File size: 4,059 Bytes
25274dd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.03624173235480656,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007248346470961312,
"grad_norm": 0.07201674580574036,
"learning_rate": 4.999451708687114e-06,
"logits/chosen": -1.9793262481689453,
"logits/rejected": -2.5381760597229004,
"logps/chosen": -0.28126341104507446,
"logps/rejected": -0.3779803514480591,
"loss": 7.3904,
"rewards/accuracies": 0.550000011920929,
"rewards/chosen": -0.4218950867652893,
"rewards/margins": 0.14507544040679932,
"rewards/rejected": -0.5669704675674438,
"step": 10
},
{
"epoch": 0.014496692941922623,
"grad_norm": 0.07562297582626343,
"learning_rate": 4.997807075247147e-06,
"logits/chosen": -2.0567643642425537,
"logits/rejected": -2.4989147186279297,
"logps/chosen": -0.27690139412879944,
"logps/rejected": -0.33544114232063293,
"loss": 7.3756,
"rewards/accuracies": 0.574999988079071,
"rewards/chosen": -0.41535210609436035,
"rewards/margins": 0.08780960738658905,
"rewards/rejected": -0.5031617283821106,
"step": 20
},
{
"epoch": 0.021745039412883936,
"grad_norm": 0.09685570746660233,
"learning_rate": 4.9950668210706795e-06,
"logits/chosen": -2.10174298286438,
"logits/rejected": -2.378197431564331,
"logps/chosen": -0.26717427372932434,
"logps/rejected": -0.30565372109413147,
"loss": 7.451,
"rewards/accuracies": 0.4375,
"rewards/chosen": -0.4007614254951477,
"rewards/margins": 0.05771917849779129,
"rewards/rejected": -0.4584805369377136,
"step": 30
},
{
"epoch": 0.028993385883845247,
"grad_norm": 0.08213861286640167,
"learning_rate": 4.9912321481237616e-06,
"logits/chosen": -2.1633317470550537,
"logits/rejected": -2.387866497039795,
"logps/chosen": -0.27634260058403015,
"logps/rejected": -0.37035584449768066,
"loss": 7.3892,
"rewards/accuracies": 0.6499999761581421,
"rewards/chosen": -0.4145139157772064,
"rewards/margins": 0.14101983606815338,
"rewards/rejected": -0.555533766746521,
"step": 40
},
{
"epoch": 0.03624173235480656,
"grad_norm": 0.08846044540405273,
"learning_rate": 4.986304738420684e-06,
"logits/chosen": -2.1402599811553955,
"logits/rejected": -2.4459526538848877,
"logps/chosen": -0.2535383999347687,
"logps/rejected": -0.3090876042842865,
"loss": 7.5171,
"rewards/accuracies": 0.512499988079071,
"rewards/chosen": -0.3803076148033142,
"rewards/margins": 0.08332376182079315,
"rewards/rejected": -0.4636313319206238,
"step": 50
},
{
"epoch": 0.03624173235480656,
"eval_logits/chosen": -2.1165692806243896,
"eval_logits/rejected": -2.476428747177124,
"eval_logps/chosen": -0.2828062176704407,
"eval_logps/rejected": -0.3432886600494385,
"eval_loss": 0.9120001792907715,
"eval_rewards/accuracies": 0.5089285969734192,
"eval_rewards/chosen": -0.4242093861103058,
"eval_rewards/margins": 0.09072363376617432,
"eval_rewards/rejected": -0.5149329900741577,
"eval_runtime": 30.971,
"eval_samples_per_second": 28.801,
"eval_steps_per_second": 3.616,
"step": 50
}
],
"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": 1.864510672595845e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|