
| "logits/rejected": 15.50474739074707, | |
| "logps/chosen": -0.28742527961730957, | |
| "logps/rejected": -0.37555089592933655, | |
| "loss": 0.9372, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -0.43113788962364197, | |
| "rewards/margins": 0.13218846917152405, | |
| "rewards/rejected": -0.5633264183998108, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08269208682669117, | |
| "grad_norm": 0.0602131113409996, | |
| "learning_rate": 4.9557181268217225e-06, | |
| "logits/chosen": 14.356691360473633, | |
| "logits/rejected": 14.895658493041992, | |
| "logps/chosen": -0.2613506317138672, | |
| "logps/rejected": -0.3317110538482666, | |
| "loss": 0.9324, | |
| "rewards/accuracies": 0.5625, | |
| "rewards/chosen": -0.3920259475708008, | |
| "rewards/margins": 0.10554064810276031, | |
| "rewards/rejected": -0.4975665509700775, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0918800964741013, | |
| "grad_norm": 0.07126503437757492, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "logits/chosen": 14.862826347351074, | |
| "logits/rejected": 15.257089614868164, | |
| "logps/chosen": -0.2707213759422302, | |
| "logps/rejected": -0.3511395752429962, | |
| "loss": 0.9353, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": -0.4060820937156677, | |
| "rewards/margins": 0.1206272691488266, | |
| "rewards/rejected": -0.5267094373703003, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0918800964741013, | |
| "eval_logits/chosen": 14.664334297180176, | |
| "eval_logits/rejected": 15.113536834716797, | |
| "eval_logps/chosen": -0.2750833034515381, | |
| "eval_logps/rejected": -0.36540210247039795, | |
| "eval_loss": 0.9324077367782593, | |
| "eval_rewards/accuracies": 0.5795454382896423, | |
| "eval_rewards/chosen": -0.41262495517730713, | |
| "eval_rewards/margins": 0.1354781985282898, | |
| "eval_rewards/rejected": -0.5481031537055969, | |
| "eval_runtime": 24.4286, | |
| "eval_samples_per_second": 28.819, | |
| "eval_steps_per_second": 3.602, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.437219994304512e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |