File size: 6,132 Bytes
9b7fc67 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 | {
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 4,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"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": 0.25,
"frac_reward_zero_std": 0.0,
"grad_norm": 0.16221363842487335,
"kl": -3.4924596548080444e-10,
"learning_rate": 0.0,
"loss": 0.0,
"num_tokens": 2580.0,
"reward": -0.22999998927116394,
"reward_std": 1.088944435119629,
"rewards/reward_environment_execution/mean": -0.23000000417232513,
"rewards/reward_environment_execution/std": 0.3818376660346985,
"rewards/reward_format_compliance/mean": -0.15000000596046448,
"rewards/reward_format_compliance/std": 0.4949747622013092,
"rewards/reward_investigation_quality/mean": 0.15000000596046448,
"rewards/reward_investigation_quality/std": 0.2121320366859436,
"rewards/reward_os_mechanics/mean": 0.0,
"rewards/reward_os_mechanics/std": 0.0,
"step": 1
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"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": 0.5,
"frac_reward_zero_std": 1.0,
"grad_norm": 3.505946644111191e-09,
"kl": -4.656612873077393e-10,
"learning_rate": 5.000000000000001e-07,
"loss": -1.8626451075975936e-11,
"num_tokens": 5158.0,
"reward": 0.5400000214576721,
"reward_std": 0.0,
"rewards/reward_environment_execution/mean": 0.03999999910593033,
"rewards/reward_environment_execution/std": 0.0,
"rewards/reward_format_compliance/mean": 0.20000000298023224,
"rewards/reward_format_compliance/std": 0.0,
"rewards/reward_investigation_quality/mean": 0.30000001192092896,
"rewards/reward_investigation_quality/std": 0.0,
"rewards/reward_os_mechanics/mean": 0.0,
"rewards/reward_os_mechanics/std": 0.0,
"step": 2
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"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": 0.75,
"frac_reward_zero_std": 0.0,
"grad_norm": 0.20935378968715668,
"kl": 5.7238503359258175e-06,
"learning_rate": 1.0000000000000002e-06,
"loss": 2.384185791015625e-07,
"num_tokens": 7736.0,
"reward": -0.22999998927116394,
"reward_std": 1.088944435119629,
"rewards/reward_environment_execution/mean": -0.23000000417232513,
"rewards/reward_environment_execution/std": 0.3818376660346985,
"rewards/reward_format_compliance/mean": -0.15000000596046448,
"rewards/reward_format_compliance/std": 0.4949747622013092,
"rewards/reward_investigation_quality/mean": 0.15000000596046448,
"rewards/reward_investigation_quality/std": 0.2121320366859436,
"rewards/reward_os_mechanics/mean": 0.0,
"rewards/reward_os_mechanics/std": 0.0,
"step": 3
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"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": 1.0,
"frac_reward_zero_std": 0.0,
"grad_norm": 0.16330939531326294,
"kl": 5.532288923859596e-06,
"learning_rate": 1.5e-06,
"loss": 2.384185791015625e-07,
"num_tokens": 10392.0,
"reward": -0.22999998927116394,
"reward_std": 1.088944435119629,
"rewards/reward_environment_execution/mean": -0.23000000417232513,
"rewards/reward_environment_execution/std": 0.3818376660346985,
"rewards/reward_format_compliance/mean": -0.15000000596046448,
"rewards/reward_format_compliance/std": 0.4949747622013092,
"rewards/reward_investigation_quality/mean": 0.15000000596046448,
"rewards/reward_investigation_quality/std": 0.2121320366859436,
"rewards/reward_os_mechanics/mean": 0.0,
"rewards/reward_os_mechanics/std": 0.0,
"step": 4
}
],
"logging_steps": 1,
"max_steps": 4,
"num_input_tokens_seen": 10392,
"num_train_epochs": 1,
"save_steps": 999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|