Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- Area_Time/checkpoint-200/special_tokens_map.json +23 -0
- Area_Time/checkpoint-200/tokenizer.json +0 -0
- Area_Time/checkpoint-200/trainer_state.json +333 -0
- Area_Time/checkpoint-250/README.md +202 -0
- Area_Time/checkpoint-250/adapter_config.json +34 -0
- Area_Time/checkpoint-250/special_tokens_map.json +23 -0
- Area_Time/checkpoint-250/tokenizer.json +0 -0
- Area_Time/checkpoint-250/tokenizer_config.json +196 -0
- Area_Time/checkpoint-250/trainer_state.json +408 -0
- Area_Time/checkpoint-300/README.md +202 -0
- Area_Time/checkpoint-300/adapter_config.json +34 -0
- Area_Time/checkpoint-300/special_tokens_map.json +23 -0
- Area_Time/checkpoint-300/tokenizer.json +0 -0
- Area_Time/checkpoint-300/tokenizer_config.json +196 -0
- Area_Time/checkpoint-300/trainer_state.json +483 -0
- Area_Time/checkpoint-350/README.md +202 -0
- Area_Time/checkpoint-350/adapter_config.json +34 -0
- Area_Time/checkpoint-350/special_tokens_map.json +23 -0
- Area_Time/checkpoint-350/tokenizer.json +0 -0
- Area_Time/checkpoint-350/tokenizer_config.json +196 -0
- Area_Time/checkpoint-350/trainer_state.json +558 -0
- Area_Time/checkpoint-400/README.md +202 -0
- Area_Time/checkpoint-400/adapter_config.json +34 -0
- Area_Time/checkpoint-400/special_tokens_map.json +23 -0
- Area_Time/checkpoint-400/tokenizer.json +0 -0
- Area_Time/checkpoint-400/tokenizer_config.json +196 -0
- Area_Time/checkpoint-400/trainer_state.json +633 -0
- Area_Time/checkpoint-450/README.md +202 -0
- Area_Time/checkpoint-450/adapter_config.json +34 -0
- Area_Time/checkpoint-450/special_tokens_map.json +23 -0
- Area_Time/checkpoint-450/tokenizer.json +0 -0
- Area_Time/checkpoint-450/tokenizer_config.json +196 -0
- Area_Time/checkpoint-450/trainer_state.json +708 -0
- Area_Time/checkpoint-500/README.md +202 -0
- Area_Time/checkpoint-500/adapter_config.json +34 -0
- Area_Time/checkpoint-500/special_tokens_map.json +23 -0
- Area_Time/checkpoint-500/tokenizer.json +0 -0
- Area_Time/checkpoint-500/tokenizer_config.json +196 -0
- Area_Time/checkpoint-500/trainer_state.json +783 -0
- Area_Time/checkpoint-540/README.md +202 -0
- Area_Time/checkpoint-540/adapter_config.json +34 -0
- Area_Time/checkpoint-540/special_tokens_map.json +23 -0
- Area_Time/checkpoint-540/tokenizer.json +0 -0
- Area_Time/checkpoint-540/tokenizer_config.json +196 -0
- Area_Time/checkpoint-540/trainer_state.json +843 -0
- Power/checkpoint-350/adapter_model.safetensors +3 -0
- Power_Area_Time/README.md +62 -0
- Power_Area_Time/adapter_config.json +34 -0
- Power_Area_Time/all_results.json +8 -0
- Power_Area_Time/checkpoint-100/README.md +202 -0
Area_Time/checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Area_Time/checkpoint-200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_Time/checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,333 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.207207207207207,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36036036036036034,
|
| 13 |
+
"grad_norm": 0.5300200581550598,
|
| 14 |
+
"learning_rate": 9.259259259259259e-07,
|
| 15 |
+
"logits/chosen": 1.7405741214752197,
|
| 16 |
+
"logits/rejected": 1.663368582725525,
|
| 17 |
+
"logps/chosen": -97.57881164550781,
|
| 18 |
+
"logps/rejected": -70.59793853759766,
|
| 19 |
+
"loss": 0.6938,
|
| 20 |
+
"rewards/accuracies": 0.4375,
|
| 21 |
+
"rewards/chosen": 0.0018835498485714197,
|
| 22 |
+
"rewards/margins": -0.0008800366776995361,
|
| 23 |
+
"rewards/rejected": 0.0027635858859866858,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7207207207207207,
|
| 28 |
+
"grad_norm": 0.4883837401866913,
|
| 29 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 30 |
+
"logits/chosen": 1.8280715942382812,
|
| 31 |
+
"logits/rejected": 1.8215343952178955,
|
| 32 |
+
"logps/chosen": -90.60624694824219,
|
| 33 |
+
"logps/rejected": -79.04981994628906,
|
| 34 |
+
"loss": 0.6945,
|
| 35 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 36 |
+
"rewards/chosen": 0.0014454321935772896,
|
| 37 |
+
"rewards/margins": -0.004174981266260147,
|
| 38 |
+
"rewards/rejected": 0.005620413459837437,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0810810810810811,
|
| 43 |
+
"grad_norm": 0.5554109215736389,
|
| 44 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 45 |
+
"logits/chosen": 1.7980501651763916,
|
| 46 |
+
"logits/rejected": 1.841104507446289,
|
| 47 |
+
"logps/chosen": -80.78228759765625,
|
| 48 |
+
"logps/rejected": -85.08882141113281,
|
| 49 |
+
"loss": 0.693,
|
| 50 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 51 |
+
"rewards/chosen": 0.0042568682692945,
|
| 52 |
+
"rewards/margins": -0.0038191028870642185,
|
| 53 |
+
"rewards/rejected": 0.008075973019003868,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4414414414414414,
|
| 58 |
+
"grad_norm": 0.537497341632843,
|
| 59 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 60 |
+
"logits/chosen": 1.7320470809936523,
|
| 61 |
+
"logits/rejected": 1.7411377429962158,
|
| 62 |
+
"logps/chosen": -82.24813842773438,
|
| 63 |
+
"logps/rejected": -80.90709686279297,
|
| 64 |
+
"loss": 0.6952,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.00350201572291553,
|
| 67 |
+
"rewards/margins": -0.012091752141714096,
|
| 68 |
+
"rewards/rejected": 0.008589735254645348,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.8018018018018018,
|
| 73 |
+
"grad_norm": 0.5023094415664673,
|
| 74 |
+
"learning_rate": 4.62962962962963e-06,
|
| 75 |
+
"logits/chosen": 1.8292573690414429,
|
| 76 |
+
"logits/rejected": 1.8632844686508179,
|
| 77 |
+
"logps/chosen": -85.98481750488281,
|
| 78 |
+
"logps/rejected": -86.14008331298828,
|
| 79 |
+
"loss": 0.6928,
|
| 80 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 81 |
+
"rewards/chosen": 0.00168000184930861,
|
| 82 |
+
"rewards/margins": -0.011136507615447044,
|
| 83 |
+
"rewards/rejected": 0.01281650923192501,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.1621621621621623,
|
| 88 |
+
"grad_norm": 0.4981901943683624,
|
| 89 |
+
"learning_rate": 4.998119881260576e-06,
|
| 90 |
+
"logits/chosen": 1.8536121845245361,
|
| 91 |
+
"logits/rejected": 1.7948782444000244,
|
| 92 |
+
"logps/chosen": -90.0439682006836,
|
| 93 |
+
"logps/rejected": -79.8309555053711,
|
| 94 |
+
"loss": 0.6914,
|
| 95 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 96 |
+
"rewards/chosen": 0.0025153260212391615,
|
| 97 |
+
"rewards/margins": -0.0021209525875747204,
|
| 98 |
+
"rewards/rejected": 0.004636278375983238,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5225225225225225,
|
| 103 |
+
"grad_norm": 0.6208468079566956,
|
| 104 |
+
"learning_rate": 4.9866405060165044e-06,
|
| 105 |
+
"logits/chosen": 1.7845121622085571,
|
| 106 |
+
"logits/rejected": 1.8721017837524414,
|
| 107 |
+
"logps/chosen": -74.6461181640625,
|
| 108 |
+
"logps/rejected": -98.91078186035156,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 111 |
+
"rewards/chosen": 0.00022823773906566203,
|
| 112 |
+
"rewards/margins": 0.0024594543501734734,
|
| 113 |
+
"rewards/rejected": -0.00223121652379632,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.8828828828828827,
|
| 118 |
+
"grad_norm": 0.5074446797370911,
|
| 119 |
+
"learning_rate": 4.964774158361991e-06,
|
| 120 |
+
"logits/chosen": 1.8522154092788696,
|
| 121 |
+
"logits/rejected": 1.8161392211914062,
|
| 122 |
+
"logps/chosen": -89.16864013671875,
|
| 123 |
+
"logps/rejected": -81.97349548339844,
|
| 124 |
+
"loss": 0.6911,
|
| 125 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 126 |
+
"rewards/chosen": 0.006215038243681192,
|
| 127 |
+
"rewards/margins": 0.005521883722394705,
|
| 128 |
+
"rewards/rejected": 0.0006931538810022175,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.2432432432432434,
|
| 133 |
+
"grad_norm": 0.6148263812065125,
|
| 134 |
+
"learning_rate": 4.93261217644956e-06,
|
| 135 |
+
"logits/chosen": 1.7915083169937134,
|
| 136 |
+
"logits/rejected": 1.7579513788223267,
|
| 137 |
+
"logps/chosen": -88.66618347167969,
|
| 138 |
+
"logps/rejected": -80.2238998413086,
|
| 139 |
+
"loss": 0.6918,
|
| 140 |
+
"rewards/accuracies": 0.574999988079071,
|
| 141 |
+
"rewards/chosen": 0.005774274934083223,
|
| 142 |
+
"rewards/margins": 0.016623441129922867,
|
| 143 |
+
"rewards/rejected": -0.010849165730178356,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.6036036036036037,
|
| 148 |
+
"grad_norm": 0.6143240332603455,
|
| 149 |
+
"learning_rate": 4.8902889044347e-06,
|
| 150 |
+
"logits/chosen": 1.6886920928955078,
|
| 151 |
+
"logits/rejected": 1.8121178150177002,
|
| 152 |
+
"logps/chosen": -72.908203125,
|
| 153 |
+
"logps/rejected": -92.44017028808594,
|
| 154 |
+
"loss": 0.6911,
|
| 155 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 156 |
+
"rewards/chosen": -0.0015121791511774063,
|
| 157 |
+
"rewards/margins": 0.0036420777905732393,
|
| 158 |
+
"rewards/rejected": -0.005154256708920002,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.963963963963964,
|
| 163 |
+
"grad_norm": 0.7140340209007263,
|
| 164 |
+
"learning_rate": 4.837981131305475e-06,
|
| 165 |
+
"logits/chosen": 1.7481105327606201,
|
| 166 |
+
"logits/rejected": 1.723141074180603,
|
| 167 |
+
"logps/chosen": -80.63452911376953,
|
| 168 |
+
"logps/rejected": -72.64492797851562,
|
| 169 |
+
"loss": 0.6894,
|
| 170 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 171 |
+
"rewards/chosen": -0.006246576085686684,
|
| 172 |
+
"rewards/margins": -0.0035218377597630024,
|
| 173 |
+
"rewards/rejected": -0.0027247383259236813,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.324324324324325,
|
| 178 |
+
"grad_norm": 1.1645854711532593,
|
| 179 |
+
"learning_rate": 4.775907352415367e-06,
|
| 180 |
+
"logits/chosen": 1.7416290044784546,
|
| 181 |
+
"logits/rejected": 1.8237574100494385,
|
| 182 |
+
"logps/chosen": -89.01248931884766,
|
| 183 |
+
"logps/rejected": -92.31901550292969,
|
| 184 |
+
"loss": 0.6869,
|
| 185 |
+
"rewards/accuracies": 0.612500011920929,
|
| 186 |
+
"rewards/chosen": -0.008855113759636879,
|
| 187 |
+
"rewards/margins": 0.013151508755981922,
|
| 188 |
+
"rewards/rejected": -0.022006623446941376,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.684684684684685,
|
| 193 |
+
"grad_norm": 0.6638664603233337,
|
| 194 |
+
"learning_rate": 4.70432685680402e-06,
|
| 195 |
+
"logits/chosen": 1.7124770879745483,
|
| 196 |
+
"logits/rejected": 1.7777938842773438,
|
| 197 |
+
"logps/chosen": -84.87271881103516,
|
| 198 |
+
"logps/rejected": -92.4839096069336,
|
| 199 |
+
"loss": 0.6855,
|
| 200 |
+
"rewards/accuracies": 0.574999988079071,
|
| 201 |
+
"rewards/chosen": -0.004437069408595562,
|
| 202 |
+
"rewards/margins": 0.019811339676380157,
|
| 203 |
+
"rewards/rejected": -0.024248410016298294,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.045045045045045,
|
| 208 |
+
"grad_norm": 0.785169780254364,
|
| 209 |
+
"learning_rate": 4.623538644118244e-06,
|
| 210 |
+
"logits/chosen": 1.7838690280914307,
|
| 211 |
+
"logits/rejected": 1.8052574396133423,
|
| 212 |
+
"logps/chosen": -94.57842254638672,
|
| 213 |
+
"logps/rejected": -80.6390609741211,
|
| 214 |
+
"loss": 0.6836,
|
| 215 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 216 |
+
"rewards/chosen": -0.026147600263357162,
|
| 217 |
+
"rewards/margins": 0.010936126112937927,
|
| 218 |
+
"rewards/rejected": -0.03708372637629509,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.405405405405405,
|
| 223 |
+
"grad_norm": 0.745952844619751,
|
| 224 |
+
"learning_rate": 4.533880175657419e-06,
|
| 225 |
+
"logits/chosen": 1.7925735712051392,
|
| 226 |
+
"logits/rejected": 1.7987396717071533,
|
| 227 |
+
"logps/chosen": -82.4854507446289,
|
| 228 |
+
"logps/rejected": -77.50787353515625,
|
| 229 |
+
"loss": 0.6767,
|
| 230 |
+
"rewards/accuracies": 0.625,
|
| 231 |
+
"rewards/chosen": -0.013469865545630455,
|
| 232 |
+
"rewards/margins": 0.04023212194442749,
|
| 233 |
+
"rewards/rejected": -0.053701985627412796,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.7657657657657655,
|
| 238 |
+
"grad_norm": 0.7885063290596008,
|
| 239 |
+
"learning_rate": 4.435725964760331e-06,
|
| 240 |
+
"logits/chosen": 1.7725191116333008,
|
| 241 |
+
"logits/rejected": 1.8345234394073486,
|
| 242 |
+
"logps/chosen": -78.7154541015625,
|
| 243 |
+
"logps/rejected": -80.75708770751953,
|
| 244 |
+
"loss": 0.6721,
|
| 245 |
+
"rewards/accuracies": 0.675000011920929,
|
| 246 |
+
"rewards/chosen": -0.018351273611187935,
|
| 247 |
+
"rewards/margins": 0.05368901416659355,
|
| 248 |
+
"rewards/rejected": -0.07204028964042664,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.126126126126126,
|
| 253 |
+
"grad_norm": 0.7734187245368958,
|
| 254 |
+
"learning_rate": 4.329486012421531e-06,
|
| 255 |
+
"logits/chosen": 1.827528715133667,
|
| 256 |
+
"logits/rejected": 1.7939176559448242,
|
| 257 |
+
"logps/chosen": -75.33561706542969,
|
| 258 |
+
"logps/rejected": -71.34326934814453,
|
| 259 |
+
"loss": 0.6775,
|
| 260 |
+
"rewards/accuracies": 0.612500011920929,
|
| 261 |
+
"rewards/chosen": -0.038218818604946136,
|
| 262 |
+
"rewards/margins": 0.06159939616918564,
|
| 263 |
+
"rewards/rejected": -0.09981821477413177,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.486486486486487,
|
| 268 |
+
"grad_norm": 0.7796682715415955,
|
| 269 |
+
"learning_rate": 4.215604094671835e-06,
|
| 270 |
+
"logits/chosen": 1.729288101196289,
|
| 271 |
+
"logits/rejected": 1.7497504949569702,
|
| 272 |
+
"logps/chosen": -83.02750396728516,
|
| 273 |
+
"logps/rejected": -78.53959655761719,
|
| 274 |
+
"loss": 0.6632,
|
| 275 |
+
"rewards/accuracies": 0.699999988079071,
|
| 276 |
+
"rewards/chosen": -0.03207743167877197,
|
| 277 |
+
"rewards/margins": 0.06858544796705246,
|
| 278 |
+
"rewards/rejected": -0.10066288709640503,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.846846846846847,
|
| 283 |
+
"grad_norm": 0.8168752193450928,
|
| 284 |
+
"learning_rate": 4.094555908876765e-06,
|
| 285 |
+
"logits/chosen": 1.747865080833435,
|
| 286 |
+
"logits/rejected": 1.7993282079696655,
|
| 287 |
+
"logps/chosen": -78.75782775878906,
|
| 288 |
+
"logps/rejected": -85.8946304321289,
|
| 289 |
+
"loss": 0.668,
|
| 290 |
+
"rewards/accuracies": 0.612500011920929,
|
| 291 |
+
"rewards/chosen": -0.0766468197107315,
|
| 292 |
+
"rewards/margins": 0.045263100415468216,
|
| 293 |
+
"rewards/rejected": -0.12190990149974823,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 7.207207207207207,
|
| 298 |
+
"grad_norm": 0.9816763997077942,
|
| 299 |
+
"learning_rate": 3.966847086696045e-06,
|
| 300 |
+
"logits/chosen": 1.792106032371521,
|
| 301 |
+
"logits/rejected": 1.7798125743865967,
|
| 302 |
+
"logps/chosen": -93.53439331054688,
|
| 303 |
+
"logps/rejected": -73.8904037475586,
|
| 304 |
+
"loss": 0.6582,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.06042450666427612,
|
| 307 |
+
"rewards/margins": 0.10538975894451141,
|
| 308 |
+
"rewards/rejected": -0.16581428050994873,
|
| 309 |
+
"step": 200
|
| 310 |
+
}
|
| 311 |
+
],
|
| 312 |
+
"logging_steps": 10,
|
| 313 |
+
"max_steps": 540,
|
| 314 |
+
"num_input_tokens_seen": 0,
|
| 315 |
+
"num_train_epochs": 20,
|
| 316 |
+
"save_steps": 50,
|
| 317 |
+
"stateful_callbacks": {
|
| 318 |
+
"TrainerControl": {
|
| 319 |
+
"args": {
|
| 320 |
+
"should_epoch_stop": false,
|
| 321 |
+
"should_evaluate": false,
|
| 322 |
+
"should_log": false,
|
| 323 |
+
"should_save": true,
|
| 324 |
+
"should_training_stop": false
|
| 325 |
+
},
|
| 326 |
+
"attributes": {}
|
| 327 |
+
}
|
| 328 |
+
},
|
| 329 |
+
"total_flos": 6.772300330639032e+17,
|
| 330 |
+
"train_batch_size": 1,
|
| 331 |
+
"trial_name": null,
|
| 332 |
+
"trial_params": null
|
| 333 |
+
}
|
Area_Time/checkpoint-250/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_Time/checkpoint-250/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_Time/checkpoint-250/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Area_Time/checkpoint-250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_Time/checkpoint-250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Area_Time/checkpoint-250/trainer_state.json
ADDED
|
@@ -0,0 +1,408 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.00900900900901,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36036036036036034,
|
| 13 |
+
"grad_norm": 0.5300200581550598,
|
| 14 |
+
"learning_rate": 9.259259259259259e-07,
|
| 15 |
+
"logits/chosen": 1.7405741214752197,
|
| 16 |
+
"logits/rejected": 1.663368582725525,
|
| 17 |
+
"logps/chosen": -97.57881164550781,
|
| 18 |
+
"logps/rejected": -70.59793853759766,
|
| 19 |
+
"loss": 0.6938,
|
| 20 |
+
"rewards/accuracies": 0.4375,
|
| 21 |
+
"rewards/chosen": 0.0018835498485714197,
|
| 22 |
+
"rewards/margins": -0.0008800366776995361,
|
| 23 |
+
"rewards/rejected": 0.0027635858859866858,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7207207207207207,
|
| 28 |
+
"grad_norm": 0.4883837401866913,
|
| 29 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 30 |
+
"logits/chosen": 1.8280715942382812,
|
| 31 |
+
"logits/rejected": 1.8215343952178955,
|
| 32 |
+
"logps/chosen": -90.60624694824219,
|
| 33 |
+
"logps/rejected": -79.04981994628906,
|
| 34 |
+
"loss": 0.6945,
|
| 35 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 36 |
+
"rewards/chosen": 0.0014454321935772896,
|
| 37 |
+
"rewards/margins": -0.004174981266260147,
|
| 38 |
+
"rewards/rejected": 0.005620413459837437,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0810810810810811,
|
| 43 |
+
"grad_norm": 0.5554109215736389,
|
| 44 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 45 |
+
"logits/chosen": 1.7980501651763916,
|
| 46 |
+
"logits/rejected": 1.841104507446289,
|
| 47 |
+
"logps/chosen": -80.78228759765625,
|
| 48 |
+
"logps/rejected": -85.08882141113281,
|
| 49 |
+
"loss": 0.693,
|
| 50 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 51 |
+
"rewards/chosen": 0.0042568682692945,
|
| 52 |
+
"rewards/margins": -0.0038191028870642185,
|
| 53 |
+
"rewards/rejected": 0.008075973019003868,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4414414414414414,
|
| 58 |
+
"grad_norm": 0.537497341632843,
|
| 59 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 60 |
+
"logits/chosen": 1.7320470809936523,
|
| 61 |
+
"logits/rejected": 1.7411377429962158,
|
| 62 |
+
"logps/chosen": -82.24813842773438,
|
| 63 |
+
"logps/rejected": -80.90709686279297,
|
| 64 |
+
"loss": 0.6952,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.00350201572291553,
|
| 67 |
+
"rewards/margins": -0.012091752141714096,
|
| 68 |
+
"rewards/rejected": 0.008589735254645348,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.8018018018018018,
|
| 73 |
+
"grad_norm": 0.5023094415664673,
|
| 74 |
+
"learning_rate": 4.62962962962963e-06,
|
| 75 |
+
"logits/chosen": 1.8292573690414429,
|
| 76 |
+
"logits/rejected": 1.8632844686508179,
|
| 77 |
+
"logps/chosen": -85.98481750488281,
|
| 78 |
+
"logps/rejected": -86.14008331298828,
|
| 79 |
+
"loss": 0.6928,
|
| 80 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 81 |
+
"rewards/chosen": 0.00168000184930861,
|
| 82 |
+
"rewards/margins": -0.011136507615447044,
|
| 83 |
+
"rewards/rejected": 0.01281650923192501,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.1621621621621623,
|
| 88 |
+
"grad_norm": 0.4981901943683624,
|
| 89 |
+
"learning_rate": 4.998119881260576e-06,
|
| 90 |
+
"logits/chosen": 1.8536121845245361,
|
| 91 |
+
"logits/rejected": 1.7948782444000244,
|
| 92 |
+
"logps/chosen": -90.0439682006836,
|
| 93 |
+
"logps/rejected": -79.8309555053711,
|
| 94 |
+
"loss": 0.6914,
|
| 95 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 96 |
+
"rewards/chosen": 0.0025153260212391615,
|
| 97 |
+
"rewards/margins": -0.0021209525875747204,
|
| 98 |
+
"rewards/rejected": 0.004636278375983238,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5225225225225225,
|
| 103 |
+
"grad_norm": 0.6208468079566956,
|
| 104 |
+
"learning_rate": 4.9866405060165044e-06,
|
| 105 |
+
"logits/chosen": 1.7845121622085571,
|
| 106 |
+
"logits/rejected": 1.8721017837524414,
|
| 107 |
+
"logps/chosen": -74.6461181640625,
|
| 108 |
+
"logps/rejected": -98.91078186035156,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 111 |
+
"rewards/chosen": 0.00022823773906566203,
|
| 112 |
+
"rewards/margins": 0.0024594543501734734,
|
| 113 |
+
"rewards/rejected": -0.00223121652379632,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.8828828828828827,
|
| 118 |
+
"grad_norm": 0.5074446797370911,
|
| 119 |
+
"learning_rate": 4.964774158361991e-06,
|
| 120 |
+
"logits/chosen": 1.8522154092788696,
|
| 121 |
+
"logits/rejected": 1.8161392211914062,
|
| 122 |
+
"logps/chosen": -89.16864013671875,
|
| 123 |
+
"logps/rejected": -81.97349548339844,
|
| 124 |
+
"loss": 0.6911,
|
| 125 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 126 |
+
"rewards/chosen": 0.006215038243681192,
|
| 127 |
+
"rewards/margins": 0.005521883722394705,
|
| 128 |
+
"rewards/rejected": 0.0006931538810022175,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.2432432432432434,
|
| 133 |
+
"grad_norm": 0.6148263812065125,
|
| 134 |
+
"learning_rate": 4.93261217644956e-06,
|
| 135 |
+
"logits/chosen": 1.7915083169937134,
|
| 136 |
+
"logits/rejected": 1.7579513788223267,
|
| 137 |
+
"logps/chosen": -88.66618347167969,
|
| 138 |
+
"logps/rejected": -80.2238998413086,
|
| 139 |
+
"loss": 0.6918,
|
| 140 |
+
"rewards/accuracies": 0.574999988079071,
|
| 141 |
+
"rewards/chosen": 0.005774274934083223,
|
| 142 |
+
"rewards/margins": 0.016623441129922867,
|
| 143 |
+
"rewards/rejected": -0.010849165730178356,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.6036036036036037,
|
| 148 |
+
"grad_norm": 0.6143240332603455,
|
| 149 |
+
"learning_rate": 4.8902889044347e-06,
|
| 150 |
+
"logits/chosen": 1.6886920928955078,
|
| 151 |
+
"logits/rejected": 1.8121178150177002,
|
| 152 |
+
"logps/chosen": -72.908203125,
|
| 153 |
+
"logps/rejected": -92.44017028808594,
|
| 154 |
+
"loss": 0.6911,
|
| 155 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 156 |
+
"rewards/chosen": -0.0015121791511774063,
|
| 157 |
+
"rewards/margins": 0.0036420777905732393,
|
| 158 |
+
"rewards/rejected": -0.005154256708920002,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.963963963963964,
|
| 163 |
+
"grad_norm": 0.7140340209007263,
|
| 164 |
+
"learning_rate": 4.837981131305475e-06,
|
| 165 |
+
"logits/chosen": 1.7481105327606201,
|
| 166 |
+
"logits/rejected": 1.723141074180603,
|
| 167 |
+
"logps/chosen": -80.63452911376953,
|
| 168 |
+
"logps/rejected": -72.64492797851562,
|
| 169 |
+
"loss": 0.6894,
|
| 170 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 171 |
+
"rewards/chosen": -0.006246576085686684,
|
| 172 |
+
"rewards/margins": -0.0035218377597630024,
|
| 173 |
+
"rewards/rejected": -0.0027247383259236813,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.324324324324325,
|
| 178 |
+
"grad_norm": 1.1645854711532593,
|
| 179 |
+
"learning_rate": 4.775907352415367e-06,
|
| 180 |
+
"logits/chosen": 1.7416290044784546,
|
| 181 |
+
"logits/rejected": 1.8237574100494385,
|
| 182 |
+
"logps/chosen": -89.01248931884766,
|
| 183 |
+
"logps/rejected": -92.31901550292969,
|
| 184 |
+
"loss": 0.6869,
|
| 185 |
+
"rewards/accuracies": 0.612500011920929,
|
| 186 |
+
"rewards/chosen": -0.008855113759636879,
|
| 187 |
+
"rewards/margins": 0.013151508755981922,
|
| 188 |
+
"rewards/rejected": -0.022006623446941376,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.684684684684685,
|
| 193 |
+
"grad_norm": 0.6638664603233337,
|
| 194 |
+
"learning_rate": 4.70432685680402e-06,
|
| 195 |
+
"logits/chosen": 1.7124770879745483,
|
| 196 |
+
"logits/rejected": 1.7777938842773438,
|
| 197 |
+
"logps/chosen": -84.87271881103516,
|
| 198 |
+
"logps/rejected": -92.4839096069336,
|
| 199 |
+
"loss": 0.6855,
|
| 200 |
+
"rewards/accuracies": 0.574999988079071,
|
| 201 |
+
"rewards/chosen": -0.004437069408595562,
|
| 202 |
+
"rewards/margins": 0.019811339676380157,
|
| 203 |
+
"rewards/rejected": -0.024248410016298294,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.045045045045045,
|
| 208 |
+
"grad_norm": 0.785169780254364,
|
| 209 |
+
"learning_rate": 4.623538644118244e-06,
|
| 210 |
+
"logits/chosen": 1.7838690280914307,
|
| 211 |
+
"logits/rejected": 1.8052574396133423,
|
| 212 |
+
"logps/chosen": -94.57842254638672,
|
| 213 |
+
"logps/rejected": -80.6390609741211,
|
| 214 |
+
"loss": 0.6836,
|
| 215 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 216 |
+
"rewards/chosen": -0.026147600263357162,
|
| 217 |
+
"rewards/margins": 0.010936126112937927,
|
| 218 |
+
"rewards/rejected": -0.03708372637629509,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.405405405405405,
|
| 223 |
+
"grad_norm": 0.745952844619751,
|
| 224 |
+
"learning_rate": 4.533880175657419e-06,
|
| 225 |
+
"logits/chosen": 1.7925735712051392,
|
| 226 |
+
"logits/rejected": 1.7987396717071533,
|
| 227 |
+
"logps/chosen": -82.4854507446289,
|
| 228 |
+
"logps/rejected": -77.50787353515625,
|
| 229 |
+
"loss": 0.6767,
|
| 230 |
+
"rewards/accuracies": 0.625,
|
| 231 |
+
"rewards/chosen": -0.013469865545630455,
|
| 232 |
+
"rewards/margins": 0.04023212194442749,
|
| 233 |
+
"rewards/rejected": -0.053701985627412796,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.7657657657657655,
|
| 238 |
+
"grad_norm": 0.7885063290596008,
|
| 239 |
+
"learning_rate": 4.435725964760331e-06,
|
| 240 |
+
"logits/chosen": 1.7725191116333008,
|
| 241 |
+
"logits/rejected": 1.8345234394073486,
|
| 242 |
+
"logps/chosen": -78.7154541015625,
|
| 243 |
+
"logps/rejected": -80.75708770751953,
|
| 244 |
+
"loss": 0.6721,
|
| 245 |
+
"rewards/accuracies": 0.675000011920929,
|
| 246 |
+
"rewards/chosen": -0.018351273611187935,
|
| 247 |
+
"rewards/margins": 0.05368901416659355,
|
| 248 |
+
"rewards/rejected": -0.07204028964042664,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.126126126126126,
|
| 253 |
+
"grad_norm": 0.7734187245368958,
|
| 254 |
+
"learning_rate": 4.329486012421531e-06,
|
| 255 |
+
"logits/chosen": 1.827528715133667,
|
| 256 |
+
"logits/rejected": 1.7939176559448242,
|
| 257 |
+
"logps/chosen": -75.33561706542969,
|
| 258 |
+
"logps/rejected": -71.34326934814453,
|
| 259 |
+
"loss": 0.6775,
|
| 260 |
+
"rewards/accuracies": 0.612500011920929,
|
| 261 |
+
"rewards/chosen": -0.038218818604946136,
|
| 262 |
+
"rewards/margins": 0.06159939616918564,
|
| 263 |
+
"rewards/rejected": -0.09981821477413177,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.486486486486487,
|
| 268 |
+
"grad_norm": 0.7796682715415955,
|
| 269 |
+
"learning_rate": 4.215604094671835e-06,
|
| 270 |
+
"logits/chosen": 1.729288101196289,
|
| 271 |
+
"logits/rejected": 1.7497504949569702,
|
| 272 |
+
"logps/chosen": -83.02750396728516,
|
| 273 |
+
"logps/rejected": -78.53959655761719,
|
| 274 |
+
"loss": 0.6632,
|
| 275 |
+
"rewards/accuracies": 0.699999988079071,
|
| 276 |
+
"rewards/chosen": -0.03207743167877197,
|
| 277 |
+
"rewards/margins": 0.06858544796705246,
|
| 278 |
+
"rewards/rejected": -0.10066288709640503,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.846846846846847,
|
| 283 |
+
"grad_norm": 0.8168752193450928,
|
| 284 |
+
"learning_rate": 4.094555908876765e-06,
|
| 285 |
+
"logits/chosen": 1.747865080833435,
|
| 286 |
+
"logits/rejected": 1.7993282079696655,
|
| 287 |
+
"logps/chosen": -78.75782775878906,
|
| 288 |
+
"logps/rejected": -85.8946304321289,
|
| 289 |
+
"loss": 0.668,
|
| 290 |
+
"rewards/accuracies": 0.612500011920929,
|
| 291 |
+
"rewards/chosen": -0.0766468197107315,
|
| 292 |
+
"rewards/margins": 0.045263100415468216,
|
| 293 |
+
"rewards/rejected": -0.12190990149974823,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 7.207207207207207,
|
| 298 |
+
"grad_norm": 0.9816763997077942,
|
| 299 |
+
"learning_rate": 3.966847086696045e-06,
|
| 300 |
+
"logits/chosen": 1.792106032371521,
|
| 301 |
+
"logits/rejected": 1.7798125743865967,
|
| 302 |
+
"logps/chosen": -93.53439331054688,
|
| 303 |
+
"logps/rejected": -73.8904037475586,
|
| 304 |
+
"loss": 0.6582,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.06042450666427612,
|
| 307 |
+
"rewards/margins": 0.10538975894451141,
|
| 308 |
+
"rewards/rejected": -0.16581428050994873,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.5675675675675675,
|
| 313 |
+
"grad_norm": 0.9053374528884888,
|
| 314 |
+
"learning_rate": 3.833011082004229e-06,
|
| 315 |
+
"logits/chosen": 1.7648969888687134,
|
| 316 |
+
"logits/rejected": 1.7725557088851929,
|
| 317 |
+
"logps/chosen": -79.61383056640625,
|
| 318 |
+
"logps/rejected": -71.8048095703125,
|
| 319 |
+
"loss": 0.6551,
|
| 320 |
+
"rewards/accuracies": 0.6875,
|
| 321 |
+
"rewards/chosen": -0.040038011968135834,
|
| 322 |
+
"rewards/margins": 0.11104954779148102,
|
| 323 |
+
"rewards/rejected": -0.15108755230903625,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.927927927927928,
|
| 328 |
+
"grad_norm": 1.1332669258117676,
|
| 329 |
+
"learning_rate": 3.693606942594873e-06,
|
| 330 |
+
"logits/chosen": 1.8605678081512451,
|
| 331 |
+
"logits/rejected": 1.91280996799469,
|
| 332 |
+
"logps/chosen": -74.39783477783203,
|
| 333 |
+
"logps/rejected": -90.66893005371094,
|
| 334 |
+
"loss": 0.6565,
|
| 335 |
+
"rewards/accuracies": 0.637499988079071,
|
| 336 |
+
"rewards/chosen": -0.08056517690420151,
|
| 337 |
+
"rewards/margins": 0.0968993678689003,
|
| 338 |
+
"rewards/rejected": -0.1774645447731018,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.288288288288289,
|
| 343 |
+
"grad_norm": 1.0496221780776978,
|
| 344 |
+
"learning_rate": 3.549216974976073e-06,
|
| 345 |
+
"logits/chosen": 1.8636070489883423,
|
| 346 |
+
"logits/rejected": 1.7996151447296143,
|
| 347 |
+
"logps/chosen": -89.9018783569336,
|
| 348 |
+
"logps/rejected": -74.14125061035156,
|
| 349 |
+
"loss": 0.6423,
|
| 350 |
+
"rewards/accuracies": 0.6875,
|
| 351 |
+
"rewards/chosen": -0.05598217993974686,
|
| 352 |
+
"rewards/margins": 0.14807265996932983,
|
| 353 |
+
"rewards/rejected": -0.2040548026561737,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.64864864864865,
|
| 358 |
+
"grad_norm": 0.8506491780281067,
|
| 359 |
+
"learning_rate": 3.400444312011776e-06,
|
| 360 |
+
"logits/chosen": 1.7753232717514038,
|
| 361 |
+
"logits/rejected": 1.7647806406021118,
|
| 362 |
+
"logps/chosen": -88.50201416015625,
|
| 363 |
+
"logps/rejected": -81.80894470214844,
|
| 364 |
+
"loss": 0.6358,
|
| 365 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 366 |
+
"rewards/chosen": -0.09656485170125961,
|
| 367 |
+
"rewards/margins": 0.11554913222789764,
|
| 368 |
+
"rewards/rejected": -0.21211397647857666,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.00900900900901,
|
| 373 |
+
"grad_norm": 0.9554071426391602,
|
| 374 |
+
"learning_rate": 3.2479103935691047e-06,
|
| 375 |
+
"logits/chosen": 1.7528200149536133,
|
| 376 |
+
"logits/rejected": 1.7827808856964111,
|
| 377 |
+
"logps/chosen": -90.01268005371094,
|
| 378 |
+
"logps/rejected": -89.0714340209961,
|
| 379 |
+
"loss": 0.6374,
|
| 380 |
+
"rewards/accuracies": 0.675000011920929,
|
| 381 |
+
"rewards/chosen": -0.07412372529506683,
|
| 382 |
+
"rewards/margins": 0.1321595013141632,
|
| 383 |
+
"rewards/rejected": -0.20628324151039124,
|
| 384 |
+
"step": 250
|
| 385 |
+
}
|
| 386 |
+
],
|
| 387 |
+
"logging_steps": 10,
|
| 388 |
+
"max_steps": 540,
|
| 389 |
+
"num_input_tokens_seen": 0,
|
| 390 |
+
"num_train_epochs": 20,
|
| 391 |
+
"save_steps": 50,
|
| 392 |
+
"stateful_callbacks": {
|
| 393 |
+
"TrainerControl": {
|
| 394 |
+
"args": {
|
| 395 |
+
"should_epoch_stop": false,
|
| 396 |
+
"should_evaluate": false,
|
| 397 |
+
"should_log": false,
|
| 398 |
+
"should_save": true,
|
| 399 |
+
"should_training_stop": false
|
| 400 |
+
},
|
| 401 |
+
"attributes": {}
|
| 402 |
+
}
|
| 403 |
+
},
|
| 404 |
+
"total_flos": 8.467418008476713e+17,
|
| 405 |
+
"train_batch_size": 1,
|
| 406 |
+
"trial_name": null,
|
| 407 |
+
"trial_params": null
|
| 408 |
+
}
|
Area_Time/checkpoint-300/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_Time/checkpoint-300/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_Time/checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Area_Time/checkpoint-300/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_Time/checkpoint-300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Area_Time/checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.81081081081081,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36036036036036034,
|
| 13 |
+
"grad_norm": 0.5300200581550598,
|
| 14 |
+
"learning_rate": 9.259259259259259e-07,
|
| 15 |
+
"logits/chosen": 1.7405741214752197,
|
| 16 |
+
"logits/rejected": 1.663368582725525,
|
| 17 |
+
"logps/chosen": -97.57881164550781,
|
| 18 |
+
"logps/rejected": -70.59793853759766,
|
| 19 |
+
"loss": 0.6938,
|
| 20 |
+
"rewards/accuracies": 0.4375,
|
| 21 |
+
"rewards/chosen": 0.0018835498485714197,
|
| 22 |
+
"rewards/margins": -0.0008800366776995361,
|
| 23 |
+
"rewards/rejected": 0.0027635858859866858,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7207207207207207,
|
| 28 |
+
"grad_norm": 0.4883837401866913,
|
| 29 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 30 |
+
"logits/chosen": 1.8280715942382812,
|
| 31 |
+
"logits/rejected": 1.8215343952178955,
|
| 32 |
+
"logps/chosen": -90.60624694824219,
|
| 33 |
+
"logps/rejected": -79.04981994628906,
|
| 34 |
+
"loss": 0.6945,
|
| 35 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 36 |
+
"rewards/chosen": 0.0014454321935772896,
|
| 37 |
+
"rewards/margins": -0.004174981266260147,
|
| 38 |
+
"rewards/rejected": 0.005620413459837437,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0810810810810811,
|
| 43 |
+
"grad_norm": 0.5554109215736389,
|
| 44 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 45 |
+
"logits/chosen": 1.7980501651763916,
|
| 46 |
+
"logits/rejected": 1.841104507446289,
|
| 47 |
+
"logps/chosen": -80.78228759765625,
|
| 48 |
+
"logps/rejected": -85.08882141113281,
|
| 49 |
+
"loss": 0.693,
|
| 50 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 51 |
+
"rewards/chosen": 0.0042568682692945,
|
| 52 |
+
"rewards/margins": -0.0038191028870642185,
|
| 53 |
+
"rewards/rejected": 0.008075973019003868,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4414414414414414,
|
| 58 |
+
"grad_norm": 0.537497341632843,
|
| 59 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 60 |
+
"logits/chosen": 1.7320470809936523,
|
| 61 |
+
"logits/rejected": 1.7411377429962158,
|
| 62 |
+
"logps/chosen": -82.24813842773438,
|
| 63 |
+
"logps/rejected": -80.90709686279297,
|
| 64 |
+
"loss": 0.6952,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.00350201572291553,
|
| 67 |
+
"rewards/margins": -0.012091752141714096,
|
| 68 |
+
"rewards/rejected": 0.008589735254645348,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.8018018018018018,
|
| 73 |
+
"grad_norm": 0.5023094415664673,
|
| 74 |
+
"learning_rate": 4.62962962962963e-06,
|
| 75 |
+
"logits/chosen": 1.8292573690414429,
|
| 76 |
+
"logits/rejected": 1.8632844686508179,
|
| 77 |
+
"logps/chosen": -85.98481750488281,
|
| 78 |
+
"logps/rejected": -86.14008331298828,
|
| 79 |
+
"loss": 0.6928,
|
| 80 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 81 |
+
"rewards/chosen": 0.00168000184930861,
|
| 82 |
+
"rewards/margins": -0.011136507615447044,
|
| 83 |
+
"rewards/rejected": 0.01281650923192501,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.1621621621621623,
|
| 88 |
+
"grad_norm": 0.4981901943683624,
|
| 89 |
+
"learning_rate": 4.998119881260576e-06,
|
| 90 |
+
"logits/chosen": 1.8536121845245361,
|
| 91 |
+
"logits/rejected": 1.7948782444000244,
|
| 92 |
+
"logps/chosen": -90.0439682006836,
|
| 93 |
+
"logps/rejected": -79.8309555053711,
|
| 94 |
+
"loss": 0.6914,
|
| 95 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 96 |
+
"rewards/chosen": 0.0025153260212391615,
|
| 97 |
+
"rewards/margins": -0.0021209525875747204,
|
| 98 |
+
"rewards/rejected": 0.004636278375983238,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5225225225225225,
|
| 103 |
+
"grad_norm": 0.6208468079566956,
|
| 104 |
+
"learning_rate": 4.9866405060165044e-06,
|
| 105 |
+
"logits/chosen": 1.7845121622085571,
|
| 106 |
+
"logits/rejected": 1.8721017837524414,
|
| 107 |
+
"logps/chosen": -74.6461181640625,
|
| 108 |
+
"logps/rejected": -98.91078186035156,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 111 |
+
"rewards/chosen": 0.00022823773906566203,
|
| 112 |
+
"rewards/margins": 0.0024594543501734734,
|
| 113 |
+
"rewards/rejected": -0.00223121652379632,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.8828828828828827,
|
| 118 |
+
"grad_norm": 0.5074446797370911,
|
| 119 |
+
"learning_rate": 4.964774158361991e-06,
|
| 120 |
+
"logits/chosen": 1.8522154092788696,
|
| 121 |
+
"logits/rejected": 1.8161392211914062,
|
| 122 |
+
"logps/chosen": -89.16864013671875,
|
| 123 |
+
"logps/rejected": -81.97349548339844,
|
| 124 |
+
"loss": 0.6911,
|
| 125 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 126 |
+
"rewards/chosen": 0.006215038243681192,
|
| 127 |
+
"rewards/margins": 0.005521883722394705,
|
| 128 |
+
"rewards/rejected": 0.0006931538810022175,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.2432432432432434,
|
| 133 |
+
"grad_norm": 0.6148263812065125,
|
| 134 |
+
"learning_rate": 4.93261217644956e-06,
|
| 135 |
+
"logits/chosen": 1.7915083169937134,
|
| 136 |
+
"logits/rejected": 1.7579513788223267,
|
| 137 |
+
"logps/chosen": -88.66618347167969,
|
| 138 |
+
"logps/rejected": -80.2238998413086,
|
| 139 |
+
"loss": 0.6918,
|
| 140 |
+
"rewards/accuracies": 0.574999988079071,
|
| 141 |
+
"rewards/chosen": 0.005774274934083223,
|
| 142 |
+
"rewards/margins": 0.016623441129922867,
|
| 143 |
+
"rewards/rejected": -0.010849165730178356,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.6036036036036037,
|
| 148 |
+
"grad_norm": 0.6143240332603455,
|
| 149 |
+
"learning_rate": 4.8902889044347e-06,
|
| 150 |
+
"logits/chosen": 1.6886920928955078,
|
| 151 |
+
"logits/rejected": 1.8121178150177002,
|
| 152 |
+
"logps/chosen": -72.908203125,
|
| 153 |
+
"logps/rejected": -92.44017028808594,
|
| 154 |
+
"loss": 0.6911,
|
| 155 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 156 |
+
"rewards/chosen": -0.0015121791511774063,
|
| 157 |
+
"rewards/margins": 0.0036420777905732393,
|
| 158 |
+
"rewards/rejected": -0.005154256708920002,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.963963963963964,
|
| 163 |
+
"grad_norm": 0.7140340209007263,
|
| 164 |
+
"learning_rate": 4.837981131305475e-06,
|
| 165 |
+
"logits/chosen": 1.7481105327606201,
|
| 166 |
+
"logits/rejected": 1.723141074180603,
|
| 167 |
+
"logps/chosen": -80.63452911376953,
|
| 168 |
+
"logps/rejected": -72.64492797851562,
|
| 169 |
+
"loss": 0.6894,
|
| 170 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 171 |
+
"rewards/chosen": -0.006246576085686684,
|
| 172 |
+
"rewards/margins": -0.0035218377597630024,
|
| 173 |
+
"rewards/rejected": -0.0027247383259236813,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.324324324324325,
|
| 178 |
+
"grad_norm": 1.1645854711532593,
|
| 179 |
+
"learning_rate": 4.775907352415367e-06,
|
| 180 |
+
"logits/chosen": 1.7416290044784546,
|
| 181 |
+
"logits/rejected": 1.8237574100494385,
|
| 182 |
+
"logps/chosen": -89.01248931884766,
|
| 183 |
+
"logps/rejected": -92.31901550292969,
|
| 184 |
+
"loss": 0.6869,
|
| 185 |
+
"rewards/accuracies": 0.612500011920929,
|
| 186 |
+
"rewards/chosen": -0.008855113759636879,
|
| 187 |
+
"rewards/margins": 0.013151508755981922,
|
| 188 |
+
"rewards/rejected": -0.022006623446941376,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.684684684684685,
|
| 193 |
+
"grad_norm": 0.6638664603233337,
|
| 194 |
+
"learning_rate": 4.70432685680402e-06,
|
| 195 |
+
"logits/chosen": 1.7124770879745483,
|
| 196 |
+
"logits/rejected": 1.7777938842773438,
|
| 197 |
+
"logps/chosen": -84.87271881103516,
|
| 198 |
+
"logps/rejected": -92.4839096069336,
|
| 199 |
+
"loss": 0.6855,
|
| 200 |
+
"rewards/accuracies": 0.574999988079071,
|
| 201 |
+
"rewards/chosen": -0.004437069408595562,
|
| 202 |
+
"rewards/margins": 0.019811339676380157,
|
| 203 |
+
"rewards/rejected": -0.024248410016298294,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.045045045045045,
|
| 208 |
+
"grad_norm": 0.785169780254364,
|
| 209 |
+
"learning_rate": 4.623538644118244e-06,
|
| 210 |
+
"logits/chosen": 1.7838690280914307,
|
| 211 |
+
"logits/rejected": 1.8052574396133423,
|
| 212 |
+
"logps/chosen": -94.57842254638672,
|
| 213 |
+
"logps/rejected": -80.6390609741211,
|
| 214 |
+
"loss": 0.6836,
|
| 215 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 216 |
+
"rewards/chosen": -0.026147600263357162,
|
| 217 |
+
"rewards/margins": 0.010936126112937927,
|
| 218 |
+
"rewards/rejected": -0.03708372637629509,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.405405405405405,
|
| 223 |
+
"grad_norm": 0.745952844619751,
|
| 224 |
+
"learning_rate": 4.533880175657419e-06,
|
| 225 |
+
"logits/chosen": 1.7925735712051392,
|
| 226 |
+
"logits/rejected": 1.7987396717071533,
|
| 227 |
+
"logps/chosen": -82.4854507446289,
|
| 228 |
+
"logps/rejected": -77.50787353515625,
|
| 229 |
+
"loss": 0.6767,
|
| 230 |
+
"rewards/accuracies": 0.625,
|
| 231 |
+
"rewards/chosen": -0.013469865545630455,
|
| 232 |
+
"rewards/margins": 0.04023212194442749,
|
| 233 |
+
"rewards/rejected": -0.053701985627412796,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.7657657657657655,
|
| 238 |
+
"grad_norm": 0.7885063290596008,
|
| 239 |
+
"learning_rate": 4.435725964760331e-06,
|
| 240 |
+
"logits/chosen": 1.7725191116333008,
|
| 241 |
+
"logits/rejected": 1.8345234394073486,
|
| 242 |
+
"logps/chosen": -78.7154541015625,
|
| 243 |
+
"logps/rejected": -80.75708770751953,
|
| 244 |
+
"loss": 0.6721,
|
| 245 |
+
"rewards/accuracies": 0.675000011920929,
|
| 246 |
+
"rewards/chosen": -0.018351273611187935,
|
| 247 |
+
"rewards/margins": 0.05368901416659355,
|
| 248 |
+
"rewards/rejected": -0.07204028964042664,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.126126126126126,
|
| 253 |
+
"grad_norm": 0.7734187245368958,
|
| 254 |
+
"learning_rate": 4.329486012421531e-06,
|
| 255 |
+
"logits/chosen": 1.827528715133667,
|
| 256 |
+
"logits/rejected": 1.7939176559448242,
|
| 257 |
+
"logps/chosen": -75.33561706542969,
|
| 258 |
+
"logps/rejected": -71.34326934814453,
|
| 259 |
+
"loss": 0.6775,
|
| 260 |
+
"rewards/accuracies": 0.612500011920929,
|
| 261 |
+
"rewards/chosen": -0.038218818604946136,
|
| 262 |
+
"rewards/margins": 0.06159939616918564,
|
| 263 |
+
"rewards/rejected": -0.09981821477413177,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.486486486486487,
|
| 268 |
+
"grad_norm": 0.7796682715415955,
|
| 269 |
+
"learning_rate": 4.215604094671835e-06,
|
| 270 |
+
"logits/chosen": 1.729288101196289,
|
| 271 |
+
"logits/rejected": 1.7497504949569702,
|
| 272 |
+
"logps/chosen": -83.02750396728516,
|
| 273 |
+
"logps/rejected": -78.53959655761719,
|
| 274 |
+
"loss": 0.6632,
|
| 275 |
+
"rewards/accuracies": 0.699999988079071,
|
| 276 |
+
"rewards/chosen": -0.03207743167877197,
|
| 277 |
+
"rewards/margins": 0.06858544796705246,
|
| 278 |
+
"rewards/rejected": -0.10066288709640503,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.846846846846847,
|
| 283 |
+
"grad_norm": 0.8168752193450928,
|
| 284 |
+
"learning_rate": 4.094555908876765e-06,
|
| 285 |
+
"logits/chosen": 1.747865080833435,
|
| 286 |
+
"logits/rejected": 1.7993282079696655,
|
| 287 |
+
"logps/chosen": -78.75782775878906,
|
| 288 |
+
"logps/rejected": -85.8946304321289,
|
| 289 |
+
"loss": 0.668,
|
| 290 |
+
"rewards/accuracies": 0.612500011920929,
|
| 291 |
+
"rewards/chosen": -0.0766468197107315,
|
| 292 |
+
"rewards/margins": 0.045263100415468216,
|
| 293 |
+
"rewards/rejected": -0.12190990149974823,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 7.207207207207207,
|
| 298 |
+
"grad_norm": 0.9816763997077942,
|
| 299 |
+
"learning_rate": 3.966847086696045e-06,
|
| 300 |
+
"logits/chosen": 1.792106032371521,
|
| 301 |
+
"logits/rejected": 1.7798125743865967,
|
| 302 |
+
"logps/chosen": -93.53439331054688,
|
| 303 |
+
"logps/rejected": -73.8904037475586,
|
| 304 |
+
"loss": 0.6582,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.06042450666427612,
|
| 307 |
+
"rewards/margins": 0.10538975894451141,
|
| 308 |
+
"rewards/rejected": -0.16581428050994873,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.5675675675675675,
|
| 313 |
+
"grad_norm": 0.9053374528884888,
|
| 314 |
+
"learning_rate": 3.833011082004229e-06,
|
| 315 |
+
"logits/chosen": 1.7648969888687134,
|
| 316 |
+
"logits/rejected": 1.7725557088851929,
|
| 317 |
+
"logps/chosen": -79.61383056640625,
|
| 318 |
+
"logps/rejected": -71.8048095703125,
|
| 319 |
+
"loss": 0.6551,
|
| 320 |
+
"rewards/accuracies": 0.6875,
|
| 321 |
+
"rewards/chosen": -0.040038011968135834,
|
| 322 |
+
"rewards/margins": 0.11104954779148102,
|
| 323 |
+
"rewards/rejected": -0.15108755230903625,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.927927927927928,
|
| 328 |
+
"grad_norm": 1.1332669258117676,
|
| 329 |
+
"learning_rate": 3.693606942594873e-06,
|
| 330 |
+
"logits/chosen": 1.8605678081512451,
|
| 331 |
+
"logits/rejected": 1.91280996799469,
|
| 332 |
+
"logps/chosen": -74.39783477783203,
|
| 333 |
+
"logps/rejected": -90.66893005371094,
|
| 334 |
+
"loss": 0.6565,
|
| 335 |
+
"rewards/accuracies": 0.637499988079071,
|
| 336 |
+
"rewards/chosen": -0.08056517690420151,
|
| 337 |
+
"rewards/margins": 0.0968993678689003,
|
| 338 |
+
"rewards/rejected": -0.1774645447731018,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.288288288288289,
|
| 343 |
+
"grad_norm": 1.0496221780776978,
|
| 344 |
+
"learning_rate": 3.549216974976073e-06,
|
| 345 |
+
"logits/chosen": 1.8636070489883423,
|
| 346 |
+
"logits/rejected": 1.7996151447296143,
|
| 347 |
+
"logps/chosen": -89.9018783569336,
|
| 348 |
+
"logps/rejected": -74.14125061035156,
|
| 349 |
+
"loss": 0.6423,
|
| 350 |
+
"rewards/accuracies": 0.6875,
|
| 351 |
+
"rewards/chosen": -0.05598217993974686,
|
| 352 |
+
"rewards/margins": 0.14807265996932983,
|
| 353 |
+
"rewards/rejected": -0.2040548026561737,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.64864864864865,
|
| 358 |
+
"grad_norm": 0.8506491780281067,
|
| 359 |
+
"learning_rate": 3.400444312011776e-06,
|
| 360 |
+
"logits/chosen": 1.7753232717514038,
|
| 361 |
+
"logits/rejected": 1.7647806406021118,
|
| 362 |
+
"logps/chosen": -88.50201416015625,
|
| 363 |
+
"logps/rejected": -81.80894470214844,
|
| 364 |
+
"loss": 0.6358,
|
| 365 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 366 |
+
"rewards/chosen": -0.09656485170125961,
|
| 367 |
+
"rewards/margins": 0.11554913222789764,
|
| 368 |
+
"rewards/rejected": -0.21211397647857666,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.00900900900901,
|
| 373 |
+
"grad_norm": 0.9554071426391602,
|
| 374 |
+
"learning_rate": 3.2479103935691047e-06,
|
| 375 |
+
"logits/chosen": 1.7528200149536133,
|
| 376 |
+
"logits/rejected": 1.7827808856964111,
|
| 377 |
+
"logps/chosen": -90.01268005371094,
|
| 378 |
+
"logps/rejected": -89.0714340209961,
|
| 379 |
+
"loss": 0.6374,
|
| 380 |
+
"rewards/accuracies": 0.675000011920929,
|
| 381 |
+
"rewards/chosen": -0.07412372529506683,
|
| 382 |
+
"rewards/margins": 0.1321595013141632,
|
| 383 |
+
"rewards/rejected": -0.20628324151039124,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.36936936936937,
|
| 388 |
+
"grad_norm": 0.9363342523574829,
|
| 389 |
+
"learning_rate": 3.092252370695298e-06,
|
| 390 |
+
"logits/chosen": 1.6990101337432861,
|
| 391 |
+
"logits/rejected": 1.8281656503677368,
|
| 392 |
+
"logps/chosen": -71.15428161621094,
|
| 393 |
+
"logps/rejected": -79.72063446044922,
|
| 394 |
+
"loss": 0.6303,
|
| 395 |
+
"rewards/accuracies": 0.762499988079071,
|
| 396 |
+
"rewards/chosen": -0.08240491151809692,
|
| 397 |
+
"rewards/margins": 0.16954098641872406,
|
| 398 |
+
"rewards/rejected": -0.2519459128379822,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.72972972972973,
|
| 403 |
+
"grad_norm": 1.023535966873169,
|
| 404 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 405 |
+
"logits/chosen": 1.7418006658554077,
|
| 406 |
+
"logits/rejected": 1.7500028610229492,
|
| 407 |
+
"logps/chosen": -82.24595642089844,
|
| 408 |
+
"logps/rejected": -91.16307067871094,
|
| 409 |
+
"loss": 0.6321,
|
| 410 |
+
"rewards/accuracies": 0.6875,
|
| 411 |
+
"rewards/chosen": -0.13560767471790314,
|
| 412 |
+
"rewards/margins": 0.1204828992486,
|
| 413 |
+
"rewards/rejected": -0.25609058141708374,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 10.09009009009009,
|
| 418 |
+
"grad_norm": 1.0393471717834473,
|
| 419 |
+
"learning_rate": 2.7741751485313295e-06,
|
| 420 |
+
"logits/chosen": 1.8437154293060303,
|
| 421 |
+
"logits/rejected": 1.8877627849578857,
|
| 422 |
+
"logps/chosen": -68.61182403564453,
|
| 423 |
+
"logps/rejected": -77.12557220458984,
|
| 424 |
+
"loss": 0.6109,
|
| 425 |
+
"rewards/accuracies": 0.737500011920929,
|
| 426 |
+
"rewards/chosen": -0.11025551706552505,
|
| 427 |
+
"rewards/margins": 0.14969798922538757,
|
| 428 |
+
"rewards/rejected": -0.25995349884033203,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 10.45045045045045,
|
| 433 |
+
"grad_norm": 0.9554691910743713,
|
| 434 |
+
"learning_rate": 2.6130845929767662e-06,
|
| 435 |
+
"logits/chosen": 1.7998764514923096,
|
| 436 |
+
"logits/rejected": 1.796451210975647,
|
| 437 |
+
"logps/chosen": -72.6626205444336,
|
| 438 |
+
"logps/rejected": -74.15937042236328,
|
| 439 |
+
"loss": 0.6123,
|
| 440 |
+
"rewards/accuracies": 0.737500011920929,
|
| 441 |
+
"rewards/chosen": -0.13948099315166473,
|
| 442 |
+
"rewards/margins": 0.18039894104003906,
|
| 443 |
+
"rewards/rejected": -0.319879949092865,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.81081081081081,
|
| 448 |
+
"grad_norm": 1.1667226552963257,
|
| 449 |
+
"learning_rate": 2.4515216705704396e-06,
|
| 450 |
+
"logits/chosen": 1.8437564373016357,
|
| 451 |
+
"logits/rejected": 1.9043811559677124,
|
| 452 |
+
"logps/chosen": -78.18916320800781,
|
| 453 |
+
"logps/rejected": -90.88524627685547,
|
| 454 |
+
"loss": 0.6218,
|
| 455 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 456 |
+
"rewards/chosen": -0.12091793864965439,
|
| 457 |
+
"rewards/margins": 0.20490169525146484,
|
| 458 |
+
"rewards/rejected": -0.32581964135169983,
|
| 459 |
+
"step": 300
|
| 460 |
+
}
|
| 461 |
+
],
|
| 462 |
+
"logging_steps": 10,
|
| 463 |
+
"max_steps": 540,
|
| 464 |
+
"num_input_tokens_seen": 0,
|
| 465 |
+
"num_train_epochs": 20,
|
| 466 |
+
"save_steps": 50,
|
| 467 |
+
"stateful_callbacks": {
|
| 468 |
+
"TrainerControl": {
|
| 469 |
+
"args": {
|
| 470 |
+
"should_epoch_stop": false,
|
| 471 |
+
"should_evaluate": false,
|
| 472 |
+
"should_log": false,
|
| 473 |
+
"should_save": true,
|
| 474 |
+
"should_training_stop": false
|
| 475 |
+
},
|
| 476 |
+
"attributes": {}
|
| 477 |
+
}
|
| 478 |
+
},
|
| 479 |
+
"total_flos": 1.0165901866932634e+18,
|
| 480 |
+
"train_batch_size": 1,
|
| 481 |
+
"trial_name": null,
|
| 482 |
+
"trial_params": null
|
| 483 |
+
}
|
Area_Time/checkpoint-350/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_Time/checkpoint-350/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_Time/checkpoint-350/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Area_Time/checkpoint-350/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_Time/checkpoint-350/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Area_Time/checkpoint-350/trainer_state.json
ADDED
|
@@ -0,0 +1,558 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 12.612612612612612,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 350,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36036036036036034,
|
| 13 |
+
"grad_norm": 0.5300200581550598,
|
| 14 |
+
"learning_rate": 9.259259259259259e-07,
|
| 15 |
+
"logits/chosen": 1.7405741214752197,
|
| 16 |
+
"logits/rejected": 1.663368582725525,
|
| 17 |
+
"logps/chosen": -97.57881164550781,
|
| 18 |
+
"logps/rejected": -70.59793853759766,
|
| 19 |
+
"loss": 0.6938,
|
| 20 |
+
"rewards/accuracies": 0.4375,
|
| 21 |
+
"rewards/chosen": 0.0018835498485714197,
|
| 22 |
+
"rewards/margins": -0.0008800366776995361,
|
| 23 |
+
"rewards/rejected": 0.0027635858859866858,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7207207207207207,
|
| 28 |
+
"grad_norm": 0.4883837401866913,
|
| 29 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 30 |
+
"logits/chosen": 1.8280715942382812,
|
| 31 |
+
"logits/rejected": 1.8215343952178955,
|
| 32 |
+
"logps/chosen": -90.60624694824219,
|
| 33 |
+
"logps/rejected": -79.04981994628906,
|
| 34 |
+
"loss": 0.6945,
|
| 35 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 36 |
+
"rewards/chosen": 0.0014454321935772896,
|
| 37 |
+
"rewards/margins": -0.004174981266260147,
|
| 38 |
+
"rewards/rejected": 0.005620413459837437,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0810810810810811,
|
| 43 |
+
"grad_norm": 0.5554109215736389,
|
| 44 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 45 |
+
"logits/chosen": 1.7980501651763916,
|
| 46 |
+
"logits/rejected": 1.841104507446289,
|
| 47 |
+
"logps/chosen": -80.78228759765625,
|
| 48 |
+
"logps/rejected": -85.08882141113281,
|
| 49 |
+
"loss": 0.693,
|
| 50 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 51 |
+
"rewards/chosen": 0.0042568682692945,
|
| 52 |
+
"rewards/margins": -0.0038191028870642185,
|
| 53 |
+
"rewards/rejected": 0.008075973019003868,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4414414414414414,
|
| 58 |
+
"grad_norm": 0.537497341632843,
|
| 59 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 60 |
+
"logits/chosen": 1.7320470809936523,
|
| 61 |
+
"logits/rejected": 1.7411377429962158,
|
| 62 |
+
"logps/chosen": -82.24813842773438,
|
| 63 |
+
"logps/rejected": -80.90709686279297,
|
| 64 |
+
"loss": 0.6952,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.00350201572291553,
|
| 67 |
+
"rewards/margins": -0.012091752141714096,
|
| 68 |
+
"rewards/rejected": 0.008589735254645348,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.8018018018018018,
|
| 73 |
+
"grad_norm": 0.5023094415664673,
|
| 74 |
+
"learning_rate": 4.62962962962963e-06,
|
| 75 |
+
"logits/chosen": 1.8292573690414429,
|
| 76 |
+
"logits/rejected": 1.8632844686508179,
|
| 77 |
+
"logps/chosen": -85.98481750488281,
|
| 78 |
+
"logps/rejected": -86.14008331298828,
|
| 79 |
+
"loss": 0.6928,
|
| 80 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 81 |
+
"rewards/chosen": 0.00168000184930861,
|
| 82 |
+
"rewards/margins": -0.011136507615447044,
|
| 83 |
+
"rewards/rejected": 0.01281650923192501,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.1621621621621623,
|
| 88 |
+
"grad_norm": 0.4981901943683624,
|
| 89 |
+
"learning_rate": 4.998119881260576e-06,
|
| 90 |
+
"logits/chosen": 1.8536121845245361,
|
| 91 |
+
"logits/rejected": 1.7948782444000244,
|
| 92 |
+
"logps/chosen": -90.0439682006836,
|
| 93 |
+
"logps/rejected": -79.8309555053711,
|
| 94 |
+
"loss": 0.6914,
|
| 95 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 96 |
+
"rewards/chosen": 0.0025153260212391615,
|
| 97 |
+
"rewards/margins": -0.0021209525875747204,
|
| 98 |
+
"rewards/rejected": 0.004636278375983238,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5225225225225225,
|
| 103 |
+
"grad_norm": 0.6208468079566956,
|
| 104 |
+
"learning_rate": 4.9866405060165044e-06,
|
| 105 |
+
"logits/chosen": 1.7845121622085571,
|
| 106 |
+
"logits/rejected": 1.8721017837524414,
|
| 107 |
+
"logps/chosen": -74.6461181640625,
|
| 108 |
+
"logps/rejected": -98.91078186035156,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 111 |
+
"rewards/chosen": 0.00022823773906566203,
|
| 112 |
+
"rewards/margins": 0.0024594543501734734,
|
| 113 |
+
"rewards/rejected": -0.00223121652379632,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.8828828828828827,
|
| 118 |
+
"grad_norm": 0.5074446797370911,
|
| 119 |
+
"learning_rate": 4.964774158361991e-06,
|
| 120 |
+
"logits/chosen": 1.8522154092788696,
|
| 121 |
+
"logits/rejected": 1.8161392211914062,
|
| 122 |
+
"logps/chosen": -89.16864013671875,
|
| 123 |
+
"logps/rejected": -81.97349548339844,
|
| 124 |
+
"loss": 0.6911,
|
| 125 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 126 |
+
"rewards/chosen": 0.006215038243681192,
|
| 127 |
+
"rewards/margins": 0.005521883722394705,
|
| 128 |
+
"rewards/rejected": 0.0006931538810022175,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.2432432432432434,
|
| 133 |
+
"grad_norm": 0.6148263812065125,
|
| 134 |
+
"learning_rate": 4.93261217644956e-06,
|
| 135 |
+
"logits/chosen": 1.7915083169937134,
|
| 136 |
+
"logits/rejected": 1.7579513788223267,
|
| 137 |
+
"logps/chosen": -88.66618347167969,
|
| 138 |
+
"logps/rejected": -80.2238998413086,
|
| 139 |
+
"loss": 0.6918,
|
| 140 |
+
"rewards/accuracies": 0.574999988079071,
|
| 141 |
+
"rewards/chosen": 0.005774274934083223,
|
| 142 |
+
"rewards/margins": 0.016623441129922867,
|
| 143 |
+
"rewards/rejected": -0.010849165730178356,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.6036036036036037,
|
| 148 |
+
"grad_norm": 0.6143240332603455,
|
| 149 |
+
"learning_rate": 4.8902889044347e-06,
|
| 150 |
+
"logits/chosen": 1.6886920928955078,
|
| 151 |
+
"logits/rejected": 1.8121178150177002,
|
| 152 |
+
"logps/chosen": -72.908203125,
|
| 153 |
+
"logps/rejected": -92.44017028808594,
|
| 154 |
+
"loss": 0.6911,
|
| 155 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 156 |
+
"rewards/chosen": -0.0015121791511774063,
|
| 157 |
+
"rewards/margins": 0.0036420777905732393,
|
| 158 |
+
"rewards/rejected": -0.005154256708920002,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.963963963963964,
|
| 163 |
+
"grad_norm": 0.7140340209007263,
|
| 164 |
+
"learning_rate": 4.837981131305475e-06,
|
| 165 |
+
"logits/chosen": 1.7481105327606201,
|
| 166 |
+
"logits/rejected": 1.723141074180603,
|
| 167 |
+
"logps/chosen": -80.63452911376953,
|
| 168 |
+
"logps/rejected": -72.64492797851562,
|
| 169 |
+
"loss": 0.6894,
|
| 170 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 171 |
+
"rewards/chosen": -0.006246576085686684,
|
| 172 |
+
"rewards/margins": -0.0035218377597630024,
|
| 173 |
+
"rewards/rejected": -0.0027247383259236813,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.324324324324325,
|
| 178 |
+
"grad_norm": 1.1645854711532593,
|
| 179 |
+
"learning_rate": 4.775907352415367e-06,
|
| 180 |
+
"logits/chosen": 1.7416290044784546,
|
| 181 |
+
"logits/rejected": 1.8237574100494385,
|
| 182 |
+
"logps/chosen": -89.01248931884766,
|
| 183 |
+
"logps/rejected": -92.31901550292969,
|
| 184 |
+
"loss": 0.6869,
|
| 185 |
+
"rewards/accuracies": 0.612500011920929,
|
| 186 |
+
"rewards/chosen": -0.008855113759636879,
|
| 187 |
+
"rewards/margins": 0.013151508755981922,
|
| 188 |
+
"rewards/rejected": -0.022006623446941376,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.684684684684685,
|
| 193 |
+
"grad_norm": 0.6638664603233337,
|
| 194 |
+
"learning_rate": 4.70432685680402e-06,
|
| 195 |
+
"logits/chosen": 1.7124770879745483,
|
| 196 |
+
"logits/rejected": 1.7777938842773438,
|
| 197 |
+
"logps/chosen": -84.87271881103516,
|
| 198 |
+
"logps/rejected": -92.4839096069336,
|
| 199 |
+
"loss": 0.6855,
|
| 200 |
+
"rewards/accuracies": 0.574999988079071,
|
| 201 |
+
"rewards/chosen": -0.004437069408595562,
|
| 202 |
+
"rewards/margins": 0.019811339676380157,
|
| 203 |
+
"rewards/rejected": -0.024248410016298294,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.045045045045045,
|
| 208 |
+
"grad_norm": 0.785169780254364,
|
| 209 |
+
"learning_rate": 4.623538644118244e-06,
|
| 210 |
+
"logits/chosen": 1.7838690280914307,
|
| 211 |
+
"logits/rejected": 1.8052574396133423,
|
| 212 |
+
"logps/chosen": -94.57842254638672,
|
| 213 |
+
"logps/rejected": -80.6390609741211,
|
| 214 |
+
"loss": 0.6836,
|
| 215 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 216 |
+
"rewards/chosen": -0.026147600263357162,
|
| 217 |
+
"rewards/margins": 0.010936126112937927,
|
| 218 |
+
"rewards/rejected": -0.03708372637629509,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.405405405405405,
|
| 223 |
+
"grad_norm": 0.745952844619751,
|
| 224 |
+
"learning_rate": 4.533880175657419e-06,
|
| 225 |
+
"logits/chosen": 1.7925735712051392,
|
| 226 |
+
"logits/rejected": 1.7987396717071533,
|
| 227 |
+
"logps/chosen": -82.4854507446289,
|
| 228 |
+
"logps/rejected": -77.50787353515625,
|
| 229 |
+
"loss": 0.6767,
|
| 230 |
+
"rewards/accuracies": 0.625,
|
| 231 |
+
"rewards/chosen": -0.013469865545630455,
|
| 232 |
+
"rewards/margins": 0.04023212194442749,
|
| 233 |
+
"rewards/rejected": -0.053701985627412796,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.7657657657657655,
|
| 238 |
+
"grad_norm": 0.7885063290596008,
|
| 239 |
+
"learning_rate": 4.435725964760331e-06,
|
| 240 |
+
"logits/chosen": 1.7725191116333008,
|
| 241 |
+
"logits/rejected": 1.8345234394073486,
|
| 242 |
+
"logps/chosen": -78.7154541015625,
|
| 243 |
+
"logps/rejected": -80.75708770751953,
|
| 244 |
+
"loss": 0.6721,
|
| 245 |
+
"rewards/accuracies": 0.675000011920929,
|
| 246 |
+
"rewards/chosen": -0.018351273611187935,
|
| 247 |
+
"rewards/margins": 0.05368901416659355,
|
| 248 |
+
"rewards/rejected": -0.07204028964042664,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.126126126126126,
|
| 253 |
+
"grad_norm": 0.7734187245368958,
|
| 254 |
+
"learning_rate": 4.329486012421531e-06,
|
| 255 |
+
"logits/chosen": 1.827528715133667,
|
| 256 |
+
"logits/rejected": 1.7939176559448242,
|
| 257 |
+
"logps/chosen": -75.33561706542969,
|
| 258 |
+
"logps/rejected": -71.34326934814453,
|
| 259 |
+
"loss": 0.6775,
|
| 260 |
+
"rewards/accuracies": 0.612500011920929,
|
| 261 |
+
"rewards/chosen": -0.038218818604946136,
|
| 262 |
+
"rewards/margins": 0.06159939616918564,
|
| 263 |
+
"rewards/rejected": -0.09981821477413177,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.486486486486487,
|
| 268 |
+
"grad_norm": 0.7796682715415955,
|
| 269 |
+
"learning_rate": 4.215604094671835e-06,
|
| 270 |
+
"logits/chosen": 1.729288101196289,
|
| 271 |
+
"logits/rejected": 1.7497504949569702,
|
| 272 |
+
"logps/chosen": -83.02750396728516,
|
| 273 |
+
"logps/rejected": -78.53959655761719,
|
| 274 |
+
"loss": 0.6632,
|
| 275 |
+
"rewards/accuracies": 0.699999988079071,
|
| 276 |
+
"rewards/chosen": -0.03207743167877197,
|
| 277 |
+
"rewards/margins": 0.06858544796705246,
|
| 278 |
+
"rewards/rejected": -0.10066288709640503,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.846846846846847,
|
| 283 |
+
"grad_norm": 0.8168752193450928,
|
| 284 |
+
"learning_rate": 4.094555908876765e-06,
|
| 285 |
+
"logits/chosen": 1.747865080833435,
|
| 286 |
+
"logits/rejected": 1.7993282079696655,
|
| 287 |
+
"logps/chosen": -78.75782775878906,
|
| 288 |
+
"logps/rejected": -85.8946304321289,
|
| 289 |
+
"loss": 0.668,
|
| 290 |
+
"rewards/accuracies": 0.612500011920929,
|
| 291 |
+
"rewards/chosen": -0.0766468197107315,
|
| 292 |
+
"rewards/margins": 0.045263100415468216,
|
| 293 |
+
"rewards/rejected": -0.12190990149974823,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 7.207207207207207,
|
| 298 |
+
"grad_norm": 0.9816763997077942,
|
| 299 |
+
"learning_rate": 3.966847086696045e-06,
|
| 300 |
+
"logits/chosen": 1.792106032371521,
|
| 301 |
+
"logits/rejected": 1.7798125743865967,
|
| 302 |
+
"logps/chosen": -93.53439331054688,
|
| 303 |
+
"logps/rejected": -73.8904037475586,
|
| 304 |
+
"loss": 0.6582,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.06042450666427612,
|
| 307 |
+
"rewards/margins": 0.10538975894451141,
|
| 308 |
+
"rewards/rejected": -0.16581428050994873,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.5675675675675675,
|
| 313 |
+
"grad_norm": 0.9053374528884888,
|
| 314 |
+
"learning_rate": 3.833011082004229e-06,
|
| 315 |
+
"logits/chosen": 1.7648969888687134,
|
| 316 |
+
"logits/rejected": 1.7725557088851929,
|
| 317 |
+
"logps/chosen": -79.61383056640625,
|
| 318 |
+
"logps/rejected": -71.8048095703125,
|
| 319 |
+
"loss": 0.6551,
|
| 320 |
+
"rewards/accuracies": 0.6875,
|
| 321 |
+
"rewards/chosen": -0.040038011968135834,
|
| 322 |
+
"rewards/margins": 0.11104954779148102,
|
| 323 |
+
"rewards/rejected": -0.15108755230903625,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.927927927927928,
|
| 328 |
+
"grad_norm": 1.1332669258117676,
|
| 329 |
+
"learning_rate": 3.693606942594873e-06,
|
| 330 |
+
"logits/chosen": 1.8605678081512451,
|
| 331 |
+
"logits/rejected": 1.91280996799469,
|
| 332 |
+
"logps/chosen": -74.39783477783203,
|
| 333 |
+
"logps/rejected": -90.66893005371094,
|
| 334 |
+
"loss": 0.6565,
|
| 335 |
+
"rewards/accuracies": 0.637499988079071,
|
| 336 |
+
"rewards/chosen": -0.08056517690420151,
|
| 337 |
+
"rewards/margins": 0.0968993678689003,
|
| 338 |
+
"rewards/rejected": -0.1774645447731018,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.288288288288289,
|
| 343 |
+
"grad_norm": 1.0496221780776978,
|
| 344 |
+
"learning_rate": 3.549216974976073e-06,
|
| 345 |
+
"logits/chosen": 1.8636070489883423,
|
| 346 |
+
"logits/rejected": 1.7996151447296143,
|
| 347 |
+
"logps/chosen": -89.9018783569336,
|
| 348 |
+
"logps/rejected": -74.14125061035156,
|
| 349 |
+
"loss": 0.6423,
|
| 350 |
+
"rewards/accuracies": 0.6875,
|
| 351 |
+
"rewards/chosen": -0.05598217993974686,
|
| 352 |
+
"rewards/margins": 0.14807265996932983,
|
| 353 |
+
"rewards/rejected": -0.2040548026561737,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.64864864864865,
|
| 358 |
+
"grad_norm": 0.8506491780281067,
|
| 359 |
+
"learning_rate": 3.400444312011776e-06,
|
| 360 |
+
"logits/chosen": 1.7753232717514038,
|
| 361 |
+
"logits/rejected": 1.7647806406021118,
|
| 362 |
+
"logps/chosen": -88.50201416015625,
|
| 363 |
+
"logps/rejected": -81.80894470214844,
|
| 364 |
+
"loss": 0.6358,
|
| 365 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 366 |
+
"rewards/chosen": -0.09656485170125961,
|
| 367 |
+
"rewards/margins": 0.11554913222789764,
|
| 368 |
+
"rewards/rejected": -0.21211397647857666,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.00900900900901,
|
| 373 |
+
"grad_norm": 0.9554071426391602,
|
| 374 |
+
"learning_rate": 3.2479103935691047e-06,
|
| 375 |
+
"logits/chosen": 1.7528200149536133,
|
| 376 |
+
"logits/rejected": 1.7827808856964111,
|
| 377 |
+
"logps/chosen": -90.01268005371094,
|
| 378 |
+
"logps/rejected": -89.0714340209961,
|
| 379 |
+
"loss": 0.6374,
|
| 380 |
+
"rewards/accuracies": 0.675000011920929,
|
| 381 |
+
"rewards/chosen": -0.07412372529506683,
|
| 382 |
+
"rewards/margins": 0.1321595013141632,
|
| 383 |
+
"rewards/rejected": -0.20628324151039124,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.36936936936937,
|
| 388 |
+
"grad_norm": 0.9363342523574829,
|
| 389 |
+
"learning_rate": 3.092252370695298e-06,
|
| 390 |
+
"logits/chosen": 1.6990101337432861,
|
| 391 |
+
"logits/rejected": 1.8281656503677368,
|
| 392 |
+
"logps/chosen": -71.15428161621094,
|
| 393 |
+
"logps/rejected": -79.72063446044922,
|
| 394 |
+
"loss": 0.6303,
|
| 395 |
+
"rewards/accuracies": 0.762499988079071,
|
| 396 |
+
"rewards/chosen": -0.08240491151809692,
|
| 397 |
+
"rewards/margins": 0.16954098641872406,
|
| 398 |
+
"rewards/rejected": -0.2519459128379822,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.72972972972973,
|
| 403 |
+
"grad_norm": 1.023535966873169,
|
| 404 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 405 |
+
"logits/chosen": 1.7418006658554077,
|
| 406 |
+
"logits/rejected": 1.7500028610229492,
|
| 407 |
+
"logps/chosen": -82.24595642089844,
|
| 408 |
+
"logps/rejected": -91.16307067871094,
|
| 409 |
+
"loss": 0.6321,
|
| 410 |
+
"rewards/accuracies": 0.6875,
|
| 411 |
+
"rewards/chosen": -0.13560767471790314,
|
| 412 |
+
"rewards/margins": 0.1204828992486,
|
| 413 |
+
"rewards/rejected": -0.25609058141708374,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 10.09009009009009,
|
| 418 |
+
"grad_norm": 1.0393471717834473,
|
| 419 |
+
"learning_rate": 2.7741751485313295e-06,
|
| 420 |
+
"logits/chosen": 1.8437154293060303,
|
| 421 |
+
"logits/rejected": 1.8877627849578857,
|
| 422 |
+
"logps/chosen": -68.61182403564453,
|
| 423 |
+
"logps/rejected": -77.12557220458984,
|
| 424 |
+
"loss": 0.6109,
|
| 425 |
+
"rewards/accuracies": 0.737500011920929,
|
| 426 |
+
"rewards/chosen": -0.11025551706552505,
|
| 427 |
+
"rewards/margins": 0.14969798922538757,
|
| 428 |
+
"rewards/rejected": -0.25995349884033203,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 10.45045045045045,
|
| 433 |
+
"grad_norm": 0.9554691910743713,
|
| 434 |
+
"learning_rate": 2.6130845929767662e-06,
|
| 435 |
+
"logits/chosen": 1.7998764514923096,
|
| 436 |
+
"logits/rejected": 1.796451210975647,
|
| 437 |
+
"logps/chosen": -72.6626205444336,
|
| 438 |
+
"logps/rejected": -74.15937042236328,
|
| 439 |
+
"loss": 0.6123,
|
| 440 |
+
"rewards/accuracies": 0.737500011920929,
|
| 441 |
+
"rewards/chosen": -0.13948099315166473,
|
| 442 |
+
"rewards/margins": 0.18039894104003906,
|
| 443 |
+
"rewards/rejected": -0.319879949092865,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.81081081081081,
|
| 448 |
+
"grad_norm": 1.1667226552963257,
|
| 449 |
+
"learning_rate": 2.4515216705704396e-06,
|
| 450 |
+
"logits/chosen": 1.8437564373016357,
|
| 451 |
+
"logits/rejected": 1.9043811559677124,
|
| 452 |
+
"logps/chosen": -78.18916320800781,
|
| 453 |
+
"logps/rejected": -90.88524627685547,
|
| 454 |
+
"loss": 0.6218,
|
| 455 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 456 |
+
"rewards/chosen": -0.12091793864965439,
|
| 457 |
+
"rewards/margins": 0.20490169525146484,
|
| 458 |
+
"rewards/rejected": -0.32581964135169983,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 11.17117117117117,
|
| 463 |
+
"grad_norm": 1.2568660974502563,
|
| 464 |
+
"learning_rate": 2.290161247507733e-06,
|
| 465 |
+
"logits/chosen": 1.7295608520507812,
|
| 466 |
+
"logits/rejected": 1.8652616739273071,
|
| 467 |
+
"logps/chosen": -79.8567886352539,
|
| 468 |
+
"logps/rejected": -87.59798431396484,
|
| 469 |
+
"loss": 0.6067,
|
| 470 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 471 |
+
"rewards/chosen": -0.10961383581161499,
|
| 472 |
+
"rewards/margins": 0.2835196554660797,
|
| 473 |
+
"rewards/rejected": -0.3931335210800171,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 11.531531531531531,
|
| 478 |
+
"grad_norm": 1.115491271018982,
|
| 479 |
+
"learning_rate": 2.129677344121879e-06,
|
| 480 |
+
"logits/chosen": 1.803063988685608,
|
| 481 |
+
"logits/rejected": 1.820227861404419,
|
| 482 |
+
"logps/chosen": -74.64582061767578,
|
| 483 |
+
"logps/rejected": -72.14736938476562,
|
| 484 |
+
"loss": 0.6113,
|
| 485 |
+
"rewards/accuracies": 0.75,
|
| 486 |
+
"rewards/chosen": -0.09987158328294754,
|
| 487 |
+
"rewards/margins": 0.2059938907623291,
|
| 488 |
+
"rewards/rejected": -0.30586546659469604,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.891891891891891,
|
| 493 |
+
"grad_norm": 0.9227492213249207,
|
| 494 |
+
"learning_rate": 1.970740319426474e-06,
|
| 495 |
+
"logits/chosen": 1.7561572790145874,
|
| 496 |
+
"logits/rejected": 1.789878249168396,
|
| 497 |
+
"logps/chosen": -85.27911376953125,
|
| 498 |
+
"logps/rejected": -77.4220962524414,
|
| 499 |
+
"loss": 0.5891,
|
| 500 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 501 |
+
"rewards/chosen": -0.14200571179389954,
|
| 502 |
+
"rewards/margins": 0.22272682189941406,
|
| 503 |
+
"rewards/rejected": -0.3647325336933136,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 12.252252252252251,
|
| 508 |
+
"grad_norm": 1.541570782661438,
|
| 509 |
+
"learning_rate": 1.8140140709517467e-06,
|
| 510 |
+
"logits/chosen": 1.7364771366119385,
|
| 511 |
+
"logits/rejected": 1.7182557582855225,
|
| 512 |
+
"logps/chosen": -76.05533599853516,
|
| 513 |
+
"logps/rejected": -81.50830078125,
|
| 514 |
+
"loss": 0.5994,
|
| 515 |
+
"rewards/accuracies": 0.75,
|
| 516 |
+
"rewards/chosen": -0.12165775150060654,
|
| 517 |
+
"rewards/margins": 0.19019995629787445,
|
| 518 |
+
"rewards/rejected": -0.3118577301502228,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 12.612612612612612,
|
| 523 |
+
"grad_norm": 1.1125155687332153,
|
| 524 |
+
"learning_rate": 1.6601532615711452e-06,
|
| 525 |
+
"logits/chosen": 1.7223026752471924,
|
| 526 |
+
"logits/rejected": 1.8163812160491943,
|
| 527 |
+
"logps/chosen": -71.94869232177734,
|
| 528 |
+
"logps/rejected": -90.12442016601562,
|
| 529 |
+
"loss": 0.6013,
|
| 530 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 531 |
+
"rewards/chosen": -0.16840626299381256,
|
| 532 |
+
"rewards/margins": 0.1776614487171173,
|
| 533 |
+
"rewards/rejected": -0.3460676968097687,
|
| 534 |
+
"step": 350
|
| 535 |
+
}
|
| 536 |
+
],
|
| 537 |
+
"logging_steps": 10,
|
| 538 |
+
"max_steps": 540,
|
| 539 |
+
"num_input_tokens_seen": 0,
|
| 540 |
+
"num_train_epochs": 20,
|
| 541 |
+
"save_steps": 50,
|
| 542 |
+
"stateful_callbacks": {
|
| 543 |
+
"TrainerControl": {
|
| 544 |
+
"args": {
|
| 545 |
+
"should_epoch_stop": false,
|
| 546 |
+
"should_evaluate": false,
|
| 547 |
+
"should_log": false,
|
| 548 |
+
"should_save": true,
|
| 549 |
+
"should_training_stop": false
|
| 550 |
+
},
|
| 551 |
+
"attributes": {}
|
| 552 |
+
}
|
| 553 |
+
},
|
| 554 |
+
"total_flos": 1.1850583847982858e+18,
|
| 555 |
+
"train_batch_size": 1,
|
| 556 |
+
"trial_name": null,
|
| 557 |
+
"trial_params": null
|
| 558 |
+
}
|
Area_Time/checkpoint-400/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_Time/checkpoint-400/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_Time/checkpoint-400/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Area_Time/checkpoint-400/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_Time/checkpoint-400/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Area_Time/checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,633 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.414414414414415,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36036036036036034,
|
| 13 |
+
"grad_norm": 0.5300200581550598,
|
| 14 |
+
"learning_rate": 9.259259259259259e-07,
|
| 15 |
+
"logits/chosen": 1.7405741214752197,
|
| 16 |
+
"logits/rejected": 1.663368582725525,
|
| 17 |
+
"logps/chosen": -97.57881164550781,
|
| 18 |
+
"logps/rejected": -70.59793853759766,
|
| 19 |
+
"loss": 0.6938,
|
| 20 |
+
"rewards/accuracies": 0.4375,
|
| 21 |
+
"rewards/chosen": 0.0018835498485714197,
|
| 22 |
+
"rewards/margins": -0.0008800366776995361,
|
| 23 |
+
"rewards/rejected": 0.0027635858859866858,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7207207207207207,
|
| 28 |
+
"grad_norm": 0.4883837401866913,
|
| 29 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 30 |
+
"logits/chosen": 1.8280715942382812,
|
| 31 |
+
"logits/rejected": 1.8215343952178955,
|
| 32 |
+
"logps/chosen": -90.60624694824219,
|
| 33 |
+
"logps/rejected": -79.04981994628906,
|
| 34 |
+
"loss": 0.6945,
|
| 35 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 36 |
+
"rewards/chosen": 0.0014454321935772896,
|
| 37 |
+
"rewards/margins": -0.004174981266260147,
|
| 38 |
+
"rewards/rejected": 0.005620413459837437,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0810810810810811,
|
| 43 |
+
"grad_norm": 0.5554109215736389,
|
| 44 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 45 |
+
"logits/chosen": 1.7980501651763916,
|
| 46 |
+
"logits/rejected": 1.841104507446289,
|
| 47 |
+
"logps/chosen": -80.78228759765625,
|
| 48 |
+
"logps/rejected": -85.08882141113281,
|
| 49 |
+
"loss": 0.693,
|
| 50 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 51 |
+
"rewards/chosen": 0.0042568682692945,
|
| 52 |
+
"rewards/margins": -0.0038191028870642185,
|
| 53 |
+
"rewards/rejected": 0.008075973019003868,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4414414414414414,
|
| 58 |
+
"grad_norm": 0.537497341632843,
|
| 59 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 60 |
+
"logits/chosen": 1.7320470809936523,
|
| 61 |
+
"logits/rejected": 1.7411377429962158,
|
| 62 |
+
"logps/chosen": -82.24813842773438,
|
| 63 |
+
"logps/rejected": -80.90709686279297,
|
| 64 |
+
"loss": 0.6952,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.00350201572291553,
|
| 67 |
+
"rewards/margins": -0.012091752141714096,
|
| 68 |
+
"rewards/rejected": 0.008589735254645348,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.8018018018018018,
|
| 73 |
+
"grad_norm": 0.5023094415664673,
|
| 74 |
+
"learning_rate": 4.62962962962963e-06,
|
| 75 |
+
"logits/chosen": 1.8292573690414429,
|
| 76 |
+
"logits/rejected": 1.8632844686508179,
|
| 77 |
+
"logps/chosen": -85.98481750488281,
|
| 78 |
+
"logps/rejected": -86.14008331298828,
|
| 79 |
+
"loss": 0.6928,
|
| 80 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 81 |
+
"rewards/chosen": 0.00168000184930861,
|
| 82 |
+
"rewards/margins": -0.011136507615447044,
|
| 83 |
+
"rewards/rejected": 0.01281650923192501,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.1621621621621623,
|
| 88 |
+
"grad_norm": 0.4981901943683624,
|
| 89 |
+
"learning_rate": 4.998119881260576e-06,
|
| 90 |
+
"logits/chosen": 1.8536121845245361,
|
| 91 |
+
"logits/rejected": 1.7948782444000244,
|
| 92 |
+
"logps/chosen": -90.0439682006836,
|
| 93 |
+
"logps/rejected": -79.8309555053711,
|
| 94 |
+
"loss": 0.6914,
|
| 95 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 96 |
+
"rewards/chosen": 0.0025153260212391615,
|
| 97 |
+
"rewards/margins": -0.0021209525875747204,
|
| 98 |
+
"rewards/rejected": 0.004636278375983238,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5225225225225225,
|
| 103 |
+
"grad_norm": 0.6208468079566956,
|
| 104 |
+
"learning_rate": 4.9866405060165044e-06,
|
| 105 |
+
"logits/chosen": 1.7845121622085571,
|
| 106 |
+
"logits/rejected": 1.8721017837524414,
|
| 107 |
+
"logps/chosen": -74.6461181640625,
|
| 108 |
+
"logps/rejected": -98.91078186035156,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 111 |
+
"rewards/chosen": 0.00022823773906566203,
|
| 112 |
+
"rewards/margins": 0.0024594543501734734,
|
| 113 |
+
"rewards/rejected": -0.00223121652379632,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.8828828828828827,
|
| 118 |
+
"grad_norm": 0.5074446797370911,
|
| 119 |
+
"learning_rate": 4.964774158361991e-06,
|
| 120 |
+
"logits/chosen": 1.8522154092788696,
|
| 121 |
+
"logits/rejected": 1.8161392211914062,
|
| 122 |
+
"logps/chosen": -89.16864013671875,
|
| 123 |
+
"logps/rejected": -81.97349548339844,
|
| 124 |
+
"loss": 0.6911,
|
| 125 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 126 |
+
"rewards/chosen": 0.006215038243681192,
|
| 127 |
+
"rewards/margins": 0.005521883722394705,
|
| 128 |
+
"rewards/rejected": 0.0006931538810022175,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.2432432432432434,
|
| 133 |
+
"grad_norm": 0.6148263812065125,
|
| 134 |
+
"learning_rate": 4.93261217644956e-06,
|
| 135 |
+
"logits/chosen": 1.7915083169937134,
|
| 136 |
+
"logits/rejected": 1.7579513788223267,
|
| 137 |
+
"logps/chosen": -88.66618347167969,
|
| 138 |
+
"logps/rejected": -80.2238998413086,
|
| 139 |
+
"loss": 0.6918,
|
| 140 |
+
"rewards/accuracies": 0.574999988079071,
|
| 141 |
+
"rewards/chosen": 0.005774274934083223,
|
| 142 |
+
"rewards/margins": 0.016623441129922867,
|
| 143 |
+
"rewards/rejected": -0.010849165730178356,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.6036036036036037,
|
| 148 |
+
"grad_norm": 0.6143240332603455,
|
| 149 |
+
"learning_rate": 4.8902889044347e-06,
|
| 150 |
+
"logits/chosen": 1.6886920928955078,
|
| 151 |
+
"logits/rejected": 1.8121178150177002,
|
| 152 |
+
"logps/chosen": -72.908203125,
|
| 153 |
+
"logps/rejected": -92.44017028808594,
|
| 154 |
+
"loss": 0.6911,
|
| 155 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 156 |
+
"rewards/chosen": -0.0015121791511774063,
|
| 157 |
+
"rewards/margins": 0.0036420777905732393,
|
| 158 |
+
"rewards/rejected": -0.005154256708920002,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.963963963963964,
|
| 163 |
+
"grad_norm": 0.7140340209007263,
|
| 164 |
+
"learning_rate": 4.837981131305475e-06,
|
| 165 |
+
"logits/chosen": 1.7481105327606201,
|
| 166 |
+
"logits/rejected": 1.723141074180603,
|
| 167 |
+
"logps/chosen": -80.63452911376953,
|
| 168 |
+
"logps/rejected": -72.64492797851562,
|
| 169 |
+
"loss": 0.6894,
|
| 170 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 171 |
+
"rewards/chosen": -0.006246576085686684,
|
| 172 |
+
"rewards/margins": -0.0035218377597630024,
|
| 173 |
+
"rewards/rejected": -0.0027247383259236813,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.324324324324325,
|
| 178 |
+
"grad_norm": 1.1645854711532593,
|
| 179 |
+
"learning_rate": 4.775907352415367e-06,
|
| 180 |
+
"logits/chosen": 1.7416290044784546,
|
| 181 |
+
"logits/rejected": 1.8237574100494385,
|
| 182 |
+
"logps/chosen": -89.01248931884766,
|
| 183 |
+
"logps/rejected": -92.31901550292969,
|
| 184 |
+
"loss": 0.6869,
|
| 185 |
+
"rewards/accuracies": 0.612500011920929,
|
| 186 |
+
"rewards/chosen": -0.008855113759636879,
|
| 187 |
+
"rewards/margins": 0.013151508755981922,
|
| 188 |
+
"rewards/rejected": -0.022006623446941376,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.684684684684685,
|
| 193 |
+
"grad_norm": 0.6638664603233337,
|
| 194 |
+
"learning_rate": 4.70432685680402e-06,
|
| 195 |
+
"logits/chosen": 1.7124770879745483,
|
| 196 |
+
"logits/rejected": 1.7777938842773438,
|
| 197 |
+
"logps/chosen": -84.87271881103516,
|
| 198 |
+
"logps/rejected": -92.4839096069336,
|
| 199 |
+
"loss": 0.6855,
|
| 200 |
+
"rewards/accuracies": 0.574999988079071,
|
| 201 |
+
"rewards/chosen": -0.004437069408595562,
|
| 202 |
+
"rewards/margins": 0.019811339676380157,
|
| 203 |
+
"rewards/rejected": -0.024248410016298294,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.045045045045045,
|
| 208 |
+
"grad_norm": 0.785169780254364,
|
| 209 |
+
"learning_rate": 4.623538644118244e-06,
|
| 210 |
+
"logits/chosen": 1.7838690280914307,
|
| 211 |
+
"logits/rejected": 1.8052574396133423,
|
| 212 |
+
"logps/chosen": -94.57842254638672,
|
| 213 |
+
"logps/rejected": -80.6390609741211,
|
| 214 |
+
"loss": 0.6836,
|
| 215 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 216 |
+
"rewards/chosen": -0.026147600263357162,
|
| 217 |
+
"rewards/margins": 0.010936126112937927,
|
| 218 |
+
"rewards/rejected": -0.03708372637629509,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.405405405405405,
|
| 223 |
+
"grad_norm": 0.745952844619751,
|
| 224 |
+
"learning_rate": 4.533880175657419e-06,
|
| 225 |
+
"logits/chosen": 1.7925735712051392,
|
| 226 |
+
"logits/rejected": 1.7987396717071533,
|
| 227 |
+
"logps/chosen": -82.4854507446289,
|
| 228 |
+
"logps/rejected": -77.50787353515625,
|
| 229 |
+
"loss": 0.6767,
|
| 230 |
+
"rewards/accuracies": 0.625,
|
| 231 |
+
"rewards/chosen": -0.013469865545630455,
|
| 232 |
+
"rewards/margins": 0.04023212194442749,
|
| 233 |
+
"rewards/rejected": -0.053701985627412796,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.7657657657657655,
|
| 238 |
+
"grad_norm": 0.7885063290596008,
|
| 239 |
+
"learning_rate": 4.435725964760331e-06,
|
| 240 |
+
"logits/chosen": 1.7725191116333008,
|
| 241 |
+
"logits/rejected": 1.8345234394073486,
|
| 242 |
+
"logps/chosen": -78.7154541015625,
|
| 243 |
+
"logps/rejected": -80.75708770751953,
|
| 244 |
+
"loss": 0.6721,
|
| 245 |
+
"rewards/accuracies": 0.675000011920929,
|
| 246 |
+
"rewards/chosen": -0.018351273611187935,
|
| 247 |
+
"rewards/margins": 0.05368901416659355,
|
| 248 |
+
"rewards/rejected": -0.07204028964042664,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.126126126126126,
|
| 253 |
+
"grad_norm": 0.7734187245368958,
|
| 254 |
+
"learning_rate": 4.329486012421531e-06,
|
| 255 |
+
"logits/chosen": 1.827528715133667,
|
| 256 |
+
"logits/rejected": 1.7939176559448242,
|
| 257 |
+
"logps/chosen": -75.33561706542969,
|
| 258 |
+
"logps/rejected": -71.34326934814453,
|
| 259 |
+
"loss": 0.6775,
|
| 260 |
+
"rewards/accuracies": 0.612500011920929,
|
| 261 |
+
"rewards/chosen": -0.038218818604946136,
|
| 262 |
+
"rewards/margins": 0.06159939616918564,
|
| 263 |
+
"rewards/rejected": -0.09981821477413177,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.486486486486487,
|
| 268 |
+
"grad_norm": 0.7796682715415955,
|
| 269 |
+
"learning_rate": 4.215604094671835e-06,
|
| 270 |
+
"logits/chosen": 1.729288101196289,
|
| 271 |
+
"logits/rejected": 1.7497504949569702,
|
| 272 |
+
"logps/chosen": -83.02750396728516,
|
| 273 |
+
"logps/rejected": -78.53959655761719,
|
| 274 |
+
"loss": 0.6632,
|
| 275 |
+
"rewards/accuracies": 0.699999988079071,
|
| 276 |
+
"rewards/chosen": -0.03207743167877197,
|
| 277 |
+
"rewards/margins": 0.06858544796705246,
|
| 278 |
+
"rewards/rejected": -0.10066288709640503,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.846846846846847,
|
| 283 |
+
"grad_norm": 0.8168752193450928,
|
| 284 |
+
"learning_rate": 4.094555908876765e-06,
|
| 285 |
+
"logits/chosen": 1.747865080833435,
|
| 286 |
+
"logits/rejected": 1.7993282079696655,
|
| 287 |
+
"logps/chosen": -78.75782775878906,
|
| 288 |
+
"logps/rejected": -85.8946304321289,
|
| 289 |
+
"loss": 0.668,
|
| 290 |
+
"rewards/accuracies": 0.612500011920929,
|
| 291 |
+
"rewards/chosen": -0.0766468197107315,
|
| 292 |
+
"rewards/margins": 0.045263100415468216,
|
| 293 |
+
"rewards/rejected": -0.12190990149974823,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 7.207207207207207,
|
| 298 |
+
"grad_norm": 0.9816763997077942,
|
| 299 |
+
"learning_rate": 3.966847086696045e-06,
|
| 300 |
+
"logits/chosen": 1.792106032371521,
|
| 301 |
+
"logits/rejected": 1.7798125743865967,
|
| 302 |
+
"logps/chosen": -93.53439331054688,
|
| 303 |
+
"logps/rejected": -73.8904037475586,
|
| 304 |
+
"loss": 0.6582,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.06042450666427612,
|
| 307 |
+
"rewards/margins": 0.10538975894451141,
|
| 308 |
+
"rewards/rejected": -0.16581428050994873,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.5675675675675675,
|
| 313 |
+
"grad_norm": 0.9053374528884888,
|
| 314 |
+
"learning_rate": 3.833011082004229e-06,
|
| 315 |
+
"logits/chosen": 1.7648969888687134,
|
| 316 |
+
"logits/rejected": 1.7725557088851929,
|
| 317 |
+
"logps/chosen": -79.61383056640625,
|
| 318 |
+
"logps/rejected": -71.8048095703125,
|
| 319 |
+
"loss": 0.6551,
|
| 320 |
+
"rewards/accuracies": 0.6875,
|
| 321 |
+
"rewards/chosen": -0.040038011968135834,
|
| 322 |
+
"rewards/margins": 0.11104954779148102,
|
| 323 |
+
"rewards/rejected": -0.15108755230903625,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.927927927927928,
|
| 328 |
+
"grad_norm": 1.1332669258117676,
|
| 329 |
+
"learning_rate": 3.693606942594873e-06,
|
| 330 |
+
"logits/chosen": 1.8605678081512451,
|
| 331 |
+
"logits/rejected": 1.91280996799469,
|
| 332 |
+
"logps/chosen": -74.39783477783203,
|
| 333 |
+
"logps/rejected": -90.66893005371094,
|
| 334 |
+
"loss": 0.6565,
|
| 335 |
+
"rewards/accuracies": 0.637499988079071,
|
| 336 |
+
"rewards/chosen": -0.08056517690420151,
|
| 337 |
+
"rewards/margins": 0.0968993678689003,
|
| 338 |
+
"rewards/rejected": -0.1774645447731018,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.288288288288289,
|
| 343 |
+
"grad_norm": 1.0496221780776978,
|
| 344 |
+
"learning_rate": 3.549216974976073e-06,
|
| 345 |
+
"logits/chosen": 1.8636070489883423,
|
| 346 |
+
"logits/rejected": 1.7996151447296143,
|
| 347 |
+
"logps/chosen": -89.9018783569336,
|
| 348 |
+
"logps/rejected": -74.14125061035156,
|
| 349 |
+
"loss": 0.6423,
|
| 350 |
+
"rewards/accuracies": 0.6875,
|
| 351 |
+
"rewards/chosen": -0.05598217993974686,
|
| 352 |
+
"rewards/margins": 0.14807265996932983,
|
| 353 |
+
"rewards/rejected": -0.2040548026561737,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.64864864864865,
|
| 358 |
+
"grad_norm": 0.8506491780281067,
|
| 359 |
+
"learning_rate": 3.400444312011776e-06,
|
| 360 |
+
"logits/chosen": 1.7753232717514038,
|
| 361 |
+
"logits/rejected": 1.7647806406021118,
|
| 362 |
+
"logps/chosen": -88.50201416015625,
|
| 363 |
+
"logps/rejected": -81.80894470214844,
|
| 364 |
+
"loss": 0.6358,
|
| 365 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 366 |
+
"rewards/chosen": -0.09656485170125961,
|
| 367 |
+
"rewards/margins": 0.11554913222789764,
|
| 368 |
+
"rewards/rejected": -0.21211397647857666,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.00900900900901,
|
| 373 |
+
"grad_norm": 0.9554071426391602,
|
| 374 |
+
"learning_rate": 3.2479103935691047e-06,
|
| 375 |
+
"logits/chosen": 1.7528200149536133,
|
| 376 |
+
"logits/rejected": 1.7827808856964111,
|
| 377 |
+
"logps/chosen": -90.01268005371094,
|
| 378 |
+
"logps/rejected": -89.0714340209961,
|
| 379 |
+
"loss": 0.6374,
|
| 380 |
+
"rewards/accuracies": 0.675000011920929,
|
| 381 |
+
"rewards/chosen": -0.07412372529506683,
|
| 382 |
+
"rewards/margins": 0.1321595013141632,
|
| 383 |
+
"rewards/rejected": -0.20628324151039124,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.36936936936937,
|
| 388 |
+
"grad_norm": 0.9363342523574829,
|
| 389 |
+
"learning_rate": 3.092252370695298e-06,
|
| 390 |
+
"logits/chosen": 1.6990101337432861,
|
| 391 |
+
"logits/rejected": 1.8281656503677368,
|
| 392 |
+
"logps/chosen": -71.15428161621094,
|
| 393 |
+
"logps/rejected": -79.72063446044922,
|
| 394 |
+
"loss": 0.6303,
|
| 395 |
+
"rewards/accuracies": 0.762499988079071,
|
| 396 |
+
"rewards/chosen": -0.08240491151809692,
|
| 397 |
+
"rewards/margins": 0.16954098641872406,
|
| 398 |
+
"rewards/rejected": -0.2519459128379822,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.72972972972973,
|
| 403 |
+
"grad_norm": 1.023535966873169,
|
| 404 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 405 |
+
"logits/chosen": 1.7418006658554077,
|
| 406 |
+
"logits/rejected": 1.7500028610229492,
|
| 407 |
+
"logps/chosen": -82.24595642089844,
|
| 408 |
+
"logps/rejected": -91.16307067871094,
|
| 409 |
+
"loss": 0.6321,
|
| 410 |
+
"rewards/accuracies": 0.6875,
|
| 411 |
+
"rewards/chosen": -0.13560767471790314,
|
| 412 |
+
"rewards/margins": 0.1204828992486,
|
| 413 |
+
"rewards/rejected": -0.25609058141708374,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 10.09009009009009,
|
| 418 |
+
"grad_norm": 1.0393471717834473,
|
| 419 |
+
"learning_rate": 2.7741751485313295e-06,
|
| 420 |
+
"logits/chosen": 1.8437154293060303,
|
| 421 |
+
"logits/rejected": 1.8877627849578857,
|
| 422 |
+
"logps/chosen": -68.61182403564453,
|
| 423 |
+
"logps/rejected": -77.12557220458984,
|
| 424 |
+
"loss": 0.6109,
|
| 425 |
+
"rewards/accuracies": 0.737500011920929,
|
| 426 |
+
"rewards/chosen": -0.11025551706552505,
|
| 427 |
+
"rewards/margins": 0.14969798922538757,
|
| 428 |
+
"rewards/rejected": -0.25995349884033203,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 10.45045045045045,
|
| 433 |
+
"grad_norm": 0.9554691910743713,
|
| 434 |
+
"learning_rate": 2.6130845929767662e-06,
|
| 435 |
+
"logits/chosen": 1.7998764514923096,
|
| 436 |
+
"logits/rejected": 1.796451210975647,
|
| 437 |
+
"logps/chosen": -72.6626205444336,
|
| 438 |
+
"logps/rejected": -74.15937042236328,
|
| 439 |
+
"loss": 0.6123,
|
| 440 |
+
"rewards/accuracies": 0.737500011920929,
|
| 441 |
+
"rewards/chosen": -0.13948099315166473,
|
| 442 |
+
"rewards/margins": 0.18039894104003906,
|
| 443 |
+
"rewards/rejected": -0.319879949092865,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.81081081081081,
|
| 448 |
+
"grad_norm": 1.1667226552963257,
|
| 449 |
+
"learning_rate": 2.4515216705704396e-06,
|
| 450 |
+
"logits/chosen": 1.8437564373016357,
|
| 451 |
+
"logits/rejected": 1.9043811559677124,
|
| 452 |
+
"logps/chosen": -78.18916320800781,
|
| 453 |
+
"logps/rejected": -90.88524627685547,
|
| 454 |
+
"loss": 0.6218,
|
| 455 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 456 |
+
"rewards/chosen": -0.12091793864965439,
|
| 457 |
+
"rewards/margins": 0.20490169525146484,
|
| 458 |
+
"rewards/rejected": -0.32581964135169983,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 11.17117117117117,
|
| 463 |
+
"grad_norm": 1.2568660974502563,
|
| 464 |
+
"learning_rate": 2.290161247507733e-06,
|
| 465 |
+
"logits/chosen": 1.7295608520507812,
|
| 466 |
+
"logits/rejected": 1.8652616739273071,
|
| 467 |
+
"logps/chosen": -79.8567886352539,
|
| 468 |
+
"logps/rejected": -87.59798431396484,
|
| 469 |
+
"loss": 0.6067,
|
| 470 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 471 |
+
"rewards/chosen": -0.10961383581161499,
|
| 472 |
+
"rewards/margins": 0.2835196554660797,
|
| 473 |
+
"rewards/rejected": -0.3931335210800171,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 11.531531531531531,
|
| 478 |
+
"grad_norm": 1.115491271018982,
|
| 479 |
+
"learning_rate": 2.129677344121879e-06,
|
| 480 |
+
"logits/chosen": 1.803063988685608,
|
| 481 |
+
"logits/rejected": 1.820227861404419,
|
| 482 |
+
"logps/chosen": -74.64582061767578,
|
| 483 |
+
"logps/rejected": -72.14736938476562,
|
| 484 |
+
"loss": 0.6113,
|
| 485 |
+
"rewards/accuracies": 0.75,
|
| 486 |
+
"rewards/chosen": -0.09987158328294754,
|
| 487 |
+
"rewards/margins": 0.2059938907623291,
|
| 488 |
+
"rewards/rejected": -0.30586546659469604,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.891891891891891,
|
| 493 |
+
"grad_norm": 0.9227492213249207,
|
| 494 |
+
"learning_rate": 1.970740319426474e-06,
|
| 495 |
+
"logits/chosen": 1.7561572790145874,
|
| 496 |
+
"logits/rejected": 1.789878249168396,
|
| 497 |
+
"logps/chosen": -85.27911376953125,
|
| 498 |
+
"logps/rejected": -77.4220962524414,
|
| 499 |
+
"loss": 0.5891,
|
| 500 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 501 |
+
"rewards/chosen": -0.14200571179389954,
|
| 502 |
+
"rewards/margins": 0.22272682189941406,
|
| 503 |
+
"rewards/rejected": -0.3647325336933136,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 12.252252252252251,
|
| 508 |
+
"grad_norm": 1.541570782661438,
|
| 509 |
+
"learning_rate": 1.8140140709517467e-06,
|
| 510 |
+
"logits/chosen": 1.7364771366119385,
|
| 511 |
+
"logits/rejected": 1.7182557582855225,
|
| 512 |
+
"logps/chosen": -76.05533599853516,
|
| 513 |
+
"logps/rejected": -81.50830078125,
|
| 514 |
+
"loss": 0.5994,
|
| 515 |
+
"rewards/accuracies": 0.75,
|
| 516 |
+
"rewards/chosen": -0.12165775150060654,
|
| 517 |
+
"rewards/margins": 0.19019995629787445,
|
| 518 |
+
"rewards/rejected": -0.3118577301502228,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 12.612612612612612,
|
| 523 |
+
"grad_norm": 1.1125155687332153,
|
| 524 |
+
"learning_rate": 1.6601532615711452e-06,
|
| 525 |
+
"logits/chosen": 1.7223026752471924,
|
| 526 |
+
"logits/rejected": 1.8163812160491943,
|
| 527 |
+
"logps/chosen": -71.94869232177734,
|
| 528 |
+
"logps/rejected": -90.12442016601562,
|
| 529 |
+
"loss": 0.6013,
|
| 530 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 531 |
+
"rewards/chosen": -0.16840626299381256,
|
| 532 |
+
"rewards/margins": 0.1776614487171173,
|
| 533 |
+
"rewards/rejected": -0.3460676968097687,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 12.972972972972974,
|
| 538 |
+
"grad_norm": 1.0530396699905396,
|
| 539 |
+
"learning_rate": 1.509800584902108e-06,
|
| 540 |
+
"logits/chosen": 1.795819878578186,
|
| 541 |
+
"logits/rejected": 1.8446025848388672,
|
| 542 |
+
"logps/chosen": -82.24161529541016,
|
| 543 |
+
"logps/rejected": -79.51258850097656,
|
| 544 |
+
"loss": 0.5857,
|
| 545 |
+
"rewards/accuracies": 0.800000011920929,
|
| 546 |
+
"rewards/chosen": -0.13156726956367493,
|
| 547 |
+
"rewards/margins": 0.2468404471874237,
|
| 548 |
+
"rewards/rejected": -0.37840771675109863,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 13.333333333333334,
|
| 553 |
+
"grad_norm": 1.0298306941986084,
|
| 554 |
+
"learning_rate": 1.3635840807037487e-06,
|
| 555 |
+
"logits/chosen": 1.8054157495498657,
|
| 556 |
+
"logits/rejected": 1.8246568441390991,
|
| 557 |
+
"logps/chosen": -85.40760803222656,
|
| 558 |
+
"logps/rejected": -78.77482604980469,
|
| 559 |
+
"loss": 0.5943,
|
| 560 |
+
"rewards/accuracies": 0.762499988079071,
|
| 561 |
+
"rewards/chosen": -0.10383795201778412,
|
| 562 |
+
"rewards/margins": 0.2493254393339157,
|
| 563 |
+
"rewards/rejected": -0.35316339135169983,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 13.693693693693694,
|
| 568 |
+
"grad_norm": 1.0601342916488647,
|
| 569 |
+
"learning_rate": 1.2221145114853172e-06,
|
| 570 |
+
"logits/chosen": 1.6507200002670288,
|
| 571 |
+
"logits/rejected": 1.720569372177124,
|
| 572 |
+
"logps/chosen": -74.90982055664062,
|
| 573 |
+
"logps/rejected": -92.51995849609375,
|
| 574 |
+
"loss": 0.5789,
|
| 575 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 576 |
+
"rewards/chosen": -0.13705268502235413,
|
| 577 |
+
"rewards/margins": 0.2740176022052765,
|
| 578 |
+
"rewards/rejected": -0.4110702872276306,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 14.054054054054054,
|
| 583 |
+
"grad_norm": 1.1135063171386719,
|
| 584 |
+
"learning_rate": 1.085982811283654e-06,
|
| 585 |
+
"logits/chosen": 1.7133989334106445,
|
| 586 |
+
"logits/rejected": 1.7338130474090576,
|
| 587 |
+
"logps/chosen": -80.55327606201172,
|
| 588 |
+
"logps/rejected": -82.32875061035156,
|
| 589 |
+
"loss": 0.5847,
|
| 590 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 591 |
+
"rewards/chosen": -0.12969203293323517,
|
| 592 |
+
"rewards/margins": 0.26957422494888306,
|
| 593 |
+
"rewards/rejected": -0.39926621317863464,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 14.414414414414415,
|
| 598 |
+
"grad_norm": 1.0821375846862793,
|
| 599 |
+
"learning_rate": 9.557576172663577e-07,
|
| 600 |
+
"logits/chosen": 1.7035369873046875,
|
| 601 |
+
"logits/rejected": 1.7184028625488281,
|
| 602 |
+
"logps/chosen": -80.99266052246094,
|
| 603 |
+
"logps/rejected": -85.05413818359375,
|
| 604 |
+
"loss": 0.583,
|
| 605 |
+
"rewards/accuracies": 0.824999988079071,
|
| 606 |
+
"rewards/chosen": -0.1366995871067047,
|
| 607 |
+
"rewards/margins": 0.268393874168396,
|
| 608 |
+
"rewards/rejected": -0.4050934910774231,
|
| 609 |
+
"step": 400
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 10,
|
| 613 |
+
"max_steps": 540,
|
| 614 |
+
"num_input_tokens_seen": 0,
|
| 615 |
+
"num_train_epochs": 20,
|
| 616 |
+
"save_steps": 50,
|
| 617 |
+
"stateful_callbacks": {
|
| 618 |
+
"TrainerControl": {
|
| 619 |
+
"args": {
|
| 620 |
+
"should_epoch_stop": false,
|
| 621 |
+
"should_evaluate": false,
|
| 622 |
+
"should_log": false,
|
| 623 |
+
"should_save": true,
|
| 624 |
+
"should_training_stop": false
|
| 625 |
+
},
|
| 626 |
+
"attributes": {}
|
| 627 |
+
}
|
| 628 |
+
},
|
| 629 |
+
"total_flos": 1.35529556182093e+18,
|
| 630 |
+
"train_batch_size": 1,
|
| 631 |
+
"trial_name": null,
|
| 632 |
+
"trial_params": null
|
| 633 |
+
}
|
Area_Time/checkpoint-450/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_Time/checkpoint-450/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_Time/checkpoint-450/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Area_Time/checkpoint-450/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_Time/checkpoint-450/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Area_Time/checkpoint-450/trainer_state.json
ADDED
|
@@ -0,0 +1,708 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 16.216216216216218,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 450,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36036036036036034,
|
| 13 |
+
"grad_norm": 0.5300200581550598,
|
| 14 |
+
"learning_rate": 9.259259259259259e-07,
|
| 15 |
+
"logits/chosen": 1.7405741214752197,
|
| 16 |
+
"logits/rejected": 1.663368582725525,
|
| 17 |
+
"logps/chosen": -97.57881164550781,
|
| 18 |
+
"logps/rejected": -70.59793853759766,
|
| 19 |
+
"loss": 0.6938,
|
| 20 |
+
"rewards/accuracies": 0.4375,
|
| 21 |
+
"rewards/chosen": 0.0018835498485714197,
|
| 22 |
+
"rewards/margins": -0.0008800366776995361,
|
| 23 |
+
"rewards/rejected": 0.0027635858859866858,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7207207207207207,
|
| 28 |
+
"grad_norm": 0.4883837401866913,
|
| 29 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 30 |
+
"logits/chosen": 1.8280715942382812,
|
| 31 |
+
"logits/rejected": 1.8215343952178955,
|
| 32 |
+
"logps/chosen": -90.60624694824219,
|
| 33 |
+
"logps/rejected": -79.04981994628906,
|
| 34 |
+
"loss": 0.6945,
|
| 35 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 36 |
+
"rewards/chosen": 0.0014454321935772896,
|
| 37 |
+
"rewards/margins": -0.004174981266260147,
|
| 38 |
+
"rewards/rejected": 0.005620413459837437,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0810810810810811,
|
| 43 |
+
"grad_norm": 0.5554109215736389,
|
| 44 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 45 |
+
"logits/chosen": 1.7980501651763916,
|
| 46 |
+
"logits/rejected": 1.841104507446289,
|
| 47 |
+
"logps/chosen": -80.78228759765625,
|
| 48 |
+
"logps/rejected": -85.08882141113281,
|
| 49 |
+
"loss": 0.693,
|
| 50 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 51 |
+
"rewards/chosen": 0.0042568682692945,
|
| 52 |
+
"rewards/margins": -0.0038191028870642185,
|
| 53 |
+
"rewards/rejected": 0.008075973019003868,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4414414414414414,
|
| 58 |
+
"grad_norm": 0.537497341632843,
|
| 59 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 60 |
+
"logits/chosen": 1.7320470809936523,
|
| 61 |
+
"logits/rejected": 1.7411377429962158,
|
| 62 |
+
"logps/chosen": -82.24813842773438,
|
| 63 |
+
"logps/rejected": -80.90709686279297,
|
| 64 |
+
"loss": 0.6952,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.00350201572291553,
|
| 67 |
+
"rewards/margins": -0.012091752141714096,
|
| 68 |
+
"rewards/rejected": 0.008589735254645348,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.8018018018018018,
|
| 73 |
+
"grad_norm": 0.5023094415664673,
|
| 74 |
+
"learning_rate": 4.62962962962963e-06,
|
| 75 |
+
"logits/chosen": 1.8292573690414429,
|
| 76 |
+
"logits/rejected": 1.8632844686508179,
|
| 77 |
+
"logps/chosen": -85.98481750488281,
|
| 78 |
+
"logps/rejected": -86.14008331298828,
|
| 79 |
+
"loss": 0.6928,
|
| 80 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 81 |
+
"rewards/chosen": 0.00168000184930861,
|
| 82 |
+
"rewards/margins": -0.011136507615447044,
|
| 83 |
+
"rewards/rejected": 0.01281650923192501,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.1621621621621623,
|
| 88 |
+
"grad_norm": 0.4981901943683624,
|
| 89 |
+
"learning_rate": 4.998119881260576e-06,
|
| 90 |
+
"logits/chosen": 1.8536121845245361,
|
| 91 |
+
"logits/rejected": 1.7948782444000244,
|
| 92 |
+
"logps/chosen": -90.0439682006836,
|
| 93 |
+
"logps/rejected": -79.8309555053711,
|
| 94 |
+
"loss": 0.6914,
|
| 95 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 96 |
+
"rewards/chosen": 0.0025153260212391615,
|
| 97 |
+
"rewards/margins": -0.0021209525875747204,
|
| 98 |
+
"rewards/rejected": 0.004636278375983238,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5225225225225225,
|
| 103 |
+
"grad_norm": 0.6208468079566956,
|
| 104 |
+
"learning_rate": 4.9866405060165044e-06,
|
| 105 |
+
"logits/chosen": 1.7845121622085571,
|
| 106 |
+
"logits/rejected": 1.8721017837524414,
|
| 107 |
+
"logps/chosen": -74.6461181640625,
|
| 108 |
+
"logps/rejected": -98.91078186035156,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 111 |
+
"rewards/chosen": 0.00022823773906566203,
|
| 112 |
+
"rewards/margins": 0.0024594543501734734,
|
| 113 |
+
"rewards/rejected": -0.00223121652379632,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.8828828828828827,
|
| 118 |
+
"grad_norm": 0.5074446797370911,
|
| 119 |
+
"learning_rate": 4.964774158361991e-06,
|
| 120 |
+
"logits/chosen": 1.8522154092788696,
|
| 121 |
+
"logits/rejected": 1.8161392211914062,
|
| 122 |
+
"logps/chosen": -89.16864013671875,
|
| 123 |
+
"logps/rejected": -81.97349548339844,
|
| 124 |
+
"loss": 0.6911,
|
| 125 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 126 |
+
"rewards/chosen": 0.006215038243681192,
|
| 127 |
+
"rewards/margins": 0.005521883722394705,
|
| 128 |
+
"rewards/rejected": 0.0006931538810022175,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.2432432432432434,
|
| 133 |
+
"grad_norm": 0.6148263812065125,
|
| 134 |
+
"learning_rate": 4.93261217644956e-06,
|
| 135 |
+
"logits/chosen": 1.7915083169937134,
|
| 136 |
+
"logits/rejected": 1.7579513788223267,
|
| 137 |
+
"logps/chosen": -88.66618347167969,
|
| 138 |
+
"logps/rejected": -80.2238998413086,
|
| 139 |
+
"loss": 0.6918,
|
| 140 |
+
"rewards/accuracies": 0.574999988079071,
|
| 141 |
+
"rewards/chosen": 0.005774274934083223,
|
| 142 |
+
"rewards/margins": 0.016623441129922867,
|
| 143 |
+
"rewards/rejected": -0.010849165730178356,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.6036036036036037,
|
| 148 |
+
"grad_norm": 0.6143240332603455,
|
| 149 |
+
"learning_rate": 4.8902889044347e-06,
|
| 150 |
+
"logits/chosen": 1.6886920928955078,
|
| 151 |
+
"logits/rejected": 1.8121178150177002,
|
| 152 |
+
"logps/chosen": -72.908203125,
|
| 153 |
+
"logps/rejected": -92.44017028808594,
|
| 154 |
+
"loss": 0.6911,
|
| 155 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 156 |
+
"rewards/chosen": -0.0015121791511774063,
|
| 157 |
+
"rewards/margins": 0.0036420777905732393,
|
| 158 |
+
"rewards/rejected": -0.005154256708920002,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.963963963963964,
|
| 163 |
+
"grad_norm": 0.7140340209007263,
|
| 164 |
+
"learning_rate": 4.837981131305475e-06,
|
| 165 |
+
"logits/chosen": 1.7481105327606201,
|
| 166 |
+
"logits/rejected": 1.723141074180603,
|
| 167 |
+
"logps/chosen": -80.63452911376953,
|
| 168 |
+
"logps/rejected": -72.64492797851562,
|
| 169 |
+
"loss": 0.6894,
|
| 170 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 171 |
+
"rewards/chosen": -0.006246576085686684,
|
| 172 |
+
"rewards/margins": -0.0035218377597630024,
|
| 173 |
+
"rewards/rejected": -0.0027247383259236813,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.324324324324325,
|
| 178 |
+
"grad_norm": 1.1645854711532593,
|
| 179 |
+
"learning_rate": 4.775907352415367e-06,
|
| 180 |
+
"logits/chosen": 1.7416290044784546,
|
| 181 |
+
"logits/rejected": 1.8237574100494385,
|
| 182 |
+
"logps/chosen": -89.01248931884766,
|
| 183 |
+
"logps/rejected": -92.31901550292969,
|
| 184 |
+
"loss": 0.6869,
|
| 185 |
+
"rewards/accuracies": 0.612500011920929,
|
| 186 |
+
"rewards/chosen": -0.008855113759636879,
|
| 187 |
+
"rewards/margins": 0.013151508755981922,
|
| 188 |
+
"rewards/rejected": -0.022006623446941376,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.684684684684685,
|
| 193 |
+
"grad_norm": 0.6638664603233337,
|
| 194 |
+
"learning_rate": 4.70432685680402e-06,
|
| 195 |
+
"logits/chosen": 1.7124770879745483,
|
| 196 |
+
"logits/rejected": 1.7777938842773438,
|
| 197 |
+
"logps/chosen": -84.87271881103516,
|
| 198 |
+
"logps/rejected": -92.4839096069336,
|
| 199 |
+
"loss": 0.6855,
|
| 200 |
+
"rewards/accuracies": 0.574999988079071,
|
| 201 |
+
"rewards/chosen": -0.004437069408595562,
|
| 202 |
+
"rewards/margins": 0.019811339676380157,
|
| 203 |
+
"rewards/rejected": -0.024248410016298294,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.045045045045045,
|
| 208 |
+
"grad_norm": 0.785169780254364,
|
| 209 |
+
"learning_rate": 4.623538644118244e-06,
|
| 210 |
+
"logits/chosen": 1.7838690280914307,
|
| 211 |
+
"logits/rejected": 1.8052574396133423,
|
| 212 |
+
"logps/chosen": -94.57842254638672,
|
| 213 |
+
"logps/rejected": -80.6390609741211,
|
| 214 |
+
"loss": 0.6836,
|
| 215 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 216 |
+
"rewards/chosen": -0.026147600263357162,
|
| 217 |
+
"rewards/margins": 0.010936126112937927,
|
| 218 |
+
"rewards/rejected": -0.03708372637629509,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.405405405405405,
|
| 223 |
+
"grad_norm": 0.745952844619751,
|
| 224 |
+
"learning_rate": 4.533880175657419e-06,
|
| 225 |
+
"logits/chosen": 1.7925735712051392,
|
| 226 |
+
"logits/rejected": 1.7987396717071533,
|
| 227 |
+
"logps/chosen": -82.4854507446289,
|
| 228 |
+
"logps/rejected": -77.50787353515625,
|
| 229 |
+
"loss": 0.6767,
|
| 230 |
+
"rewards/accuracies": 0.625,
|
| 231 |
+
"rewards/chosen": -0.013469865545630455,
|
| 232 |
+
"rewards/margins": 0.04023212194442749,
|
| 233 |
+
"rewards/rejected": -0.053701985627412796,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.7657657657657655,
|
| 238 |
+
"grad_norm": 0.7885063290596008,
|
| 239 |
+
"learning_rate": 4.435725964760331e-06,
|
| 240 |
+
"logits/chosen": 1.7725191116333008,
|
| 241 |
+
"logits/rejected": 1.8345234394073486,
|
| 242 |
+
"logps/chosen": -78.7154541015625,
|
| 243 |
+
"logps/rejected": -80.75708770751953,
|
| 244 |
+
"loss": 0.6721,
|
| 245 |
+
"rewards/accuracies": 0.675000011920929,
|
| 246 |
+
"rewards/chosen": -0.018351273611187935,
|
| 247 |
+
"rewards/margins": 0.05368901416659355,
|
| 248 |
+
"rewards/rejected": -0.07204028964042664,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.126126126126126,
|
| 253 |
+
"grad_norm": 0.7734187245368958,
|
| 254 |
+
"learning_rate": 4.329486012421531e-06,
|
| 255 |
+
"logits/chosen": 1.827528715133667,
|
| 256 |
+
"logits/rejected": 1.7939176559448242,
|
| 257 |
+
"logps/chosen": -75.33561706542969,
|
| 258 |
+
"logps/rejected": -71.34326934814453,
|
| 259 |
+
"loss": 0.6775,
|
| 260 |
+
"rewards/accuracies": 0.612500011920929,
|
| 261 |
+
"rewards/chosen": -0.038218818604946136,
|
| 262 |
+
"rewards/margins": 0.06159939616918564,
|
| 263 |
+
"rewards/rejected": -0.09981821477413177,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.486486486486487,
|
| 268 |
+
"grad_norm": 0.7796682715415955,
|
| 269 |
+
"learning_rate": 4.215604094671835e-06,
|
| 270 |
+
"logits/chosen": 1.729288101196289,
|
| 271 |
+
"logits/rejected": 1.7497504949569702,
|
| 272 |
+
"logps/chosen": -83.02750396728516,
|
| 273 |
+
"logps/rejected": -78.53959655761719,
|
| 274 |
+
"loss": 0.6632,
|
| 275 |
+
"rewards/accuracies": 0.699999988079071,
|
| 276 |
+
"rewards/chosen": -0.03207743167877197,
|
| 277 |
+
"rewards/margins": 0.06858544796705246,
|
| 278 |
+
"rewards/rejected": -0.10066288709640503,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.846846846846847,
|
| 283 |
+
"grad_norm": 0.8168752193450928,
|
| 284 |
+
"learning_rate": 4.094555908876765e-06,
|
| 285 |
+
"logits/chosen": 1.747865080833435,
|
| 286 |
+
"logits/rejected": 1.7993282079696655,
|
| 287 |
+
"logps/chosen": -78.75782775878906,
|
| 288 |
+
"logps/rejected": -85.8946304321289,
|
| 289 |
+
"loss": 0.668,
|
| 290 |
+
"rewards/accuracies": 0.612500011920929,
|
| 291 |
+
"rewards/chosen": -0.0766468197107315,
|
| 292 |
+
"rewards/margins": 0.045263100415468216,
|
| 293 |
+
"rewards/rejected": -0.12190990149974823,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 7.207207207207207,
|
| 298 |
+
"grad_norm": 0.9816763997077942,
|
| 299 |
+
"learning_rate": 3.966847086696045e-06,
|
| 300 |
+
"logits/chosen": 1.792106032371521,
|
| 301 |
+
"logits/rejected": 1.7798125743865967,
|
| 302 |
+
"logps/chosen": -93.53439331054688,
|
| 303 |
+
"logps/rejected": -73.8904037475586,
|
| 304 |
+
"loss": 0.6582,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.06042450666427612,
|
| 307 |
+
"rewards/margins": 0.10538975894451141,
|
| 308 |
+
"rewards/rejected": -0.16581428050994873,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.5675675675675675,
|
| 313 |
+
"grad_norm": 0.9053374528884888,
|
| 314 |
+
"learning_rate": 3.833011082004229e-06,
|
| 315 |
+
"logits/chosen": 1.7648969888687134,
|
| 316 |
+
"logits/rejected": 1.7725557088851929,
|
| 317 |
+
"logps/chosen": -79.61383056640625,
|
| 318 |
+
"logps/rejected": -71.8048095703125,
|
| 319 |
+
"loss": 0.6551,
|
| 320 |
+
"rewards/accuracies": 0.6875,
|
| 321 |
+
"rewards/chosen": -0.040038011968135834,
|
| 322 |
+
"rewards/margins": 0.11104954779148102,
|
| 323 |
+
"rewards/rejected": -0.15108755230903625,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.927927927927928,
|
| 328 |
+
"grad_norm": 1.1332669258117676,
|
| 329 |
+
"learning_rate": 3.693606942594873e-06,
|
| 330 |
+
"logits/chosen": 1.8605678081512451,
|
| 331 |
+
"logits/rejected": 1.91280996799469,
|
| 332 |
+
"logps/chosen": -74.39783477783203,
|
| 333 |
+
"logps/rejected": -90.66893005371094,
|
| 334 |
+
"loss": 0.6565,
|
| 335 |
+
"rewards/accuracies": 0.637499988079071,
|
| 336 |
+
"rewards/chosen": -0.08056517690420151,
|
| 337 |
+
"rewards/margins": 0.0968993678689003,
|
| 338 |
+
"rewards/rejected": -0.1774645447731018,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.288288288288289,
|
| 343 |
+
"grad_norm": 1.0496221780776978,
|
| 344 |
+
"learning_rate": 3.549216974976073e-06,
|
| 345 |
+
"logits/chosen": 1.8636070489883423,
|
| 346 |
+
"logits/rejected": 1.7996151447296143,
|
| 347 |
+
"logps/chosen": -89.9018783569336,
|
| 348 |
+
"logps/rejected": -74.14125061035156,
|
| 349 |
+
"loss": 0.6423,
|
| 350 |
+
"rewards/accuracies": 0.6875,
|
| 351 |
+
"rewards/chosen": -0.05598217993974686,
|
| 352 |
+
"rewards/margins": 0.14807265996932983,
|
| 353 |
+
"rewards/rejected": -0.2040548026561737,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.64864864864865,
|
| 358 |
+
"grad_norm": 0.8506491780281067,
|
| 359 |
+
"learning_rate": 3.400444312011776e-06,
|
| 360 |
+
"logits/chosen": 1.7753232717514038,
|
| 361 |
+
"logits/rejected": 1.7647806406021118,
|
| 362 |
+
"logps/chosen": -88.50201416015625,
|
| 363 |
+
"logps/rejected": -81.80894470214844,
|
| 364 |
+
"loss": 0.6358,
|
| 365 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 366 |
+
"rewards/chosen": -0.09656485170125961,
|
| 367 |
+
"rewards/margins": 0.11554913222789764,
|
| 368 |
+
"rewards/rejected": -0.21211397647857666,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.00900900900901,
|
| 373 |
+
"grad_norm": 0.9554071426391602,
|
| 374 |
+
"learning_rate": 3.2479103935691047e-06,
|
| 375 |
+
"logits/chosen": 1.7528200149536133,
|
| 376 |
+
"logits/rejected": 1.7827808856964111,
|
| 377 |
+
"logps/chosen": -90.01268005371094,
|
| 378 |
+
"logps/rejected": -89.0714340209961,
|
| 379 |
+
"loss": 0.6374,
|
| 380 |
+
"rewards/accuracies": 0.675000011920929,
|
| 381 |
+
"rewards/chosen": -0.07412372529506683,
|
| 382 |
+
"rewards/margins": 0.1321595013141632,
|
| 383 |
+
"rewards/rejected": -0.20628324151039124,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.36936936936937,
|
| 388 |
+
"grad_norm": 0.9363342523574829,
|
| 389 |
+
"learning_rate": 3.092252370695298e-06,
|
| 390 |
+
"logits/chosen": 1.6990101337432861,
|
| 391 |
+
"logits/rejected": 1.8281656503677368,
|
| 392 |
+
"logps/chosen": -71.15428161621094,
|
| 393 |
+
"logps/rejected": -79.72063446044922,
|
| 394 |
+
"loss": 0.6303,
|
| 395 |
+
"rewards/accuracies": 0.762499988079071,
|
| 396 |
+
"rewards/chosen": -0.08240491151809692,
|
| 397 |
+
"rewards/margins": 0.16954098641872406,
|
| 398 |
+
"rewards/rejected": -0.2519459128379822,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.72972972972973,
|
| 403 |
+
"grad_norm": 1.023535966873169,
|
| 404 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 405 |
+
"logits/chosen": 1.7418006658554077,
|
| 406 |
+
"logits/rejected": 1.7500028610229492,
|
| 407 |
+
"logps/chosen": -82.24595642089844,
|
| 408 |
+
"logps/rejected": -91.16307067871094,
|
| 409 |
+
"loss": 0.6321,
|
| 410 |
+
"rewards/accuracies": 0.6875,
|
| 411 |
+
"rewards/chosen": -0.13560767471790314,
|
| 412 |
+
"rewards/margins": 0.1204828992486,
|
| 413 |
+
"rewards/rejected": -0.25609058141708374,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 10.09009009009009,
|
| 418 |
+
"grad_norm": 1.0393471717834473,
|
| 419 |
+
"learning_rate": 2.7741751485313295e-06,
|
| 420 |
+
"logits/chosen": 1.8437154293060303,
|
| 421 |
+
"logits/rejected": 1.8877627849578857,
|
| 422 |
+
"logps/chosen": -68.61182403564453,
|
| 423 |
+
"logps/rejected": -77.12557220458984,
|
| 424 |
+
"loss": 0.6109,
|
| 425 |
+
"rewards/accuracies": 0.737500011920929,
|
| 426 |
+
"rewards/chosen": -0.11025551706552505,
|
| 427 |
+
"rewards/margins": 0.14969798922538757,
|
| 428 |
+
"rewards/rejected": -0.25995349884033203,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 10.45045045045045,
|
| 433 |
+
"grad_norm": 0.9554691910743713,
|
| 434 |
+
"learning_rate": 2.6130845929767662e-06,
|
| 435 |
+
"logits/chosen": 1.7998764514923096,
|
| 436 |
+
"logits/rejected": 1.796451210975647,
|
| 437 |
+
"logps/chosen": -72.6626205444336,
|
| 438 |
+
"logps/rejected": -74.15937042236328,
|
| 439 |
+
"loss": 0.6123,
|
| 440 |
+
"rewards/accuracies": 0.737500011920929,
|
| 441 |
+
"rewards/chosen": -0.13948099315166473,
|
| 442 |
+
"rewards/margins": 0.18039894104003906,
|
| 443 |
+
"rewards/rejected": -0.319879949092865,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.81081081081081,
|
| 448 |
+
"grad_norm": 1.1667226552963257,
|
| 449 |
+
"learning_rate": 2.4515216705704396e-06,
|
| 450 |
+
"logits/chosen": 1.8437564373016357,
|
| 451 |
+
"logits/rejected": 1.9043811559677124,
|
| 452 |
+
"logps/chosen": -78.18916320800781,
|
| 453 |
+
"logps/rejected": -90.88524627685547,
|
| 454 |
+
"loss": 0.6218,
|
| 455 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 456 |
+
"rewards/chosen": -0.12091793864965439,
|
| 457 |
+
"rewards/margins": 0.20490169525146484,
|
| 458 |
+
"rewards/rejected": -0.32581964135169983,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 11.17117117117117,
|
| 463 |
+
"grad_norm": 1.2568660974502563,
|
| 464 |
+
"learning_rate": 2.290161247507733e-06,
|
| 465 |
+
"logits/chosen": 1.7295608520507812,
|
| 466 |
+
"logits/rejected": 1.8652616739273071,
|
| 467 |
+
"logps/chosen": -79.8567886352539,
|
| 468 |
+
"logps/rejected": -87.59798431396484,
|
| 469 |
+
"loss": 0.6067,
|
| 470 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 471 |
+
"rewards/chosen": -0.10961383581161499,
|
| 472 |
+
"rewards/margins": 0.2835196554660797,
|
| 473 |
+
"rewards/rejected": -0.3931335210800171,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 11.531531531531531,
|
| 478 |
+
"grad_norm": 1.115491271018982,
|
| 479 |
+
"learning_rate": 2.129677344121879e-06,
|
| 480 |
+
"logits/chosen": 1.803063988685608,
|
| 481 |
+
"logits/rejected": 1.820227861404419,
|
| 482 |
+
"logps/chosen": -74.64582061767578,
|
| 483 |
+
"logps/rejected": -72.14736938476562,
|
| 484 |
+
"loss": 0.6113,
|
| 485 |
+
"rewards/accuracies": 0.75,
|
| 486 |
+
"rewards/chosen": -0.09987158328294754,
|
| 487 |
+
"rewards/margins": 0.2059938907623291,
|
| 488 |
+
"rewards/rejected": -0.30586546659469604,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.891891891891891,
|
| 493 |
+
"grad_norm": 0.9227492213249207,
|
| 494 |
+
"learning_rate": 1.970740319426474e-06,
|
| 495 |
+
"logits/chosen": 1.7561572790145874,
|
| 496 |
+
"logits/rejected": 1.789878249168396,
|
| 497 |
+
"logps/chosen": -85.27911376953125,
|
| 498 |
+
"logps/rejected": -77.4220962524414,
|
| 499 |
+
"loss": 0.5891,
|
| 500 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 501 |
+
"rewards/chosen": -0.14200571179389954,
|
| 502 |
+
"rewards/margins": 0.22272682189941406,
|
| 503 |
+
"rewards/rejected": -0.3647325336933136,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 12.252252252252251,
|
| 508 |
+
"grad_norm": 1.541570782661438,
|
| 509 |
+
"learning_rate": 1.8140140709517467e-06,
|
| 510 |
+
"logits/chosen": 1.7364771366119385,
|
| 511 |
+
"logits/rejected": 1.7182557582855225,
|
| 512 |
+
"logps/chosen": -76.05533599853516,
|
| 513 |
+
"logps/rejected": -81.50830078125,
|
| 514 |
+
"loss": 0.5994,
|
| 515 |
+
"rewards/accuracies": 0.75,
|
| 516 |
+
"rewards/chosen": -0.12165775150060654,
|
| 517 |
+
"rewards/margins": 0.19019995629787445,
|
| 518 |
+
"rewards/rejected": -0.3118577301502228,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 12.612612612612612,
|
| 523 |
+
"grad_norm": 1.1125155687332153,
|
| 524 |
+
"learning_rate": 1.6601532615711452e-06,
|
| 525 |
+
"logits/chosen": 1.7223026752471924,
|
| 526 |
+
"logits/rejected": 1.8163812160491943,
|
| 527 |
+
"logps/chosen": -71.94869232177734,
|
| 528 |
+
"logps/rejected": -90.12442016601562,
|
| 529 |
+
"loss": 0.6013,
|
| 530 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 531 |
+
"rewards/chosen": -0.16840626299381256,
|
| 532 |
+
"rewards/margins": 0.1776614487171173,
|
| 533 |
+
"rewards/rejected": -0.3460676968097687,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 12.972972972972974,
|
| 538 |
+
"grad_norm": 1.0530396699905396,
|
| 539 |
+
"learning_rate": 1.509800584902108e-06,
|
| 540 |
+
"logits/chosen": 1.795819878578186,
|
| 541 |
+
"logits/rejected": 1.8446025848388672,
|
| 542 |
+
"logps/chosen": -82.24161529541016,
|
| 543 |
+
"logps/rejected": -79.51258850097656,
|
| 544 |
+
"loss": 0.5857,
|
| 545 |
+
"rewards/accuracies": 0.800000011920929,
|
| 546 |
+
"rewards/chosen": -0.13156726956367493,
|
| 547 |
+
"rewards/margins": 0.2468404471874237,
|
| 548 |
+
"rewards/rejected": -0.37840771675109863,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 13.333333333333334,
|
| 553 |
+
"grad_norm": 1.0298306941986084,
|
| 554 |
+
"learning_rate": 1.3635840807037487e-06,
|
| 555 |
+
"logits/chosen": 1.8054157495498657,
|
| 556 |
+
"logits/rejected": 1.8246568441390991,
|
| 557 |
+
"logps/chosen": -85.40760803222656,
|
| 558 |
+
"logps/rejected": -78.77482604980469,
|
| 559 |
+
"loss": 0.5943,
|
| 560 |
+
"rewards/accuracies": 0.762499988079071,
|
| 561 |
+
"rewards/chosen": -0.10383795201778412,
|
| 562 |
+
"rewards/margins": 0.2493254393339157,
|
| 563 |
+
"rewards/rejected": -0.35316339135169983,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 13.693693693693694,
|
| 568 |
+
"grad_norm": 1.0601342916488647,
|
| 569 |
+
"learning_rate": 1.2221145114853172e-06,
|
| 570 |
+
"logits/chosen": 1.6507200002670288,
|
| 571 |
+
"logits/rejected": 1.720569372177124,
|
| 572 |
+
"logps/chosen": -74.90982055664062,
|
| 573 |
+
"logps/rejected": -92.51995849609375,
|
| 574 |
+
"loss": 0.5789,
|
| 575 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 576 |
+
"rewards/chosen": -0.13705268502235413,
|
| 577 |
+
"rewards/margins": 0.2740176022052765,
|
| 578 |
+
"rewards/rejected": -0.4110702872276306,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 14.054054054054054,
|
| 583 |
+
"grad_norm": 1.1135063171386719,
|
| 584 |
+
"learning_rate": 1.085982811283654e-06,
|
| 585 |
+
"logits/chosen": 1.7133989334106445,
|
| 586 |
+
"logits/rejected": 1.7338130474090576,
|
| 587 |
+
"logps/chosen": -80.55327606201172,
|
| 588 |
+
"logps/rejected": -82.32875061035156,
|
| 589 |
+
"loss": 0.5847,
|
| 590 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 591 |
+
"rewards/chosen": -0.12969203293323517,
|
| 592 |
+
"rewards/margins": 0.26957422494888306,
|
| 593 |
+
"rewards/rejected": -0.39926621317863464,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 14.414414414414415,
|
| 598 |
+
"grad_norm": 1.0821375846862793,
|
| 599 |
+
"learning_rate": 9.557576172663577e-07,
|
| 600 |
+
"logits/chosen": 1.7035369873046875,
|
| 601 |
+
"logits/rejected": 1.7184028625488281,
|
| 602 |
+
"logps/chosen": -80.99266052246094,
|
| 603 |
+
"logps/rejected": -85.05413818359375,
|
| 604 |
+
"loss": 0.583,
|
| 605 |
+
"rewards/accuracies": 0.824999988079071,
|
| 606 |
+
"rewards/chosen": -0.1366995871067047,
|
| 607 |
+
"rewards/margins": 0.268393874168396,
|
| 608 |
+
"rewards/rejected": -0.4050934910774231,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 14.774774774774775,
|
| 613 |
+
"grad_norm": 1.1167497634887695,
|
| 614 |
+
"learning_rate": 8.319828944714508e-07,
|
| 615 |
+
"logits/chosen": 1.8293631076812744,
|
| 616 |
+
"logits/rejected": 1.7202396392822266,
|
| 617 |
+
"logps/chosen": -96.96324157714844,
|
| 618 |
+
"logps/rejected": -80.58685302734375,
|
| 619 |
+
"loss": 0.5768,
|
| 620 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 621 |
+
"rewards/chosen": -0.14515718817710876,
|
| 622 |
+
"rewards/margins": 0.27918386459350586,
|
| 623 |
+
"rewards/rejected": -0.4243410527706146,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 15.135135135135135,
|
| 628 |
+
"grad_norm": 1.0140223503112793,
|
| 629 |
+
"learning_rate": 7.151756636052529e-07,
|
| 630 |
+
"logits/chosen": 1.7751014232635498,
|
| 631 |
+
"logits/rejected": 1.7394100427627563,
|
| 632 |
+
"logps/chosen": -104.48625183105469,
|
| 633 |
+
"logps/rejected": -90.3105239868164,
|
| 634 |
+
"loss": 0.5804,
|
| 635 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 636 |
+
"rewards/chosen": -0.14849844574928284,
|
| 637 |
+
"rewards/margins": 0.2261633574962616,
|
| 638 |
+
"rewards/rejected": -0.37466174364089966,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 15.495495495495495,
|
| 643 |
+
"grad_norm": 1.0056337118148804,
|
| 644 |
+
"learning_rate": 6.058238413897052e-07,
|
| 645 |
+
"logits/chosen": 1.7368510961532593,
|
| 646 |
+
"logits/rejected": 1.844665288925171,
|
| 647 |
+
"logps/chosen": -88.00404357910156,
|
| 648 |
+
"logps/rejected": -103.71427917480469,
|
| 649 |
+
"loss": 0.5786,
|
| 650 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 651 |
+
"rewards/chosen": -0.2264096438884735,
|
| 652 |
+
"rewards/margins": 0.2332192212343216,
|
| 653 |
+
"rewards/rejected": -0.4596289098262787,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 15.855855855855856,
|
| 658 |
+
"grad_norm": 1.0402743816375732,
|
| 659 |
+
"learning_rate": 5.043842024802675e-07,
|
| 660 |
+
"logits/chosen": 1.835862398147583,
|
| 661 |
+
"logits/rejected": 1.8621985912322998,
|
| 662 |
+
"logps/chosen": -80.8730697631836,
|
| 663 |
+
"logps/rejected": -77.32243347167969,
|
| 664 |
+
"loss": 0.5737,
|
| 665 |
+
"rewards/accuracies": 0.762499988079071,
|
| 666 |
+
"rewards/chosen": -0.10934928804636002,
|
| 667 |
+
"rewards/margins": 0.26070791482925415,
|
| 668 |
+
"rewards/rejected": -0.3700571656227112,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 16.216216216216218,
|
| 673 |
+
"grad_norm": 1.0037925243377686,
|
| 674 |
+
"learning_rate": 4.1128047146765936e-07,
|
| 675 |
+
"logits/chosen": 1.6536343097686768,
|
| 676 |
+
"logits/rejected": 1.748152494430542,
|
| 677 |
+
"logps/chosen": -85.28504180908203,
|
| 678 |
+
"logps/rejected": -83.04313659667969,
|
| 679 |
+
"loss": 0.5869,
|
| 680 |
+
"rewards/accuracies": 0.8125,
|
| 681 |
+
"rewards/chosen": -0.1468530297279358,
|
| 682 |
+
"rewards/margins": 0.24461284279823303,
|
| 683 |
+
"rewards/rejected": -0.39146584272384644,
|
| 684 |
+
"step": 450
|
| 685 |
+
}
|
| 686 |
+
],
|
| 687 |
+
"logging_steps": 10,
|
| 688 |
+
"max_steps": 540,
|
| 689 |
+
"num_input_tokens_seen": 0,
|
| 690 |
+
"num_train_epochs": 20,
|
| 691 |
+
"save_steps": 50,
|
| 692 |
+
"stateful_callbacks": {
|
| 693 |
+
"TrainerControl": {
|
| 694 |
+
"args": {
|
| 695 |
+
"should_epoch_stop": false,
|
| 696 |
+
"should_evaluate": false,
|
| 697 |
+
"should_log": false,
|
| 698 |
+
"should_save": true,
|
| 699 |
+
"should_training_stop": false
|
| 700 |
+
},
|
| 701 |
+
"attributes": {}
|
| 702 |
+
}
|
| 703 |
+
},
|
| 704 |
+
"total_flos": 1.5241964585536717e+18,
|
| 705 |
+
"train_batch_size": 1,
|
| 706 |
+
"trial_name": null,
|
| 707 |
+
"trial_params": null
|
| 708 |
+
}
|
Area_Time/checkpoint-500/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_Time/checkpoint-500/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_Time/checkpoint-500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Area_Time/checkpoint-500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_Time/checkpoint-500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Area_Time/checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,783 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 18.01801801801802,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36036036036036034,
|
| 13 |
+
"grad_norm": 0.5300200581550598,
|
| 14 |
+
"learning_rate": 9.259259259259259e-07,
|
| 15 |
+
"logits/chosen": 1.7405741214752197,
|
| 16 |
+
"logits/rejected": 1.663368582725525,
|
| 17 |
+
"logps/chosen": -97.57881164550781,
|
| 18 |
+
"logps/rejected": -70.59793853759766,
|
| 19 |
+
"loss": 0.6938,
|
| 20 |
+
"rewards/accuracies": 0.4375,
|
| 21 |
+
"rewards/chosen": 0.0018835498485714197,
|
| 22 |
+
"rewards/margins": -0.0008800366776995361,
|
| 23 |
+
"rewards/rejected": 0.0027635858859866858,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7207207207207207,
|
| 28 |
+
"grad_norm": 0.4883837401866913,
|
| 29 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 30 |
+
"logits/chosen": 1.8280715942382812,
|
| 31 |
+
"logits/rejected": 1.8215343952178955,
|
| 32 |
+
"logps/chosen": -90.60624694824219,
|
| 33 |
+
"logps/rejected": -79.04981994628906,
|
| 34 |
+
"loss": 0.6945,
|
| 35 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 36 |
+
"rewards/chosen": 0.0014454321935772896,
|
| 37 |
+
"rewards/margins": -0.004174981266260147,
|
| 38 |
+
"rewards/rejected": 0.005620413459837437,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0810810810810811,
|
| 43 |
+
"grad_norm": 0.5554109215736389,
|
| 44 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 45 |
+
"logits/chosen": 1.7980501651763916,
|
| 46 |
+
"logits/rejected": 1.841104507446289,
|
| 47 |
+
"logps/chosen": -80.78228759765625,
|
| 48 |
+
"logps/rejected": -85.08882141113281,
|
| 49 |
+
"loss": 0.693,
|
| 50 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 51 |
+
"rewards/chosen": 0.0042568682692945,
|
| 52 |
+
"rewards/margins": -0.0038191028870642185,
|
| 53 |
+
"rewards/rejected": 0.008075973019003868,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4414414414414414,
|
| 58 |
+
"grad_norm": 0.537497341632843,
|
| 59 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 60 |
+
"logits/chosen": 1.7320470809936523,
|
| 61 |
+
"logits/rejected": 1.7411377429962158,
|
| 62 |
+
"logps/chosen": -82.24813842773438,
|
| 63 |
+
"logps/rejected": -80.90709686279297,
|
| 64 |
+
"loss": 0.6952,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.00350201572291553,
|
| 67 |
+
"rewards/margins": -0.012091752141714096,
|
| 68 |
+
"rewards/rejected": 0.008589735254645348,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.8018018018018018,
|
| 73 |
+
"grad_norm": 0.5023094415664673,
|
| 74 |
+
"learning_rate": 4.62962962962963e-06,
|
| 75 |
+
"logits/chosen": 1.8292573690414429,
|
| 76 |
+
"logits/rejected": 1.8632844686508179,
|
| 77 |
+
"logps/chosen": -85.98481750488281,
|
| 78 |
+
"logps/rejected": -86.14008331298828,
|
| 79 |
+
"loss": 0.6928,
|
| 80 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 81 |
+
"rewards/chosen": 0.00168000184930861,
|
| 82 |
+
"rewards/margins": -0.011136507615447044,
|
| 83 |
+
"rewards/rejected": 0.01281650923192501,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.1621621621621623,
|
| 88 |
+
"grad_norm": 0.4981901943683624,
|
| 89 |
+
"learning_rate": 4.998119881260576e-06,
|
| 90 |
+
"logits/chosen": 1.8536121845245361,
|
| 91 |
+
"logits/rejected": 1.7948782444000244,
|
| 92 |
+
"logps/chosen": -90.0439682006836,
|
| 93 |
+
"logps/rejected": -79.8309555053711,
|
| 94 |
+
"loss": 0.6914,
|
| 95 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 96 |
+
"rewards/chosen": 0.0025153260212391615,
|
| 97 |
+
"rewards/margins": -0.0021209525875747204,
|
| 98 |
+
"rewards/rejected": 0.004636278375983238,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5225225225225225,
|
| 103 |
+
"grad_norm": 0.6208468079566956,
|
| 104 |
+
"learning_rate": 4.9866405060165044e-06,
|
| 105 |
+
"logits/chosen": 1.7845121622085571,
|
| 106 |
+
"logits/rejected": 1.8721017837524414,
|
| 107 |
+
"logps/chosen": -74.6461181640625,
|
| 108 |
+
"logps/rejected": -98.91078186035156,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 111 |
+
"rewards/chosen": 0.00022823773906566203,
|
| 112 |
+
"rewards/margins": 0.0024594543501734734,
|
| 113 |
+
"rewards/rejected": -0.00223121652379632,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.8828828828828827,
|
| 118 |
+
"grad_norm": 0.5074446797370911,
|
| 119 |
+
"learning_rate": 4.964774158361991e-06,
|
| 120 |
+
"logits/chosen": 1.8522154092788696,
|
| 121 |
+
"logits/rejected": 1.8161392211914062,
|
| 122 |
+
"logps/chosen": -89.16864013671875,
|
| 123 |
+
"logps/rejected": -81.97349548339844,
|
| 124 |
+
"loss": 0.6911,
|
| 125 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 126 |
+
"rewards/chosen": 0.006215038243681192,
|
| 127 |
+
"rewards/margins": 0.005521883722394705,
|
| 128 |
+
"rewards/rejected": 0.0006931538810022175,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.2432432432432434,
|
| 133 |
+
"grad_norm": 0.6148263812065125,
|
| 134 |
+
"learning_rate": 4.93261217644956e-06,
|
| 135 |
+
"logits/chosen": 1.7915083169937134,
|
| 136 |
+
"logits/rejected": 1.7579513788223267,
|
| 137 |
+
"logps/chosen": -88.66618347167969,
|
| 138 |
+
"logps/rejected": -80.2238998413086,
|
| 139 |
+
"loss": 0.6918,
|
| 140 |
+
"rewards/accuracies": 0.574999988079071,
|
| 141 |
+
"rewards/chosen": 0.005774274934083223,
|
| 142 |
+
"rewards/margins": 0.016623441129922867,
|
| 143 |
+
"rewards/rejected": -0.010849165730178356,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.6036036036036037,
|
| 148 |
+
"grad_norm": 0.6143240332603455,
|
| 149 |
+
"learning_rate": 4.8902889044347e-06,
|
| 150 |
+
"logits/chosen": 1.6886920928955078,
|
| 151 |
+
"logits/rejected": 1.8121178150177002,
|
| 152 |
+
"logps/chosen": -72.908203125,
|
| 153 |
+
"logps/rejected": -92.44017028808594,
|
| 154 |
+
"loss": 0.6911,
|
| 155 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 156 |
+
"rewards/chosen": -0.0015121791511774063,
|
| 157 |
+
"rewards/margins": 0.0036420777905732393,
|
| 158 |
+
"rewards/rejected": -0.005154256708920002,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.963963963963964,
|
| 163 |
+
"grad_norm": 0.7140340209007263,
|
| 164 |
+
"learning_rate": 4.837981131305475e-06,
|
| 165 |
+
"logits/chosen": 1.7481105327606201,
|
| 166 |
+
"logits/rejected": 1.723141074180603,
|
| 167 |
+
"logps/chosen": -80.63452911376953,
|
| 168 |
+
"logps/rejected": -72.64492797851562,
|
| 169 |
+
"loss": 0.6894,
|
| 170 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 171 |
+
"rewards/chosen": -0.006246576085686684,
|
| 172 |
+
"rewards/margins": -0.0035218377597630024,
|
| 173 |
+
"rewards/rejected": -0.0027247383259236813,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.324324324324325,
|
| 178 |
+
"grad_norm": 1.1645854711532593,
|
| 179 |
+
"learning_rate": 4.775907352415367e-06,
|
| 180 |
+
"logits/chosen": 1.7416290044784546,
|
| 181 |
+
"logits/rejected": 1.8237574100494385,
|
| 182 |
+
"logps/chosen": -89.01248931884766,
|
| 183 |
+
"logps/rejected": -92.31901550292969,
|
| 184 |
+
"loss": 0.6869,
|
| 185 |
+
"rewards/accuracies": 0.612500011920929,
|
| 186 |
+
"rewards/chosen": -0.008855113759636879,
|
| 187 |
+
"rewards/margins": 0.013151508755981922,
|
| 188 |
+
"rewards/rejected": -0.022006623446941376,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.684684684684685,
|
| 193 |
+
"grad_norm": 0.6638664603233337,
|
| 194 |
+
"learning_rate": 4.70432685680402e-06,
|
| 195 |
+
"logits/chosen": 1.7124770879745483,
|
| 196 |
+
"logits/rejected": 1.7777938842773438,
|
| 197 |
+
"logps/chosen": -84.87271881103516,
|
| 198 |
+
"logps/rejected": -92.4839096069336,
|
| 199 |
+
"loss": 0.6855,
|
| 200 |
+
"rewards/accuracies": 0.574999988079071,
|
| 201 |
+
"rewards/chosen": -0.004437069408595562,
|
| 202 |
+
"rewards/margins": 0.019811339676380157,
|
| 203 |
+
"rewards/rejected": -0.024248410016298294,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.045045045045045,
|
| 208 |
+
"grad_norm": 0.785169780254364,
|
| 209 |
+
"learning_rate": 4.623538644118244e-06,
|
| 210 |
+
"logits/chosen": 1.7838690280914307,
|
| 211 |
+
"logits/rejected": 1.8052574396133423,
|
| 212 |
+
"logps/chosen": -94.57842254638672,
|
| 213 |
+
"logps/rejected": -80.6390609741211,
|
| 214 |
+
"loss": 0.6836,
|
| 215 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 216 |
+
"rewards/chosen": -0.026147600263357162,
|
| 217 |
+
"rewards/margins": 0.010936126112937927,
|
| 218 |
+
"rewards/rejected": -0.03708372637629509,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.405405405405405,
|
| 223 |
+
"grad_norm": 0.745952844619751,
|
| 224 |
+
"learning_rate": 4.533880175657419e-06,
|
| 225 |
+
"logits/chosen": 1.7925735712051392,
|
| 226 |
+
"logits/rejected": 1.7987396717071533,
|
| 227 |
+
"logps/chosen": -82.4854507446289,
|
| 228 |
+
"logps/rejected": -77.50787353515625,
|
| 229 |
+
"loss": 0.6767,
|
| 230 |
+
"rewards/accuracies": 0.625,
|
| 231 |
+
"rewards/chosen": -0.013469865545630455,
|
| 232 |
+
"rewards/margins": 0.04023212194442749,
|
| 233 |
+
"rewards/rejected": -0.053701985627412796,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.7657657657657655,
|
| 238 |
+
"grad_norm": 0.7885063290596008,
|
| 239 |
+
"learning_rate": 4.435725964760331e-06,
|
| 240 |
+
"logits/chosen": 1.7725191116333008,
|
| 241 |
+
"logits/rejected": 1.8345234394073486,
|
| 242 |
+
"logps/chosen": -78.7154541015625,
|
| 243 |
+
"logps/rejected": -80.75708770751953,
|
| 244 |
+
"loss": 0.6721,
|
| 245 |
+
"rewards/accuracies": 0.675000011920929,
|
| 246 |
+
"rewards/chosen": -0.018351273611187935,
|
| 247 |
+
"rewards/margins": 0.05368901416659355,
|
| 248 |
+
"rewards/rejected": -0.07204028964042664,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.126126126126126,
|
| 253 |
+
"grad_norm": 0.7734187245368958,
|
| 254 |
+
"learning_rate": 4.329486012421531e-06,
|
| 255 |
+
"logits/chosen": 1.827528715133667,
|
| 256 |
+
"logits/rejected": 1.7939176559448242,
|
| 257 |
+
"logps/chosen": -75.33561706542969,
|
| 258 |
+
"logps/rejected": -71.34326934814453,
|
| 259 |
+
"loss": 0.6775,
|
| 260 |
+
"rewards/accuracies": 0.612500011920929,
|
| 261 |
+
"rewards/chosen": -0.038218818604946136,
|
| 262 |
+
"rewards/margins": 0.06159939616918564,
|
| 263 |
+
"rewards/rejected": -0.09981821477413177,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.486486486486487,
|
| 268 |
+
"grad_norm": 0.7796682715415955,
|
| 269 |
+
"learning_rate": 4.215604094671835e-06,
|
| 270 |
+
"logits/chosen": 1.729288101196289,
|
| 271 |
+
"logits/rejected": 1.7497504949569702,
|
| 272 |
+
"logps/chosen": -83.02750396728516,
|
| 273 |
+
"logps/rejected": -78.53959655761719,
|
| 274 |
+
"loss": 0.6632,
|
| 275 |
+
"rewards/accuracies": 0.699999988079071,
|
| 276 |
+
"rewards/chosen": -0.03207743167877197,
|
| 277 |
+
"rewards/margins": 0.06858544796705246,
|
| 278 |
+
"rewards/rejected": -0.10066288709640503,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.846846846846847,
|
| 283 |
+
"grad_norm": 0.8168752193450928,
|
| 284 |
+
"learning_rate": 4.094555908876765e-06,
|
| 285 |
+
"logits/chosen": 1.747865080833435,
|
| 286 |
+
"logits/rejected": 1.7993282079696655,
|
| 287 |
+
"logps/chosen": -78.75782775878906,
|
| 288 |
+
"logps/rejected": -85.8946304321289,
|
| 289 |
+
"loss": 0.668,
|
| 290 |
+
"rewards/accuracies": 0.612500011920929,
|
| 291 |
+
"rewards/chosen": -0.0766468197107315,
|
| 292 |
+
"rewards/margins": 0.045263100415468216,
|
| 293 |
+
"rewards/rejected": -0.12190990149974823,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 7.207207207207207,
|
| 298 |
+
"grad_norm": 0.9816763997077942,
|
| 299 |
+
"learning_rate": 3.966847086696045e-06,
|
| 300 |
+
"logits/chosen": 1.792106032371521,
|
| 301 |
+
"logits/rejected": 1.7798125743865967,
|
| 302 |
+
"logps/chosen": -93.53439331054688,
|
| 303 |
+
"logps/rejected": -73.8904037475586,
|
| 304 |
+
"loss": 0.6582,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.06042450666427612,
|
| 307 |
+
"rewards/margins": 0.10538975894451141,
|
| 308 |
+
"rewards/rejected": -0.16581428050994873,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.5675675675675675,
|
| 313 |
+
"grad_norm": 0.9053374528884888,
|
| 314 |
+
"learning_rate": 3.833011082004229e-06,
|
| 315 |
+
"logits/chosen": 1.7648969888687134,
|
| 316 |
+
"logits/rejected": 1.7725557088851929,
|
| 317 |
+
"logps/chosen": -79.61383056640625,
|
| 318 |
+
"logps/rejected": -71.8048095703125,
|
| 319 |
+
"loss": 0.6551,
|
| 320 |
+
"rewards/accuracies": 0.6875,
|
| 321 |
+
"rewards/chosen": -0.040038011968135834,
|
| 322 |
+
"rewards/margins": 0.11104954779148102,
|
| 323 |
+
"rewards/rejected": -0.15108755230903625,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.927927927927928,
|
| 328 |
+
"grad_norm": 1.1332669258117676,
|
| 329 |
+
"learning_rate": 3.693606942594873e-06,
|
| 330 |
+
"logits/chosen": 1.8605678081512451,
|
| 331 |
+
"logits/rejected": 1.91280996799469,
|
| 332 |
+
"logps/chosen": -74.39783477783203,
|
| 333 |
+
"logps/rejected": -90.66893005371094,
|
| 334 |
+
"loss": 0.6565,
|
| 335 |
+
"rewards/accuracies": 0.637499988079071,
|
| 336 |
+
"rewards/chosen": -0.08056517690420151,
|
| 337 |
+
"rewards/margins": 0.0968993678689003,
|
| 338 |
+
"rewards/rejected": -0.1774645447731018,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.288288288288289,
|
| 343 |
+
"grad_norm": 1.0496221780776978,
|
| 344 |
+
"learning_rate": 3.549216974976073e-06,
|
| 345 |
+
"logits/chosen": 1.8636070489883423,
|
| 346 |
+
"logits/rejected": 1.7996151447296143,
|
| 347 |
+
"logps/chosen": -89.9018783569336,
|
| 348 |
+
"logps/rejected": -74.14125061035156,
|
| 349 |
+
"loss": 0.6423,
|
| 350 |
+
"rewards/accuracies": 0.6875,
|
| 351 |
+
"rewards/chosen": -0.05598217993974686,
|
| 352 |
+
"rewards/margins": 0.14807265996932983,
|
| 353 |
+
"rewards/rejected": -0.2040548026561737,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.64864864864865,
|
| 358 |
+
"grad_norm": 0.8506491780281067,
|
| 359 |
+
"learning_rate": 3.400444312011776e-06,
|
| 360 |
+
"logits/chosen": 1.7753232717514038,
|
| 361 |
+
"logits/rejected": 1.7647806406021118,
|
| 362 |
+
"logps/chosen": -88.50201416015625,
|
| 363 |
+
"logps/rejected": -81.80894470214844,
|
| 364 |
+
"loss": 0.6358,
|
| 365 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 366 |
+
"rewards/chosen": -0.09656485170125961,
|
| 367 |
+
"rewards/margins": 0.11554913222789764,
|
| 368 |
+
"rewards/rejected": -0.21211397647857666,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.00900900900901,
|
| 373 |
+
"grad_norm": 0.9554071426391602,
|
| 374 |
+
"learning_rate": 3.2479103935691047e-06,
|
| 375 |
+
"logits/chosen": 1.7528200149536133,
|
| 376 |
+
"logits/rejected": 1.7827808856964111,
|
| 377 |
+
"logps/chosen": -90.01268005371094,
|
| 378 |
+
"logps/rejected": -89.0714340209961,
|
| 379 |
+
"loss": 0.6374,
|
| 380 |
+
"rewards/accuracies": 0.675000011920929,
|
| 381 |
+
"rewards/chosen": -0.07412372529506683,
|
| 382 |
+
"rewards/margins": 0.1321595013141632,
|
| 383 |
+
"rewards/rejected": -0.20628324151039124,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.36936936936937,
|
| 388 |
+
"grad_norm": 0.9363342523574829,
|
| 389 |
+
"learning_rate": 3.092252370695298e-06,
|
| 390 |
+
"logits/chosen": 1.6990101337432861,
|
| 391 |
+
"logits/rejected": 1.8281656503677368,
|
| 392 |
+
"logps/chosen": -71.15428161621094,
|
| 393 |
+
"logps/rejected": -79.72063446044922,
|
| 394 |
+
"loss": 0.6303,
|
| 395 |
+
"rewards/accuracies": 0.762499988079071,
|
| 396 |
+
"rewards/chosen": -0.08240491151809692,
|
| 397 |
+
"rewards/margins": 0.16954098641872406,
|
| 398 |
+
"rewards/rejected": -0.2519459128379822,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.72972972972973,
|
| 403 |
+
"grad_norm": 1.023535966873169,
|
| 404 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 405 |
+
"logits/chosen": 1.7418006658554077,
|
| 406 |
+
"logits/rejected": 1.7500028610229492,
|
| 407 |
+
"logps/chosen": -82.24595642089844,
|
| 408 |
+
"logps/rejected": -91.16307067871094,
|
| 409 |
+
"loss": 0.6321,
|
| 410 |
+
"rewards/accuracies": 0.6875,
|
| 411 |
+
"rewards/chosen": -0.13560767471790314,
|
| 412 |
+
"rewards/margins": 0.1204828992486,
|
| 413 |
+
"rewards/rejected": -0.25609058141708374,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 10.09009009009009,
|
| 418 |
+
"grad_norm": 1.0393471717834473,
|
| 419 |
+
"learning_rate": 2.7741751485313295e-06,
|
| 420 |
+
"logits/chosen": 1.8437154293060303,
|
| 421 |
+
"logits/rejected": 1.8877627849578857,
|
| 422 |
+
"logps/chosen": -68.61182403564453,
|
| 423 |
+
"logps/rejected": -77.12557220458984,
|
| 424 |
+
"loss": 0.6109,
|
| 425 |
+
"rewards/accuracies": 0.737500011920929,
|
| 426 |
+
"rewards/chosen": -0.11025551706552505,
|
| 427 |
+
"rewards/margins": 0.14969798922538757,
|
| 428 |
+
"rewards/rejected": -0.25995349884033203,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 10.45045045045045,
|
| 433 |
+
"grad_norm": 0.9554691910743713,
|
| 434 |
+
"learning_rate": 2.6130845929767662e-06,
|
| 435 |
+
"logits/chosen": 1.7998764514923096,
|
| 436 |
+
"logits/rejected": 1.796451210975647,
|
| 437 |
+
"logps/chosen": -72.6626205444336,
|
| 438 |
+
"logps/rejected": -74.15937042236328,
|
| 439 |
+
"loss": 0.6123,
|
| 440 |
+
"rewards/accuracies": 0.737500011920929,
|
| 441 |
+
"rewards/chosen": -0.13948099315166473,
|
| 442 |
+
"rewards/margins": 0.18039894104003906,
|
| 443 |
+
"rewards/rejected": -0.319879949092865,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.81081081081081,
|
| 448 |
+
"grad_norm": 1.1667226552963257,
|
| 449 |
+
"learning_rate": 2.4515216705704396e-06,
|
| 450 |
+
"logits/chosen": 1.8437564373016357,
|
| 451 |
+
"logits/rejected": 1.9043811559677124,
|
| 452 |
+
"logps/chosen": -78.18916320800781,
|
| 453 |
+
"logps/rejected": -90.88524627685547,
|
| 454 |
+
"loss": 0.6218,
|
| 455 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 456 |
+
"rewards/chosen": -0.12091793864965439,
|
| 457 |
+
"rewards/margins": 0.20490169525146484,
|
| 458 |
+
"rewards/rejected": -0.32581964135169983,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 11.17117117117117,
|
| 463 |
+
"grad_norm": 1.2568660974502563,
|
| 464 |
+
"learning_rate": 2.290161247507733e-06,
|
| 465 |
+
"logits/chosen": 1.7295608520507812,
|
| 466 |
+
"logits/rejected": 1.8652616739273071,
|
| 467 |
+
"logps/chosen": -79.8567886352539,
|
| 468 |
+
"logps/rejected": -87.59798431396484,
|
| 469 |
+
"loss": 0.6067,
|
| 470 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 471 |
+
"rewards/chosen": -0.10961383581161499,
|
| 472 |
+
"rewards/margins": 0.2835196554660797,
|
| 473 |
+
"rewards/rejected": -0.3931335210800171,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 11.531531531531531,
|
| 478 |
+
"grad_norm": 1.115491271018982,
|
| 479 |
+
"learning_rate": 2.129677344121879e-06,
|
| 480 |
+
"logits/chosen": 1.803063988685608,
|
| 481 |
+
"logits/rejected": 1.820227861404419,
|
| 482 |
+
"logps/chosen": -74.64582061767578,
|
| 483 |
+
"logps/rejected": -72.14736938476562,
|
| 484 |
+
"loss": 0.6113,
|
| 485 |
+
"rewards/accuracies": 0.75,
|
| 486 |
+
"rewards/chosen": -0.09987158328294754,
|
| 487 |
+
"rewards/margins": 0.2059938907623291,
|
| 488 |
+
"rewards/rejected": -0.30586546659469604,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.891891891891891,
|
| 493 |
+
"grad_norm": 0.9227492213249207,
|
| 494 |
+
"learning_rate": 1.970740319426474e-06,
|
| 495 |
+
"logits/chosen": 1.7561572790145874,
|
| 496 |
+
"logits/rejected": 1.789878249168396,
|
| 497 |
+
"logps/chosen": -85.27911376953125,
|
| 498 |
+
"logps/rejected": -77.4220962524414,
|
| 499 |
+
"loss": 0.5891,
|
| 500 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 501 |
+
"rewards/chosen": -0.14200571179389954,
|
| 502 |
+
"rewards/margins": 0.22272682189941406,
|
| 503 |
+
"rewards/rejected": -0.3647325336933136,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 12.252252252252251,
|
| 508 |
+
"grad_norm": 1.541570782661438,
|
| 509 |
+
"learning_rate": 1.8140140709517467e-06,
|
| 510 |
+
"logits/chosen": 1.7364771366119385,
|
| 511 |
+
"logits/rejected": 1.7182557582855225,
|
| 512 |
+
"logps/chosen": -76.05533599853516,
|
| 513 |
+
"logps/rejected": -81.50830078125,
|
| 514 |
+
"loss": 0.5994,
|
| 515 |
+
"rewards/accuracies": 0.75,
|
| 516 |
+
"rewards/chosen": -0.12165775150060654,
|
| 517 |
+
"rewards/margins": 0.19019995629787445,
|
| 518 |
+
"rewards/rejected": -0.3118577301502228,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 12.612612612612612,
|
| 523 |
+
"grad_norm": 1.1125155687332153,
|
| 524 |
+
"learning_rate": 1.6601532615711452e-06,
|
| 525 |
+
"logits/chosen": 1.7223026752471924,
|
| 526 |
+
"logits/rejected": 1.8163812160491943,
|
| 527 |
+
"logps/chosen": -71.94869232177734,
|
| 528 |
+
"logps/rejected": -90.12442016601562,
|
| 529 |
+
"loss": 0.6013,
|
| 530 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 531 |
+
"rewards/chosen": -0.16840626299381256,
|
| 532 |
+
"rewards/margins": 0.1776614487171173,
|
| 533 |
+
"rewards/rejected": -0.3460676968097687,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 12.972972972972974,
|
| 538 |
+
"grad_norm": 1.0530396699905396,
|
| 539 |
+
"learning_rate": 1.509800584902108e-06,
|
| 540 |
+
"logits/chosen": 1.795819878578186,
|
| 541 |
+
"logits/rejected": 1.8446025848388672,
|
| 542 |
+
"logps/chosen": -82.24161529541016,
|
| 543 |
+
"logps/rejected": -79.51258850097656,
|
| 544 |
+
"loss": 0.5857,
|
| 545 |
+
"rewards/accuracies": 0.800000011920929,
|
| 546 |
+
"rewards/chosen": -0.13156726956367493,
|
| 547 |
+
"rewards/margins": 0.2468404471874237,
|
| 548 |
+
"rewards/rejected": -0.37840771675109863,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 13.333333333333334,
|
| 553 |
+
"grad_norm": 1.0298306941986084,
|
| 554 |
+
"learning_rate": 1.3635840807037487e-06,
|
| 555 |
+
"logits/chosen": 1.8054157495498657,
|
| 556 |
+
"logits/rejected": 1.8246568441390991,
|
| 557 |
+
"logps/chosen": -85.40760803222656,
|
| 558 |
+
"logps/rejected": -78.77482604980469,
|
| 559 |
+
"loss": 0.5943,
|
| 560 |
+
"rewards/accuracies": 0.762499988079071,
|
| 561 |
+
"rewards/chosen": -0.10383795201778412,
|
| 562 |
+
"rewards/margins": 0.2493254393339157,
|
| 563 |
+
"rewards/rejected": -0.35316339135169983,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 13.693693693693694,
|
| 568 |
+
"grad_norm": 1.0601342916488647,
|
| 569 |
+
"learning_rate": 1.2221145114853172e-06,
|
| 570 |
+
"logits/chosen": 1.6507200002670288,
|
| 571 |
+
"logits/rejected": 1.720569372177124,
|
| 572 |
+
"logps/chosen": -74.90982055664062,
|
| 573 |
+
"logps/rejected": -92.51995849609375,
|
| 574 |
+
"loss": 0.5789,
|
| 575 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 576 |
+
"rewards/chosen": -0.13705268502235413,
|
| 577 |
+
"rewards/margins": 0.2740176022052765,
|
| 578 |
+
"rewards/rejected": -0.4110702872276306,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 14.054054054054054,
|
| 583 |
+
"grad_norm": 1.1135063171386719,
|
| 584 |
+
"learning_rate": 1.085982811283654e-06,
|
| 585 |
+
"logits/chosen": 1.7133989334106445,
|
| 586 |
+
"logits/rejected": 1.7338130474090576,
|
| 587 |
+
"logps/chosen": -80.55327606201172,
|
| 588 |
+
"logps/rejected": -82.32875061035156,
|
| 589 |
+
"loss": 0.5847,
|
| 590 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 591 |
+
"rewards/chosen": -0.12969203293323517,
|
| 592 |
+
"rewards/margins": 0.26957422494888306,
|
| 593 |
+
"rewards/rejected": -0.39926621317863464,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 14.414414414414415,
|
| 598 |
+
"grad_norm": 1.0821375846862793,
|
| 599 |
+
"learning_rate": 9.557576172663577e-07,
|
| 600 |
+
"logits/chosen": 1.7035369873046875,
|
| 601 |
+
"logits/rejected": 1.7184028625488281,
|
| 602 |
+
"logps/chosen": -80.99266052246094,
|
| 603 |
+
"logps/rejected": -85.05413818359375,
|
| 604 |
+
"loss": 0.583,
|
| 605 |
+
"rewards/accuracies": 0.824999988079071,
|
| 606 |
+
"rewards/chosen": -0.1366995871067047,
|
| 607 |
+
"rewards/margins": 0.268393874168396,
|
| 608 |
+
"rewards/rejected": -0.4050934910774231,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 14.774774774774775,
|
| 613 |
+
"grad_norm": 1.1167497634887695,
|
| 614 |
+
"learning_rate": 8.319828944714508e-07,
|
| 615 |
+
"logits/chosen": 1.8293631076812744,
|
| 616 |
+
"logits/rejected": 1.7202396392822266,
|
| 617 |
+
"logps/chosen": -96.96324157714844,
|
| 618 |
+
"logps/rejected": -80.58685302734375,
|
| 619 |
+
"loss": 0.5768,
|
| 620 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 621 |
+
"rewards/chosen": -0.14515718817710876,
|
| 622 |
+
"rewards/margins": 0.27918386459350586,
|
| 623 |
+
"rewards/rejected": -0.4243410527706146,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 15.135135135135135,
|
| 628 |
+
"grad_norm": 1.0140223503112793,
|
| 629 |
+
"learning_rate": 7.151756636052529e-07,
|
| 630 |
+
"logits/chosen": 1.7751014232635498,
|
| 631 |
+
"logits/rejected": 1.7394100427627563,
|
| 632 |
+
"logps/chosen": -104.48625183105469,
|
| 633 |
+
"logps/rejected": -90.3105239868164,
|
| 634 |
+
"loss": 0.5804,
|
| 635 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 636 |
+
"rewards/chosen": -0.14849844574928284,
|
| 637 |
+
"rewards/margins": 0.2261633574962616,
|
| 638 |
+
"rewards/rejected": -0.37466174364089966,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 15.495495495495495,
|
| 643 |
+
"grad_norm": 1.0056337118148804,
|
| 644 |
+
"learning_rate": 6.058238413897052e-07,
|
| 645 |
+
"logits/chosen": 1.7368510961532593,
|
| 646 |
+
"logits/rejected": 1.844665288925171,
|
| 647 |
+
"logps/chosen": -88.00404357910156,
|
| 648 |
+
"logps/rejected": -103.71427917480469,
|
| 649 |
+
"loss": 0.5786,
|
| 650 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 651 |
+
"rewards/chosen": -0.2264096438884735,
|
| 652 |
+
"rewards/margins": 0.2332192212343216,
|
| 653 |
+
"rewards/rejected": -0.4596289098262787,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 15.855855855855856,
|
| 658 |
+
"grad_norm": 1.0402743816375732,
|
| 659 |
+
"learning_rate": 5.043842024802675e-07,
|
| 660 |
+
"logits/chosen": 1.835862398147583,
|
| 661 |
+
"logits/rejected": 1.8621985912322998,
|
| 662 |
+
"logps/chosen": -80.8730697631836,
|
| 663 |
+
"logps/rejected": -77.32243347167969,
|
| 664 |
+
"loss": 0.5737,
|
| 665 |
+
"rewards/accuracies": 0.762499988079071,
|
| 666 |
+
"rewards/chosen": -0.10934928804636002,
|
| 667 |
+
"rewards/margins": 0.26070791482925415,
|
| 668 |
+
"rewards/rejected": -0.3700571656227112,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 16.216216216216218,
|
| 673 |
+
"grad_norm": 1.0037925243377686,
|
| 674 |
+
"learning_rate": 4.1128047146765936e-07,
|
| 675 |
+
"logits/chosen": 1.6536343097686768,
|
| 676 |
+
"logits/rejected": 1.748152494430542,
|
| 677 |
+
"logps/chosen": -85.28504180908203,
|
| 678 |
+
"logps/rejected": -83.04313659667969,
|
| 679 |
+
"loss": 0.5869,
|
| 680 |
+
"rewards/accuracies": 0.8125,
|
| 681 |
+
"rewards/chosen": -0.1468530297279358,
|
| 682 |
+
"rewards/margins": 0.24461284279823303,
|
| 683 |
+
"rewards/rejected": -0.39146584272384644,
|
| 684 |
+
"step": 450
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 16.576576576576578,
|
| 688 |
+
"grad_norm": 1.0473060607910156,
|
| 689 |
+
"learning_rate": 3.269015529333805e-07,
|
| 690 |
+
"logits/chosen": 1.7145726680755615,
|
| 691 |
+
"logits/rejected": 1.7245705127716064,
|
| 692 |
+
"logps/chosen": -68.06051635742188,
|
| 693 |
+
"logps/rejected": -77.09696960449219,
|
| 694 |
+
"loss": 0.5679,
|
| 695 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 696 |
+
"rewards/chosen": -0.16770952939987183,
|
| 697 |
+
"rewards/margins": 0.23443298041820526,
|
| 698 |
+
"rewards/rejected": -0.4021424651145935,
|
| 699 |
+
"step": 460
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 16.936936936936938,
|
| 703 |
+
"grad_norm": 1.0985324382781982,
|
| 704 |
+
"learning_rate": 2.515999069522676e-07,
|
| 705 |
+
"logits/chosen": 1.7093912363052368,
|
| 706 |
+
"logits/rejected": 1.6903793811798096,
|
| 707 |
+
"logps/chosen": -79.38801574707031,
|
| 708 |
+
"logps/rejected": -74.43864440917969,
|
| 709 |
+
"loss": 0.5754,
|
| 710 |
+
"rewards/accuracies": 0.8125,
|
| 711 |
+
"rewards/chosen": -0.14471781253814697,
|
| 712 |
+
"rewards/margins": 0.24466648697853088,
|
| 713 |
+
"rewards/rejected": -0.38938429951667786,
|
| 714 |
+
"step": 470
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 17.2972972972973,
|
| 718 |
+
"grad_norm": 1.1457403898239136,
|
| 719 |
+
"learning_rate": 1.8569007682777417e-07,
|
| 720 |
+
"logits/chosen": 1.6642320156097412,
|
| 721 |
+
"logits/rejected": 1.7295513153076172,
|
| 722 |
+
"logps/chosen": -80.79732513427734,
|
| 723 |
+
"logps/rejected": -80.07367706298828,
|
| 724 |
+
"loss": 0.5749,
|
| 725 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 726 |
+
"rewards/chosen": -0.16041259467601776,
|
| 727 |
+
"rewards/margins": 0.26678892970085144,
|
| 728 |
+
"rewards/rejected": -0.4272015690803528,
|
| 729 |
+
"step": 480
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 17.65765765765766,
|
| 733 |
+
"grad_norm": 1.04747474193573,
|
| 734 |
+
"learning_rate": 1.2944737520980883e-07,
|
| 735 |
+
"logits/chosen": 1.699061632156372,
|
| 736 |
+
"logits/rejected": 1.837684988975525,
|
| 737 |
+
"logps/chosen": -73.55027770996094,
|
| 738 |
+
"logps/rejected": -93.25712585449219,
|
| 739 |
+
"loss": 0.5732,
|
| 740 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 741 |
+
"rewards/chosen": -0.20150330662727356,
|
| 742 |
+
"rewards/margins": 0.2376147210597992,
|
| 743 |
+
"rewards/rejected": -0.43911799788475037,
|
| 744 |
+
"step": 490
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 18.01801801801802,
|
| 748 |
+
"grad_norm": 1.033074140548706,
|
| 749 |
+
"learning_rate": 8.310673408334496e-08,
|
| 750 |
+
"logits/chosen": 1.655987024307251,
|
| 751 |
+
"logits/rejected": 1.6537258625030518,
|
| 752 |
+
"logps/chosen": -103.11566162109375,
|
| 753 |
+
"logps/rejected": -96.29421997070312,
|
| 754 |
+
"loss": 0.5747,
|
| 755 |
+
"rewards/accuracies": 0.800000011920929,
|
| 756 |
+
"rewards/chosen": -0.15963700413703918,
|
| 757 |
+
"rewards/margins": 0.30574050545692444,
|
| 758 |
+
"rewards/rejected": -0.4653775095939636,
|
| 759 |
+
"step": 500
|
| 760 |
+
}
|
| 761 |
+
],
|
| 762 |
+
"logging_steps": 10,
|
| 763 |
+
"max_steps": 540,
|
| 764 |
+
"num_input_tokens_seen": 0,
|
| 765 |
+
"num_train_epochs": 20,
|
| 766 |
+
"save_steps": 50,
|
| 767 |
+
"stateful_callbacks": {
|
| 768 |
+
"TrainerControl": {
|
| 769 |
+
"args": {
|
| 770 |
+
"should_epoch_stop": false,
|
| 771 |
+
"should_evaluate": false,
|
| 772 |
+
"should_log": false,
|
| 773 |
+
"should_save": true,
|
| 774 |
+
"should_training_stop": false
|
| 775 |
+
},
|
| 776 |
+
"attributes": {}
|
| 777 |
+
}
|
| 778 |
+
},
|
| 779 |
+
"total_flos": 1.6937355895740826e+18,
|
| 780 |
+
"train_batch_size": 1,
|
| 781 |
+
"trial_name": null,
|
| 782 |
+
"trial_params": null
|
| 783 |
+
}
|
Area_Time/checkpoint-540/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_Time/checkpoint-540/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_Time/checkpoint-540/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Area_Time/checkpoint-540/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_Time/checkpoint-540/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Area_Time/checkpoint-540/trainer_state.json
ADDED
|
@@ -0,0 +1,843 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.45945945945946,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 540,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36036036036036034,
|
| 13 |
+
"grad_norm": 0.5300200581550598,
|
| 14 |
+
"learning_rate": 9.259259259259259e-07,
|
| 15 |
+
"logits/chosen": 1.7405741214752197,
|
| 16 |
+
"logits/rejected": 1.663368582725525,
|
| 17 |
+
"logps/chosen": -97.57881164550781,
|
| 18 |
+
"logps/rejected": -70.59793853759766,
|
| 19 |
+
"loss": 0.6938,
|
| 20 |
+
"rewards/accuracies": 0.4375,
|
| 21 |
+
"rewards/chosen": 0.0018835498485714197,
|
| 22 |
+
"rewards/margins": -0.0008800366776995361,
|
| 23 |
+
"rewards/rejected": 0.0027635858859866858,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7207207207207207,
|
| 28 |
+
"grad_norm": 0.4883837401866913,
|
| 29 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 30 |
+
"logits/chosen": 1.8280715942382812,
|
| 31 |
+
"logits/rejected": 1.8215343952178955,
|
| 32 |
+
"logps/chosen": -90.60624694824219,
|
| 33 |
+
"logps/rejected": -79.04981994628906,
|
| 34 |
+
"loss": 0.6945,
|
| 35 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 36 |
+
"rewards/chosen": 0.0014454321935772896,
|
| 37 |
+
"rewards/margins": -0.004174981266260147,
|
| 38 |
+
"rewards/rejected": 0.005620413459837437,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0810810810810811,
|
| 43 |
+
"grad_norm": 0.5554109215736389,
|
| 44 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 45 |
+
"logits/chosen": 1.7980501651763916,
|
| 46 |
+
"logits/rejected": 1.841104507446289,
|
| 47 |
+
"logps/chosen": -80.78228759765625,
|
| 48 |
+
"logps/rejected": -85.08882141113281,
|
| 49 |
+
"loss": 0.693,
|
| 50 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 51 |
+
"rewards/chosen": 0.0042568682692945,
|
| 52 |
+
"rewards/margins": -0.0038191028870642185,
|
| 53 |
+
"rewards/rejected": 0.008075973019003868,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.4414414414414414,
|
| 58 |
+
"grad_norm": 0.537497341632843,
|
| 59 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 60 |
+
"logits/chosen": 1.7320470809936523,
|
| 61 |
+
"logits/rejected": 1.7411377429962158,
|
| 62 |
+
"logps/chosen": -82.24813842773438,
|
| 63 |
+
"logps/rejected": -80.90709686279297,
|
| 64 |
+
"loss": 0.6952,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.00350201572291553,
|
| 67 |
+
"rewards/margins": -0.012091752141714096,
|
| 68 |
+
"rewards/rejected": 0.008589735254645348,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.8018018018018018,
|
| 73 |
+
"grad_norm": 0.5023094415664673,
|
| 74 |
+
"learning_rate": 4.62962962962963e-06,
|
| 75 |
+
"logits/chosen": 1.8292573690414429,
|
| 76 |
+
"logits/rejected": 1.8632844686508179,
|
| 77 |
+
"logps/chosen": -85.98481750488281,
|
| 78 |
+
"logps/rejected": -86.14008331298828,
|
| 79 |
+
"loss": 0.6928,
|
| 80 |
+
"rewards/accuracies": 0.4124999940395355,
|
| 81 |
+
"rewards/chosen": 0.00168000184930861,
|
| 82 |
+
"rewards/margins": -0.011136507615447044,
|
| 83 |
+
"rewards/rejected": 0.01281650923192501,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.1621621621621623,
|
| 88 |
+
"grad_norm": 0.4981901943683624,
|
| 89 |
+
"learning_rate": 4.998119881260576e-06,
|
| 90 |
+
"logits/chosen": 1.8536121845245361,
|
| 91 |
+
"logits/rejected": 1.7948782444000244,
|
| 92 |
+
"logps/chosen": -90.0439682006836,
|
| 93 |
+
"logps/rejected": -79.8309555053711,
|
| 94 |
+
"loss": 0.6914,
|
| 95 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 96 |
+
"rewards/chosen": 0.0025153260212391615,
|
| 97 |
+
"rewards/margins": -0.0021209525875747204,
|
| 98 |
+
"rewards/rejected": 0.004636278375983238,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.5225225225225225,
|
| 103 |
+
"grad_norm": 0.6208468079566956,
|
| 104 |
+
"learning_rate": 4.9866405060165044e-06,
|
| 105 |
+
"logits/chosen": 1.7845121622085571,
|
| 106 |
+
"logits/rejected": 1.8721017837524414,
|
| 107 |
+
"logps/chosen": -74.6461181640625,
|
| 108 |
+
"logps/rejected": -98.91078186035156,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 111 |
+
"rewards/chosen": 0.00022823773906566203,
|
| 112 |
+
"rewards/margins": 0.0024594543501734734,
|
| 113 |
+
"rewards/rejected": -0.00223121652379632,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.8828828828828827,
|
| 118 |
+
"grad_norm": 0.5074446797370911,
|
| 119 |
+
"learning_rate": 4.964774158361991e-06,
|
| 120 |
+
"logits/chosen": 1.8522154092788696,
|
| 121 |
+
"logits/rejected": 1.8161392211914062,
|
| 122 |
+
"logps/chosen": -89.16864013671875,
|
| 123 |
+
"logps/rejected": -81.97349548339844,
|
| 124 |
+
"loss": 0.6911,
|
| 125 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 126 |
+
"rewards/chosen": 0.006215038243681192,
|
| 127 |
+
"rewards/margins": 0.005521883722394705,
|
| 128 |
+
"rewards/rejected": 0.0006931538810022175,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.2432432432432434,
|
| 133 |
+
"grad_norm": 0.6148263812065125,
|
| 134 |
+
"learning_rate": 4.93261217644956e-06,
|
| 135 |
+
"logits/chosen": 1.7915083169937134,
|
| 136 |
+
"logits/rejected": 1.7579513788223267,
|
| 137 |
+
"logps/chosen": -88.66618347167969,
|
| 138 |
+
"logps/rejected": -80.2238998413086,
|
| 139 |
+
"loss": 0.6918,
|
| 140 |
+
"rewards/accuracies": 0.574999988079071,
|
| 141 |
+
"rewards/chosen": 0.005774274934083223,
|
| 142 |
+
"rewards/margins": 0.016623441129922867,
|
| 143 |
+
"rewards/rejected": -0.010849165730178356,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.6036036036036037,
|
| 148 |
+
"grad_norm": 0.6143240332603455,
|
| 149 |
+
"learning_rate": 4.8902889044347e-06,
|
| 150 |
+
"logits/chosen": 1.6886920928955078,
|
| 151 |
+
"logits/rejected": 1.8121178150177002,
|
| 152 |
+
"logps/chosen": -72.908203125,
|
| 153 |
+
"logps/rejected": -92.44017028808594,
|
| 154 |
+
"loss": 0.6911,
|
| 155 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 156 |
+
"rewards/chosen": -0.0015121791511774063,
|
| 157 |
+
"rewards/margins": 0.0036420777905732393,
|
| 158 |
+
"rewards/rejected": -0.005154256708920002,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.963963963963964,
|
| 163 |
+
"grad_norm": 0.7140340209007263,
|
| 164 |
+
"learning_rate": 4.837981131305475e-06,
|
| 165 |
+
"logits/chosen": 1.7481105327606201,
|
| 166 |
+
"logits/rejected": 1.723141074180603,
|
| 167 |
+
"logps/chosen": -80.63452911376953,
|
| 168 |
+
"logps/rejected": -72.64492797851562,
|
| 169 |
+
"loss": 0.6894,
|
| 170 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 171 |
+
"rewards/chosen": -0.006246576085686684,
|
| 172 |
+
"rewards/margins": -0.0035218377597630024,
|
| 173 |
+
"rewards/rejected": -0.0027247383259236813,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.324324324324325,
|
| 178 |
+
"grad_norm": 1.1645854711532593,
|
| 179 |
+
"learning_rate": 4.775907352415367e-06,
|
| 180 |
+
"logits/chosen": 1.7416290044784546,
|
| 181 |
+
"logits/rejected": 1.8237574100494385,
|
| 182 |
+
"logps/chosen": -89.01248931884766,
|
| 183 |
+
"logps/rejected": -92.31901550292969,
|
| 184 |
+
"loss": 0.6869,
|
| 185 |
+
"rewards/accuracies": 0.612500011920929,
|
| 186 |
+
"rewards/chosen": -0.008855113759636879,
|
| 187 |
+
"rewards/margins": 0.013151508755981922,
|
| 188 |
+
"rewards/rejected": -0.022006623446941376,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.684684684684685,
|
| 193 |
+
"grad_norm": 0.6638664603233337,
|
| 194 |
+
"learning_rate": 4.70432685680402e-06,
|
| 195 |
+
"logits/chosen": 1.7124770879745483,
|
| 196 |
+
"logits/rejected": 1.7777938842773438,
|
| 197 |
+
"logps/chosen": -84.87271881103516,
|
| 198 |
+
"logps/rejected": -92.4839096069336,
|
| 199 |
+
"loss": 0.6855,
|
| 200 |
+
"rewards/accuracies": 0.574999988079071,
|
| 201 |
+
"rewards/chosen": -0.004437069408595562,
|
| 202 |
+
"rewards/margins": 0.019811339676380157,
|
| 203 |
+
"rewards/rejected": -0.024248410016298294,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.045045045045045,
|
| 208 |
+
"grad_norm": 0.785169780254364,
|
| 209 |
+
"learning_rate": 4.623538644118244e-06,
|
| 210 |
+
"logits/chosen": 1.7838690280914307,
|
| 211 |
+
"logits/rejected": 1.8052574396133423,
|
| 212 |
+
"logps/chosen": -94.57842254638672,
|
| 213 |
+
"logps/rejected": -80.6390609741211,
|
| 214 |
+
"loss": 0.6836,
|
| 215 |
+
"rewards/accuracies": 0.48750001192092896,
|
| 216 |
+
"rewards/chosen": -0.026147600263357162,
|
| 217 |
+
"rewards/margins": 0.010936126112937927,
|
| 218 |
+
"rewards/rejected": -0.03708372637629509,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.405405405405405,
|
| 223 |
+
"grad_norm": 0.745952844619751,
|
| 224 |
+
"learning_rate": 4.533880175657419e-06,
|
| 225 |
+
"logits/chosen": 1.7925735712051392,
|
| 226 |
+
"logits/rejected": 1.7987396717071533,
|
| 227 |
+
"logps/chosen": -82.4854507446289,
|
| 228 |
+
"logps/rejected": -77.50787353515625,
|
| 229 |
+
"loss": 0.6767,
|
| 230 |
+
"rewards/accuracies": 0.625,
|
| 231 |
+
"rewards/chosen": -0.013469865545630455,
|
| 232 |
+
"rewards/margins": 0.04023212194442749,
|
| 233 |
+
"rewards/rejected": -0.053701985627412796,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.7657657657657655,
|
| 238 |
+
"grad_norm": 0.7885063290596008,
|
| 239 |
+
"learning_rate": 4.435725964760331e-06,
|
| 240 |
+
"logits/chosen": 1.7725191116333008,
|
| 241 |
+
"logits/rejected": 1.8345234394073486,
|
| 242 |
+
"logps/chosen": -78.7154541015625,
|
| 243 |
+
"logps/rejected": -80.75708770751953,
|
| 244 |
+
"loss": 0.6721,
|
| 245 |
+
"rewards/accuracies": 0.675000011920929,
|
| 246 |
+
"rewards/chosen": -0.018351273611187935,
|
| 247 |
+
"rewards/margins": 0.05368901416659355,
|
| 248 |
+
"rewards/rejected": -0.07204028964042664,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.126126126126126,
|
| 253 |
+
"grad_norm": 0.7734187245368958,
|
| 254 |
+
"learning_rate": 4.329486012421531e-06,
|
| 255 |
+
"logits/chosen": 1.827528715133667,
|
| 256 |
+
"logits/rejected": 1.7939176559448242,
|
| 257 |
+
"logps/chosen": -75.33561706542969,
|
| 258 |
+
"logps/rejected": -71.34326934814453,
|
| 259 |
+
"loss": 0.6775,
|
| 260 |
+
"rewards/accuracies": 0.612500011920929,
|
| 261 |
+
"rewards/chosen": -0.038218818604946136,
|
| 262 |
+
"rewards/margins": 0.06159939616918564,
|
| 263 |
+
"rewards/rejected": -0.09981821477413177,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.486486486486487,
|
| 268 |
+
"grad_norm": 0.7796682715415955,
|
| 269 |
+
"learning_rate": 4.215604094671835e-06,
|
| 270 |
+
"logits/chosen": 1.729288101196289,
|
| 271 |
+
"logits/rejected": 1.7497504949569702,
|
| 272 |
+
"logps/chosen": -83.02750396728516,
|
| 273 |
+
"logps/rejected": -78.53959655761719,
|
| 274 |
+
"loss": 0.6632,
|
| 275 |
+
"rewards/accuracies": 0.699999988079071,
|
| 276 |
+
"rewards/chosen": -0.03207743167877197,
|
| 277 |
+
"rewards/margins": 0.06858544796705246,
|
| 278 |
+
"rewards/rejected": -0.10066288709640503,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.846846846846847,
|
| 283 |
+
"grad_norm": 0.8168752193450928,
|
| 284 |
+
"learning_rate": 4.094555908876765e-06,
|
| 285 |
+
"logits/chosen": 1.747865080833435,
|
| 286 |
+
"logits/rejected": 1.7993282079696655,
|
| 287 |
+
"logps/chosen": -78.75782775878906,
|
| 288 |
+
"logps/rejected": -85.8946304321289,
|
| 289 |
+
"loss": 0.668,
|
| 290 |
+
"rewards/accuracies": 0.612500011920929,
|
| 291 |
+
"rewards/chosen": -0.0766468197107315,
|
| 292 |
+
"rewards/margins": 0.045263100415468216,
|
| 293 |
+
"rewards/rejected": -0.12190990149974823,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 7.207207207207207,
|
| 298 |
+
"grad_norm": 0.9816763997077942,
|
| 299 |
+
"learning_rate": 3.966847086696045e-06,
|
| 300 |
+
"logits/chosen": 1.792106032371521,
|
| 301 |
+
"logits/rejected": 1.7798125743865967,
|
| 302 |
+
"logps/chosen": -93.53439331054688,
|
| 303 |
+
"logps/rejected": -73.8904037475586,
|
| 304 |
+
"loss": 0.6582,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.06042450666427612,
|
| 307 |
+
"rewards/margins": 0.10538975894451141,
|
| 308 |
+
"rewards/rejected": -0.16581428050994873,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.5675675675675675,
|
| 313 |
+
"grad_norm": 0.9053374528884888,
|
| 314 |
+
"learning_rate": 3.833011082004229e-06,
|
| 315 |
+
"logits/chosen": 1.7648969888687134,
|
| 316 |
+
"logits/rejected": 1.7725557088851929,
|
| 317 |
+
"logps/chosen": -79.61383056640625,
|
| 318 |
+
"logps/rejected": -71.8048095703125,
|
| 319 |
+
"loss": 0.6551,
|
| 320 |
+
"rewards/accuracies": 0.6875,
|
| 321 |
+
"rewards/chosen": -0.040038011968135834,
|
| 322 |
+
"rewards/margins": 0.11104954779148102,
|
| 323 |
+
"rewards/rejected": -0.15108755230903625,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.927927927927928,
|
| 328 |
+
"grad_norm": 1.1332669258117676,
|
| 329 |
+
"learning_rate": 3.693606942594873e-06,
|
| 330 |
+
"logits/chosen": 1.8605678081512451,
|
| 331 |
+
"logits/rejected": 1.91280996799469,
|
| 332 |
+
"logps/chosen": -74.39783477783203,
|
| 333 |
+
"logps/rejected": -90.66893005371094,
|
| 334 |
+
"loss": 0.6565,
|
| 335 |
+
"rewards/accuracies": 0.637499988079071,
|
| 336 |
+
"rewards/chosen": -0.08056517690420151,
|
| 337 |
+
"rewards/margins": 0.0968993678689003,
|
| 338 |
+
"rewards/rejected": -0.1774645447731018,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.288288288288289,
|
| 343 |
+
"grad_norm": 1.0496221780776978,
|
| 344 |
+
"learning_rate": 3.549216974976073e-06,
|
| 345 |
+
"logits/chosen": 1.8636070489883423,
|
| 346 |
+
"logits/rejected": 1.7996151447296143,
|
| 347 |
+
"logps/chosen": -89.9018783569336,
|
| 348 |
+
"logps/rejected": -74.14125061035156,
|
| 349 |
+
"loss": 0.6423,
|
| 350 |
+
"rewards/accuracies": 0.6875,
|
| 351 |
+
"rewards/chosen": -0.05598217993974686,
|
| 352 |
+
"rewards/margins": 0.14807265996932983,
|
| 353 |
+
"rewards/rejected": -0.2040548026561737,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.64864864864865,
|
| 358 |
+
"grad_norm": 0.8506491780281067,
|
| 359 |
+
"learning_rate": 3.400444312011776e-06,
|
| 360 |
+
"logits/chosen": 1.7753232717514038,
|
| 361 |
+
"logits/rejected": 1.7647806406021118,
|
| 362 |
+
"logps/chosen": -88.50201416015625,
|
| 363 |
+
"logps/rejected": -81.80894470214844,
|
| 364 |
+
"loss": 0.6358,
|
| 365 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 366 |
+
"rewards/chosen": -0.09656485170125961,
|
| 367 |
+
"rewards/margins": 0.11554913222789764,
|
| 368 |
+
"rewards/rejected": -0.21211397647857666,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 9.00900900900901,
|
| 373 |
+
"grad_norm": 0.9554071426391602,
|
| 374 |
+
"learning_rate": 3.2479103935691047e-06,
|
| 375 |
+
"logits/chosen": 1.7528200149536133,
|
| 376 |
+
"logits/rejected": 1.7827808856964111,
|
| 377 |
+
"logps/chosen": -90.01268005371094,
|
| 378 |
+
"logps/rejected": -89.0714340209961,
|
| 379 |
+
"loss": 0.6374,
|
| 380 |
+
"rewards/accuracies": 0.675000011920929,
|
| 381 |
+
"rewards/chosen": -0.07412372529506683,
|
| 382 |
+
"rewards/margins": 0.1321595013141632,
|
| 383 |
+
"rewards/rejected": -0.20628324151039124,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.36936936936937,
|
| 388 |
+
"grad_norm": 0.9363342523574829,
|
| 389 |
+
"learning_rate": 3.092252370695298e-06,
|
| 390 |
+
"logits/chosen": 1.6990101337432861,
|
| 391 |
+
"logits/rejected": 1.8281656503677368,
|
| 392 |
+
"logps/chosen": -71.15428161621094,
|
| 393 |
+
"logps/rejected": -79.72063446044922,
|
| 394 |
+
"loss": 0.6303,
|
| 395 |
+
"rewards/accuracies": 0.762499988079071,
|
| 396 |
+
"rewards/chosen": -0.08240491151809692,
|
| 397 |
+
"rewards/margins": 0.16954098641872406,
|
| 398 |
+
"rewards/rejected": -0.2519459128379822,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.72972972972973,
|
| 403 |
+
"grad_norm": 1.023535966873169,
|
| 404 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 405 |
+
"logits/chosen": 1.7418006658554077,
|
| 406 |
+
"logits/rejected": 1.7500028610229492,
|
| 407 |
+
"logps/chosen": -82.24595642089844,
|
| 408 |
+
"logps/rejected": -91.16307067871094,
|
| 409 |
+
"loss": 0.6321,
|
| 410 |
+
"rewards/accuracies": 0.6875,
|
| 411 |
+
"rewards/chosen": -0.13560767471790314,
|
| 412 |
+
"rewards/margins": 0.1204828992486,
|
| 413 |
+
"rewards/rejected": -0.25609058141708374,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 10.09009009009009,
|
| 418 |
+
"grad_norm": 1.0393471717834473,
|
| 419 |
+
"learning_rate": 2.7741751485313295e-06,
|
| 420 |
+
"logits/chosen": 1.8437154293060303,
|
| 421 |
+
"logits/rejected": 1.8877627849578857,
|
| 422 |
+
"logps/chosen": -68.61182403564453,
|
| 423 |
+
"logps/rejected": -77.12557220458984,
|
| 424 |
+
"loss": 0.6109,
|
| 425 |
+
"rewards/accuracies": 0.737500011920929,
|
| 426 |
+
"rewards/chosen": -0.11025551706552505,
|
| 427 |
+
"rewards/margins": 0.14969798922538757,
|
| 428 |
+
"rewards/rejected": -0.25995349884033203,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 10.45045045045045,
|
| 433 |
+
"grad_norm": 0.9554691910743713,
|
| 434 |
+
"learning_rate": 2.6130845929767662e-06,
|
| 435 |
+
"logits/chosen": 1.7998764514923096,
|
| 436 |
+
"logits/rejected": 1.796451210975647,
|
| 437 |
+
"logps/chosen": -72.6626205444336,
|
| 438 |
+
"logps/rejected": -74.15937042236328,
|
| 439 |
+
"loss": 0.6123,
|
| 440 |
+
"rewards/accuracies": 0.737500011920929,
|
| 441 |
+
"rewards/chosen": -0.13948099315166473,
|
| 442 |
+
"rewards/margins": 0.18039894104003906,
|
| 443 |
+
"rewards/rejected": -0.319879949092865,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.81081081081081,
|
| 448 |
+
"grad_norm": 1.1667226552963257,
|
| 449 |
+
"learning_rate": 2.4515216705704396e-06,
|
| 450 |
+
"logits/chosen": 1.8437564373016357,
|
| 451 |
+
"logits/rejected": 1.9043811559677124,
|
| 452 |
+
"logps/chosen": -78.18916320800781,
|
| 453 |
+
"logps/rejected": -90.88524627685547,
|
| 454 |
+
"loss": 0.6218,
|
| 455 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 456 |
+
"rewards/chosen": -0.12091793864965439,
|
| 457 |
+
"rewards/margins": 0.20490169525146484,
|
| 458 |
+
"rewards/rejected": -0.32581964135169983,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 11.17117117117117,
|
| 463 |
+
"grad_norm": 1.2568660974502563,
|
| 464 |
+
"learning_rate": 2.290161247507733e-06,
|
| 465 |
+
"logits/chosen": 1.7295608520507812,
|
| 466 |
+
"logits/rejected": 1.8652616739273071,
|
| 467 |
+
"logps/chosen": -79.8567886352539,
|
| 468 |
+
"logps/rejected": -87.59798431396484,
|
| 469 |
+
"loss": 0.6067,
|
| 470 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 471 |
+
"rewards/chosen": -0.10961383581161499,
|
| 472 |
+
"rewards/margins": 0.2835196554660797,
|
| 473 |
+
"rewards/rejected": -0.3931335210800171,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 11.531531531531531,
|
| 478 |
+
"grad_norm": 1.115491271018982,
|
| 479 |
+
"learning_rate": 2.129677344121879e-06,
|
| 480 |
+
"logits/chosen": 1.803063988685608,
|
| 481 |
+
"logits/rejected": 1.820227861404419,
|
| 482 |
+
"logps/chosen": -74.64582061767578,
|
| 483 |
+
"logps/rejected": -72.14736938476562,
|
| 484 |
+
"loss": 0.6113,
|
| 485 |
+
"rewards/accuracies": 0.75,
|
| 486 |
+
"rewards/chosen": -0.09987158328294754,
|
| 487 |
+
"rewards/margins": 0.2059938907623291,
|
| 488 |
+
"rewards/rejected": -0.30586546659469604,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.891891891891891,
|
| 493 |
+
"grad_norm": 0.9227492213249207,
|
| 494 |
+
"learning_rate": 1.970740319426474e-06,
|
| 495 |
+
"logits/chosen": 1.7561572790145874,
|
| 496 |
+
"logits/rejected": 1.789878249168396,
|
| 497 |
+
"logps/chosen": -85.27911376953125,
|
| 498 |
+
"logps/rejected": -77.4220962524414,
|
| 499 |
+
"loss": 0.5891,
|
| 500 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 501 |
+
"rewards/chosen": -0.14200571179389954,
|
| 502 |
+
"rewards/margins": 0.22272682189941406,
|
| 503 |
+
"rewards/rejected": -0.3647325336933136,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 12.252252252252251,
|
| 508 |
+
"grad_norm": 1.541570782661438,
|
| 509 |
+
"learning_rate": 1.8140140709517467e-06,
|
| 510 |
+
"logits/chosen": 1.7364771366119385,
|
| 511 |
+
"logits/rejected": 1.7182557582855225,
|
| 512 |
+
"logps/chosen": -76.05533599853516,
|
| 513 |
+
"logps/rejected": -81.50830078125,
|
| 514 |
+
"loss": 0.5994,
|
| 515 |
+
"rewards/accuracies": 0.75,
|
| 516 |
+
"rewards/chosen": -0.12165775150060654,
|
| 517 |
+
"rewards/margins": 0.19019995629787445,
|
| 518 |
+
"rewards/rejected": -0.3118577301502228,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 12.612612612612612,
|
| 523 |
+
"grad_norm": 1.1125155687332153,
|
| 524 |
+
"learning_rate": 1.6601532615711452e-06,
|
| 525 |
+
"logits/chosen": 1.7223026752471924,
|
| 526 |
+
"logits/rejected": 1.8163812160491943,
|
| 527 |
+
"logps/chosen": -71.94869232177734,
|
| 528 |
+
"logps/rejected": -90.12442016601562,
|
| 529 |
+
"loss": 0.6013,
|
| 530 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 531 |
+
"rewards/chosen": -0.16840626299381256,
|
| 532 |
+
"rewards/margins": 0.1776614487171173,
|
| 533 |
+
"rewards/rejected": -0.3460676968097687,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 12.972972972972974,
|
| 538 |
+
"grad_norm": 1.0530396699905396,
|
| 539 |
+
"learning_rate": 1.509800584902108e-06,
|
| 540 |
+
"logits/chosen": 1.795819878578186,
|
| 541 |
+
"logits/rejected": 1.8446025848388672,
|
| 542 |
+
"logps/chosen": -82.24161529541016,
|
| 543 |
+
"logps/rejected": -79.51258850097656,
|
| 544 |
+
"loss": 0.5857,
|
| 545 |
+
"rewards/accuracies": 0.800000011920929,
|
| 546 |
+
"rewards/chosen": -0.13156726956367493,
|
| 547 |
+
"rewards/margins": 0.2468404471874237,
|
| 548 |
+
"rewards/rejected": -0.37840771675109863,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 13.333333333333334,
|
| 553 |
+
"grad_norm": 1.0298306941986084,
|
| 554 |
+
"learning_rate": 1.3635840807037487e-06,
|
| 555 |
+
"logits/chosen": 1.8054157495498657,
|
| 556 |
+
"logits/rejected": 1.8246568441390991,
|
| 557 |
+
"logps/chosen": -85.40760803222656,
|
| 558 |
+
"logps/rejected": -78.77482604980469,
|
| 559 |
+
"loss": 0.5943,
|
| 560 |
+
"rewards/accuracies": 0.762499988079071,
|
| 561 |
+
"rewards/chosen": -0.10383795201778412,
|
| 562 |
+
"rewards/margins": 0.2493254393339157,
|
| 563 |
+
"rewards/rejected": -0.35316339135169983,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 13.693693693693694,
|
| 568 |
+
"grad_norm": 1.0601342916488647,
|
| 569 |
+
"learning_rate": 1.2221145114853172e-06,
|
| 570 |
+
"logits/chosen": 1.6507200002670288,
|
| 571 |
+
"logits/rejected": 1.720569372177124,
|
| 572 |
+
"logps/chosen": -74.90982055664062,
|
| 573 |
+
"logps/rejected": -92.51995849609375,
|
| 574 |
+
"loss": 0.5789,
|
| 575 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 576 |
+
"rewards/chosen": -0.13705268502235413,
|
| 577 |
+
"rewards/margins": 0.2740176022052765,
|
| 578 |
+
"rewards/rejected": -0.4110702872276306,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 14.054054054054054,
|
| 583 |
+
"grad_norm": 1.1135063171386719,
|
| 584 |
+
"learning_rate": 1.085982811283654e-06,
|
| 585 |
+
"logits/chosen": 1.7133989334106445,
|
| 586 |
+
"logits/rejected": 1.7338130474090576,
|
| 587 |
+
"logps/chosen": -80.55327606201172,
|
| 588 |
+
"logps/rejected": -82.32875061035156,
|
| 589 |
+
"loss": 0.5847,
|
| 590 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 591 |
+
"rewards/chosen": -0.12969203293323517,
|
| 592 |
+
"rewards/margins": 0.26957422494888306,
|
| 593 |
+
"rewards/rejected": -0.39926621317863464,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 14.414414414414415,
|
| 598 |
+
"grad_norm": 1.0821375846862793,
|
| 599 |
+
"learning_rate": 9.557576172663577e-07,
|
| 600 |
+
"logits/chosen": 1.7035369873046875,
|
| 601 |
+
"logits/rejected": 1.7184028625488281,
|
| 602 |
+
"logps/chosen": -80.99266052246094,
|
| 603 |
+
"logps/rejected": -85.05413818359375,
|
| 604 |
+
"loss": 0.583,
|
| 605 |
+
"rewards/accuracies": 0.824999988079071,
|
| 606 |
+
"rewards/chosen": -0.1366995871067047,
|
| 607 |
+
"rewards/margins": 0.268393874168396,
|
| 608 |
+
"rewards/rejected": -0.4050934910774231,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 14.774774774774775,
|
| 613 |
+
"grad_norm": 1.1167497634887695,
|
| 614 |
+
"learning_rate": 8.319828944714508e-07,
|
| 615 |
+
"logits/chosen": 1.8293631076812744,
|
| 616 |
+
"logits/rejected": 1.7202396392822266,
|
| 617 |
+
"logps/chosen": -96.96324157714844,
|
| 618 |
+
"logps/rejected": -80.58685302734375,
|
| 619 |
+
"loss": 0.5768,
|
| 620 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 621 |
+
"rewards/chosen": -0.14515718817710876,
|
| 622 |
+
"rewards/margins": 0.27918386459350586,
|
| 623 |
+
"rewards/rejected": -0.4243410527706146,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 15.135135135135135,
|
| 628 |
+
"grad_norm": 1.0140223503112793,
|
| 629 |
+
"learning_rate": 7.151756636052529e-07,
|
| 630 |
+
"logits/chosen": 1.7751014232635498,
|
| 631 |
+
"logits/rejected": 1.7394100427627563,
|
| 632 |
+
"logps/chosen": -104.48625183105469,
|
| 633 |
+
"logps/rejected": -90.3105239868164,
|
| 634 |
+
"loss": 0.5804,
|
| 635 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 636 |
+
"rewards/chosen": -0.14849844574928284,
|
| 637 |
+
"rewards/margins": 0.2261633574962616,
|
| 638 |
+
"rewards/rejected": -0.37466174364089966,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 15.495495495495495,
|
| 643 |
+
"grad_norm": 1.0056337118148804,
|
| 644 |
+
"learning_rate": 6.058238413897052e-07,
|
| 645 |
+
"logits/chosen": 1.7368510961532593,
|
| 646 |
+
"logits/rejected": 1.844665288925171,
|
| 647 |
+
"logps/chosen": -88.00404357910156,
|
| 648 |
+
"logps/rejected": -103.71427917480469,
|
| 649 |
+
"loss": 0.5786,
|
| 650 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 651 |
+
"rewards/chosen": -0.2264096438884735,
|
| 652 |
+
"rewards/margins": 0.2332192212343216,
|
| 653 |
+
"rewards/rejected": -0.4596289098262787,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 15.855855855855856,
|
| 658 |
+
"grad_norm": 1.0402743816375732,
|
| 659 |
+
"learning_rate": 5.043842024802675e-07,
|
| 660 |
+
"logits/chosen": 1.835862398147583,
|
| 661 |
+
"logits/rejected": 1.8621985912322998,
|
| 662 |
+
"logps/chosen": -80.8730697631836,
|
| 663 |
+
"logps/rejected": -77.32243347167969,
|
| 664 |
+
"loss": 0.5737,
|
| 665 |
+
"rewards/accuracies": 0.762499988079071,
|
| 666 |
+
"rewards/chosen": -0.10934928804636002,
|
| 667 |
+
"rewards/margins": 0.26070791482925415,
|
| 668 |
+
"rewards/rejected": -0.3700571656227112,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 16.216216216216218,
|
| 673 |
+
"grad_norm": 1.0037925243377686,
|
| 674 |
+
"learning_rate": 4.1128047146765936e-07,
|
| 675 |
+
"logits/chosen": 1.6536343097686768,
|
| 676 |
+
"logits/rejected": 1.748152494430542,
|
| 677 |
+
"logps/chosen": -85.28504180908203,
|
| 678 |
+
"logps/rejected": -83.04313659667969,
|
| 679 |
+
"loss": 0.5869,
|
| 680 |
+
"rewards/accuracies": 0.8125,
|
| 681 |
+
"rewards/chosen": -0.1468530297279358,
|
| 682 |
+
"rewards/margins": 0.24461284279823303,
|
| 683 |
+
"rewards/rejected": -0.39146584272384644,
|
| 684 |
+
"step": 450
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 16.576576576576578,
|
| 688 |
+
"grad_norm": 1.0473060607910156,
|
| 689 |
+
"learning_rate": 3.269015529333805e-07,
|
| 690 |
+
"logits/chosen": 1.7145726680755615,
|
| 691 |
+
"logits/rejected": 1.7245705127716064,
|
| 692 |
+
"logps/chosen": -68.06051635742188,
|
| 693 |
+
"logps/rejected": -77.09696960449219,
|
| 694 |
+
"loss": 0.5679,
|
| 695 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 696 |
+
"rewards/chosen": -0.16770952939987183,
|
| 697 |
+
"rewards/margins": 0.23443298041820526,
|
| 698 |
+
"rewards/rejected": -0.4021424651145935,
|
| 699 |
+
"step": 460
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 16.936936936936938,
|
| 703 |
+
"grad_norm": 1.0985324382781982,
|
| 704 |
+
"learning_rate": 2.515999069522676e-07,
|
| 705 |
+
"logits/chosen": 1.7093912363052368,
|
| 706 |
+
"logits/rejected": 1.6903793811798096,
|
| 707 |
+
"logps/chosen": -79.38801574707031,
|
| 708 |
+
"logps/rejected": -74.43864440917969,
|
| 709 |
+
"loss": 0.5754,
|
| 710 |
+
"rewards/accuracies": 0.8125,
|
| 711 |
+
"rewards/chosen": -0.14471781253814697,
|
| 712 |
+
"rewards/margins": 0.24466648697853088,
|
| 713 |
+
"rewards/rejected": -0.38938429951667786,
|
| 714 |
+
"step": 470
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 17.2972972972973,
|
| 718 |
+
"grad_norm": 1.1457403898239136,
|
| 719 |
+
"learning_rate": 1.8569007682777417e-07,
|
| 720 |
+
"logits/chosen": 1.6642320156097412,
|
| 721 |
+
"logits/rejected": 1.7295513153076172,
|
| 722 |
+
"logps/chosen": -80.79732513427734,
|
| 723 |
+
"logps/rejected": -80.07367706298828,
|
| 724 |
+
"loss": 0.5749,
|
| 725 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 726 |
+
"rewards/chosen": -0.16041259467601776,
|
| 727 |
+
"rewards/margins": 0.26678892970085144,
|
| 728 |
+
"rewards/rejected": -0.4272015690803528,
|
| 729 |
+
"step": 480
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 17.65765765765766,
|
| 733 |
+
"grad_norm": 1.04747474193573,
|
| 734 |
+
"learning_rate": 1.2944737520980883e-07,
|
| 735 |
+
"logits/chosen": 1.699061632156372,
|
| 736 |
+
"logits/rejected": 1.837684988975525,
|
| 737 |
+
"logps/chosen": -73.55027770996094,
|
| 738 |
+
"logps/rejected": -93.25712585449219,
|
| 739 |
+
"loss": 0.5732,
|
| 740 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 741 |
+
"rewards/chosen": -0.20150330662727356,
|
| 742 |
+
"rewards/margins": 0.2376147210597992,
|
| 743 |
+
"rewards/rejected": -0.43911799788475037,
|
| 744 |
+
"step": 490
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 18.01801801801802,
|
| 748 |
+
"grad_norm": 1.033074140548706,
|
| 749 |
+
"learning_rate": 8.310673408334496e-08,
|
| 750 |
+
"logits/chosen": 1.655987024307251,
|
| 751 |
+
"logits/rejected": 1.6537258625030518,
|
| 752 |
+
"logps/chosen": -103.11566162109375,
|
| 753 |
+
"logps/rejected": -96.29421997070312,
|
| 754 |
+
"loss": 0.5747,
|
| 755 |
+
"rewards/accuracies": 0.800000011920929,
|
| 756 |
+
"rewards/chosen": -0.15963700413703918,
|
| 757 |
+
"rewards/margins": 0.30574050545692444,
|
| 758 |
+
"rewards/rejected": -0.4653775095939636,
|
| 759 |
+
"step": 500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 18.37837837837838,
|
| 763 |
+
"grad_norm": 1.0928398370742798,
|
| 764 |
+
"learning_rate": 4.6861723431538273e-08,
|
| 765 |
+
"logits/chosen": 1.7491756677627563,
|
| 766 |
+
"logits/rejected": 1.7941337823867798,
|
| 767 |
+
"logps/chosen": -79.0124282836914,
|
| 768 |
+
"logps/rejected": -94.39396667480469,
|
| 769 |
+
"loss": 0.5745,
|
| 770 |
+
"rewards/accuracies": 0.824999988079071,
|
| 771 |
+
"rewards/chosen": -0.14681483805179596,
|
| 772 |
+
"rewards/margins": 0.31730785965919495,
|
| 773 |
+
"rewards/rejected": -0.4641226828098297,
|
| 774 |
+
"step": 510
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 18.73873873873874,
|
| 778 |
+
"grad_norm": 1.0533796548843384,
|
| 779 |
+
"learning_rate": 2.0863742672497244e-08,
|
| 780 |
+
"logits/chosen": 1.7281211614608765,
|
| 781 |
+
"logits/rejected": 1.7764543294906616,
|
| 782 |
+
"logps/chosen": -91.92194366455078,
|
| 783 |
+
"logps/rejected": -85.10621643066406,
|
| 784 |
+
"loss": 0.5726,
|
| 785 |
+
"rewards/accuracies": 0.824999988079071,
|
| 786 |
+
"rewards/chosen": -0.15819533169269562,
|
| 787 |
+
"rewards/margins": 0.2960740923881531,
|
| 788 |
+
"rewards/rejected": -0.4542694687843323,
|
| 789 |
+
"step": 520
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 19.0990990990991,
|
| 793 |
+
"grad_norm": 1.1859172582626343,
|
| 794 |
+
"learning_rate": 5.221388247169945e-09,
|
| 795 |
+
"logits/chosen": 1.7769553661346436,
|
| 796 |
+
"logits/rejected": 1.7326488494873047,
|
| 797 |
+
"logps/chosen": -85.6234359741211,
|
| 798 |
+
"logps/rejected": -75.64092254638672,
|
| 799 |
+
"loss": 0.5688,
|
| 800 |
+
"rewards/accuracies": 0.875,
|
| 801 |
+
"rewards/chosen": -0.15740445256233215,
|
| 802 |
+
"rewards/margins": 0.31495219469070435,
|
| 803 |
+
"rewards/rejected": -0.4723566472530365,
|
| 804 |
+
"step": 530
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 19.45945945945946,
|
| 808 |
+
"grad_norm": 1.1295475959777832,
|
| 809 |
+
"learning_rate": 0.0,
|
| 810 |
+
"logits/chosen": 1.7790734767913818,
|
| 811 |
+
"logits/rejected": 1.8196531534194946,
|
| 812 |
+
"logps/chosen": -83.07762145996094,
|
| 813 |
+
"logps/rejected": -77.76747131347656,
|
| 814 |
+
"loss": 0.575,
|
| 815 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 816 |
+
"rewards/chosen": -0.1493213176727295,
|
| 817 |
+
"rewards/margins": 0.2750301659107208,
|
| 818 |
+
"rewards/rejected": -0.42435145378112793,
|
| 819 |
+
"step": 540
|
| 820 |
+
}
|
| 821 |
+
],
|
| 822 |
+
"logging_steps": 10,
|
| 823 |
+
"max_steps": 540,
|
| 824 |
+
"num_input_tokens_seen": 0,
|
| 825 |
+
"num_train_epochs": 20,
|
| 826 |
+
"save_steps": 50,
|
| 827 |
+
"stateful_callbacks": {
|
| 828 |
+
"TrainerControl": {
|
| 829 |
+
"args": {
|
| 830 |
+
"should_epoch_stop": false,
|
| 831 |
+
"should_evaluate": false,
|
| 832 |
+
"should_log": false,
|
| 833 |
+
"should_save": true,
|
| 834 |
+
"should_training_stop": true
|
| 835 |
+
},
|
| 836 |
+
"attributes": {}
|
| 837 |
+
}
|
| 838 |
+
},
|
| 839 |
+
"total_flos": 1.8293058049230766e+18,
|
| 840 |
+
"train_batch_size": 1,
|
| 841 |
+
"trial_name": null,
|
| 842 |
+
"trial_params": null
|
| 843 |
+
}
|
Power/checkpoint-350/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74fb78160963fed1906f069b9ed731049119080b95d6940b930e07be49dc29f2
|
| 3 |
+
size 80013120
|
Power_Area_Time/README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: other
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Power_Area_Time
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Power_Area_Time
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) on the power_area_time dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-06
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 64
|
| 46 |
+
- total_eval_batch_size: 64
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 20.0
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- PEFT 0.12.0
|
| 59 |
+
- Transformers 4.45.2
|
| 60 |
+
- Pytorch 2.4.1+cu124
|
| 61 |
+
- Datasets 2.21.0
|
| 62 |
+
- Tokenizers 0.20.0
|
Power_Area_Time/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Area_Time/all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 1.9591809237023457e+18,
|
| 4 |
+
"train_loss": 0.613731259313123,
|
| 5 |
+
"train_runtime": 4229.7108,
|
| 6 |
+
"train_samples_per_second": 8.752,
|
| 7 |
+
"train_steps_per_second": 0.137
|
| 8 |
+
}
|
Power_Area_Time/checkpoint-100/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|