phi3m0128-wds-0.75-kendall-onof-ofif-corr-max-2-simpo-max1500-default
/
checkpoint-100
/trainer_state.json
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08880994671403197, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008880994671403197, | |
| "grad_norm": 0.045356735587120056, | |
| "learning_rate": 4.999451708687114e-06, | |
| "logits/chosen": 14.352750778198242, | |
| "logits/rejected": 14.82281494140625, | |
| "logps/chosen": -0.2592294216156006, | |
| "logps/rejected": -0.32852867245674133, | |
| "loss": 0.9315, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": -0.38884416222572327, | |
| "rewards/margins": 0.10394889116287231, | |
| "rewards/rejected": -0.4927930235862732, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017761989342806393, | |
| "grad_norm": 0.05255189165472984, | |
| "learning_rate": 4.997807075247147e-06, | |
| "logits/chosen": 14.80792236328125, | |
| "logits/rejected": 15.017183303833008, | |
| "logps/chosen": -0.2825874388217926, | |
| "logps/rejected": -0.36373966932296753, | |
| "loss": 0.9318, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -0.4238811433315277, | |
| "rewards/margins": 0.12172831594944, | |
| "rewards/rejected": -0.5456094741821289, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02664298401420959, | |
| "grad_norm": 0.056027185171842575, | |
| "learning_rate": 4.9950668210706795e-06, | |
| "logits/chosen": 14.45336627960205, | |
| "logits/rejected": 15.261484146118164, | |
| "logps/chosen": -0.2638034522533417, | |
| "logps/rejected": -0.37216562032699585, | |
| "loss": 0.9211, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -0.3957051932811737, | |
| "rewards/margins": 0.1625431776046753, | |
| "rewards/rejected": -0.5582484006881714, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.035523978685612786, | |
| "grad_norm": 0.06511653959751129, | |
| "learning_rate": 4.9912321481237616e-06, | |
| "logits/chosen": 14.59851360321045, | |
| "logits/rejected": 15.112770080566406, | |
| "logps/chosen": -0.28972768783569336, | |
| "logps/rejected": -0.36043626070022583, | |
| "loss": 0.941, | |
| "rewards/accuracies": 0.5375000238418579, | |
| "rewards/chosen": -0.43459147214889526, | |
| "rewards/margins": 0.10606291145086288, | |
| "rewards/rejected": -0.5406544208526611, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04440497335701599, | |
| "grad_norm": 0.0637577474117279, | |
| "learning_rate": 4.986304738420684e-06, | |
| "logits/chosen": 14.678179740905762, | |
| "logits/rejected": 15.114399909973145, | |
| "logps/chosen": -0.3033604919910431, | |
| "logps/rejected": -0.3262741267681122, | |
| "loss": 0.929, | |
| "rewards/accuracies": 0.44999998807907104, | |
| "rewards/chosen": -0.45504075288772583, | |
| "rewards/margins": 0.03437047079205513, | |
| "rewards/rejected": -0.4894111752510071, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04440497335701599, | |
| "eval_logits/chosen": 14.936029434204102, | |
| "eval_logits/rejected": 14.780267715454102, | |
| "eval_logps/chosen": -0.29386037588119507, | |
| "eval_logps/rejected": -0.3304942548274994, | |
| "eval_loss": 0.9458721876144409, | |
| "eval_rewards/accuracies": 0.49450549483299255, | |
| "eval_rewards/chosen": -0.4407905340194702, | |
| "eval_rewards/margins": 0.05495081841945648, | |
| "eval_rewards/rejected": -0.49574142694473267, | |
| "eval_runtime": 27.7436, | |
| "eval_samples_per_second": 26.24, | |
| "eval_steps_per_second": 3.28, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05328596802841918, | |
| "grad_norm": 0.06470987200737, | |
| "learning_rate": 4.980286753286196e-06, | |
| "logits/chosen": 14.19079303741455, | |
| "logits/rejected": 14.986845016479492, | |
| "logps/chosen": -0.26126712560653687, | |
| "logps/rejected": -0.31976616382598877, | |
| "loss": 0.9335, | |
| "rewards/accuracies": 0.5, | |
| "rewards/chosen": -0.3919006288051605, | |
| "rewards/margins": 0.08774860948324203, | |
| "rewards/rejected": -0.47964924573898315, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06216696269982238, | |
| "grad_norm": 0.06163545697927475, | |
| "learning_rate": 4.973180832407471e-06, | |
| "logits/chosen": 14.062408447265625, | |
| "logits/rejected": 15.050743103027344, | |
| "logps/chosen": -0.2698076367378235, | |
| "logps/rejected": -0.37131980061531067, | |
| "loss": 0.9234, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": -0.4047114849090576, | |
| "rewards/margins": 0.1522682160139084, | |
| "rewards/rejected": -0.556979775428772, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07104795737122557, | |
| "grad_norm": 0.05943402647972107, | |
| "learning_rate": 4.964990092676263e-06, | |
| "logits/chosen": 14.523780822753906, | |
| "logits/rejected": 15.173608779907227, | |
| "logps/chosen": -0.2835150957107544, | |
| "logps/rejected": -0.35379332304000854, | |
| "loss": 0.9317, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -0.4252726137638092, | |
| "rewards/margins": 0.10541732609272003, | |
| "rewards/rejected": -0.5306899547576904, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07992895204262877, | |
| "grad_norm": 0.05566830188035965, | |
| "learning_rate": 4.9557181268217225e-06, | |
| "logits/chosen": 14.752237319946289, | |
| "logits/rejected": 15.213434219360352, | |
| "logps/chosen": -0.25490278005599976, | |
| "logps/rejected": -0.31673288345336914, | |
| "loss": 0.9276, | |
| "rewards/accuracies": 0.5625, | |
| "rewards/chosen": -0.38235417008399963, | |
| "rewards/margins": 0.09274514764547348, | |
| "rewards/rejected": -0.4750993847846985, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08880994671403197, | |
| "grad_norm": 0.07879115641117096, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "logits/chosen": 14.362078666687012, | |
| "logits/rejected": 14.708786010742188, | |
| "logps/chosen": -0.27969443798065186, | |
| "logps/rejected": -0.3294224143028259, | |
| "loss": 0.9448, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -0.41954168677330017, | |
| "rewards/margins": 0.0745919868350029, | |
| "rewards/rejected": -0.4941336512565613, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08880994671403197, | |
| "eval_logits/chosen": 14.668691635131836, | |
| "eval_logits/rejected": 14.53217601776123, | |
| "eval_logps/chosen": -0.2837528884410858, | |
| "eval_logps/rejected": -0.33105531334877014, | |
| "eval_loss": 0.9382757544517517, | |
| "eval_rewards/accuracies": 0.5164835453033447, | |
| "eval_rewards/chosen": -0.4256293475627899, | |
| "eval_rewards/margins": 0.07095365226268768, | |
| "eval_rewards/rejected": -0.4965830445289612, | |
| "eval_runtime": 26.9204, | |
| "eval_samples_per_second": 27.043, | |
| "eval_steps_per_second": 3.38, | |
| "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": 2.4411965756748595e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |