File size: 3,879 Bytes
6191cfa |
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 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0038828919779451735,
"eval_steps": 500,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"completion_length": 512.0,
"completions/clipped_ratio": 1.0,
"completions/max_length": 512.0,
"completions/max_terminated_length": 0.0,
"completions/mean_length": 512.0,
"completions/mean_terminated_length": 0.0,
"completions/min_length": 512.0,
"completions/min_terminated_length": 0.0,
"epoch": 0.0009707229944862934,
"frac_reward_zero_std": 0.61,
"grad_norm": 0.02464698627591133,
"kl": 0.03792417001328431,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.0,
"num_tokens": 222000.0,
"reward": 0.43,
"reward_std": 0.20350852847099304,
"rewards/compute_reward/mean": 0.43,
"rewards/compute_reward/std": 0.3326409870386124,
"step": 50
},
{
"completion_length": 512.0,
"completions/clipped_ratio": 1.0,
"completions/max_length": 512.0,
"completions/max_terminated_length": 0.0,
"completions/mean_length": 512.0,
"completions/mean_terminated_length": 0.0,
"completions/min_length": 512.0,
"completions/min_terminated_length": 0.0,
"epoch": 0.0019414459889725867,
"frac_reward_zero_std": 0.67,
"grad_norm": 0.020398980006575584,
"kl": 0.27587527528405187,
"learning_rate": 4.855143631968242e-06,
"loss": 0.0003,
"num_tokens": 444000.0,
"reward": 0.4275,
"reward_std": 0.17582903623580934,
"rewards/compute_reward/mean": 0.4275,
"rewards/compute_reward/std": 0.40157180368900297,
"step": 100
},
{
"completion_length": 512.0,
"completions/clipped_ratio": 1.0,
"completions/max_length": 512.0,
"completions/max_terminated_length": 0.0,
"completions/mean_length": 512.0,
"completions/mean_terminated_length": 0.0,
"completions/min_length": 512.0,
"completions/min_terminated_length": 0.0,
"epoch": 0.00291216898345888,
"frac_reward_zero_std": 0.66,
"grad_norm": 0.02328324504196644,
"kl": 0.2890375615656376,
"learning_rate": 4.426283106939474e-06,
"loss": 0.0003,
"num_tokens": 666000.0,
"reward": 0.425,
"reward_std": 0.17928203105926513,
"rewards/compute_reward/mean": 0.425,
"rewards/compute_reward/std": 0.3971991038322449,
"step": 150
},
{
"completion_length": 512.0,
"completions/clipped_ratio": 1.0,
"completions/max_length": 512.0,
"completions/max_terminated_length": 0.0,
"completions/mean_length": 512.0,
"completions/mean_terminated_length": 0.0,
"completions/min_length": 512.0,
"completions/min_terminated_length": 0.0,
"epoch": 0.0038828919779451735,
"frac_reward_zero_std": 0.62,
"grad_norm": 5.6864848136901855,
"kl": 0.496561706662178,
"learning_rate": 3.7650844103029093e-06,
"loss": 0.0005,
"num_tokens": 888000.0,
"reward": 0.475,
"reward_std": 0.19928203105926515,
"rewards/compute_reward/mean": 0.475,
"rewards/compute_reward/std": 0.3720254868268967,
"step": 200
}
],
"logging_steps": 50,
"max_steps": 500,
"num_input_tokens_seen": 888000,
"num_train_epochs": 1,
"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": 0.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|