Upload checkpoint 180
Browse files- README.md +3 -3
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +302 -2
README.md
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
base_model: smirki/UIGEN-T1.1-Qwen-7B
|
3 |
library_name: peft
|
4 |
---
|
5 |
-
# UIGEN T1.2 7B GRPO (Step
|
6 |
|
7 |
> [!NOTE]
|
8 |
> Training in progress...
|
@@ -38,10 +38,10 @@ library_name: peft
|
|
38 |
</head>
|
39 |
<body>
|
40 |
<div style="width: 100%; background-color: #e0e0e0; border-radius: 25px; overflow: hidden; margin: 20px 0;">
|
41 |
-
<div style="height: 30px; width:
|
42 |
<!-- 3.75% -->
|
43 |
</div>
|
44 |
</div>
|
45 |
-
<p style="font-family: Arial, sans-serif; font-size: 16px;">Progress:
|
46 |
</body>
|
47 |
</html>
|
|
|
2 |
base_model: smirki/UIGEN-T1.1-Qwen-7B
|
3 |
library_name: peft
|
4 |
---
|
5 |
+
# UIGEN T1.2 7B GRPO (Step 180 Checkpoint)
|
6 |
|
7 |
> [!NOTE]
|
8 |
> Training in progress...
|
|
|
38 |
</head>
|
39 |
<body>
|
40 |
<div style="width: 100%; background-color: #e0e0e0; border-radius: 25px; overflow: hidden; margin: 20px 0;">
|
41 |
+
<div style="height: 30px; width: 22.50%; background-color: #76c7c0; text-align: center; line-height: 30px; color: white; border-radius: 25px 0 0 25px;">
|
42 |
<!-- 3.75% -->
|
43 |
</div>
|
44 |
</div>
|
45 |
+
<p style="font-family: Arial, sans-serif; font-size: 16px;">Progress: 180 out of 800 steps</p>
|
46 |
</body>
|
47 |
</html>
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 645975704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26409fc7545df1dd97aa4a6b2aa4da74ce151a1ba41a908151457173d9b9885a
|
3 |
size 645975704
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 329488130
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e31453e015fccb32b129bd26df8d8cdcc4589413dbb7498275a0dd7daae5955c
|
3 |
size 329488130
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0dde09f21833f8e39dfb8efa755afcbb9c8ed4069c02ca59f28eb52aa4c00b0
|
3 |
size 14244
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d99a469e15218772b7fadd81f497d527d3940f8e386b540e234b9e7acb293ae9
|
3 |
size 1064
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -5107,6 +5107,306 @@
|
|
5107 |
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5108 |
"rewards/visual_hierarchy_reward_func": 0.05006365571171045,
|
5109 |
"step": 170
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5110 |
}
|
5111 |
],
|
5112 |
"logging_steps": 1,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9314359637774903,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 180,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
5107 |
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5108 |
"rewards/visual_hierarchy_reward_func": 0.05006365571171045,
|
5109 |
"step": 170
|
5110 |
+
},
|
5111 |
+
{
|
5112 |
+
"completion_length": 5394.0,
|
5113 |
+
"epoch": 0.8848641655886158,
|
5114 |
+
"grad_norm": 0.09889987856149673,
|
5115 |
+
"kl": 0.003882193996105343,
|
5116 |
+
"learning_rate": 4.930924800994192e-06,
|
5117 |
+
"loss": 0.0002,
|
5118 |
+
"reward": 4.174183368682861,
|
5119 |
+
"reward_std": 0.6262644361704588,
|
5120 |
+
"rewards/accessibility_reward_func": 0.3920000195503235,
|
5121 |
+
"rewards/animation_reward_func": 0.30799999460577965,
|
5122 |
+
"rewards/color_theory_reward_func": 0.3424166738986969,
|
5123 |
+
"rewards/design_system_reward_func": 0.9583333432674408,
|
5124 |
+
"rewards/element_spacing_reward_func": 0.1588766798377037,
|
5125 |
+
"rewards/enhanced_html_validity_reward_func": 0.08616667240858078,
|
5126 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8487500250339508,
|
5127 |
+
"rewards/general_responsiveness_reward_func": 0.05375000089406967,
|
5128 |
+
"rewards/hover_reward_func": 0.17250000685453415,
|
5129 |
+
"rewards/image_size_reward_func": 0.054375000298023224,
|
5130 |
+
"rewards/interactivity_reward_func": 0.5740000009536743,
|
5131 |
+
"rewards/link_validity_reward_func": 0.0372500023804605,
|
5132 |
+
"rewards/lorem_picsum_reward_func": 0.004458333365619183,
|
5133 |
+
"rewards/mobile_responsiveness_reward_func": 0.0020000000949949026,
|
5134 |
+
"rewards/section_size_reward_func": 0.0,
|
5135 |
+
"rewards/tailwind_cdn_reward_func": 0.06416666693985462,
|
5136 |
+
"rewards/text_contrast_reward_func": 0.01916666654869914,
|
5137 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5138 |
+
"rewards/visual_hierarchy_reward_func": 0.05797312594950199,
|
5139 |
+
"step": 171
|
5140 |
+
},
|
5141 |
+
{
|
5142 |
+
"completion_length": 5646.0001220703125,
|
5143 |
+
"epoch": 0.890038809831824,
|
5144 |
+
"grad_norm": 0.11238585412502289,
|
5145 |
+
"kl": 0.003986692405305803,
|
5146 |
+
"learning_rate": 4.928202579790285e-06,
|
5147 |
+
"loss": 0.0002,
|
5148 |
+
"reward": 3.9328404664993286,
|
5149 |
+
"reward_std": 0.7754750922322273,
|
5150 |
+
"rewards/accessibility_reward_func": 0.32200001180171967,
|
5151 |
+
"rewards/animation_reward_func": 0.3193333335220814,
|
5152 |
+
"rewards/color_theory_reward_func": 0.28291667625308037,
|
5153 |
+
"rewards/design_system_reward_func": 0.9166666716337204,
|
5154 |
+
"rewards/element_spacing_reward_func": 0.15673686936497688,
|
5155 |
+
"rewards/enhanced_html_validity_reward_func": 0.0860000029206276,
|
5156 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.798750028014183,
|
5157 |
+
"rewards/general_responsiveness_reward_func": 0.0537499999627471,
|
5158 |
+
"rewards/hover_reward_func": 0.16500000655651093,
|
5159 |
+
"rewards/image_size_reward_func": 0.060125005431473255,
|
5160 |
+
"rewards/interactivity_reward_func": 0.5500000268220901,
|
5161 |
+
"rewards/link_validity_reward_func": 0.03875000076368451,
|
5162 |
+
"rewards/lorem_picsum_reward_func": 0.004291666555218399,
|
5163 |
+
"rewards/mobile_responsiveness_reward_func": 0.010666667600162327,
|
5164 |
+
"rewards/section_size_reward_func": 0.0011666667414829135,
|
5165 |
+
"rewards/tailwind_cdn_reward_func": 0.06125000026077032,
|
5166 |
+
"rewards/text_contrast_reward_func": 0.01749999902676791,
|
5167 |
+
"rewards/think_tag_reward_func": 0.033333332277834415,
|
5168 |
+
"rewards/visual_hierarchy_reward_func": 0.054603368043899536,
|
5169 |
+
"step": 172
|
5170 |
+
},
|
5171 |
+
{
|
5172 |
+
"completion_length": 5726.08349609375,
|
5173 |
+
"epoch": 0.8952134540750324,
|
5174 |
+
"grad_norm": 0.09589073061943054,
|
5175 |
+
"kl": 0.0036144027253612876,
|
5176 |
+
"learning_rate": 4.925428530393815e-06,
|
5177 |
+
"loss": 0.0001,
|
5178 |
+
"reward": 4.226910829544067,
|
5179 |
+
"reward_std": 0.23560119047760963,
|
5180 |
+
"rewards/accessibility_reward_func": 0.30916667357087135,
|
5181 |
+
"rewards/animation_reward_func": 0.3489999994635582,
|
5182 |
+
"rewards/color_theory_reward_func": 0.2992500066757202,
|
5183 |
+
"rewards/design_system_reward_func": 1.0,
|
5184 |
+
"rewards/element_spacing_reward_func": 0.16949399933218956,
|
5185 |
+
"rewards/enhanced_html_validity_reward_func": 0.08841666765511036,
|
5186 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.867500051856041,
|
5187 |
+
"rewards/general_responsiveness_reward_func": 0.06075000111013651,
|
5188 |
+
"rewards/hover_reward_func": 0.18000000715255737,
|
5189 |
+
"rewards/image_size_reward_func": 0.04937500227242708,
|
5190 |
+
"rewards/interactivity_reward_func": 0.6000000238418579,
|
5191 |
+
"rewards/link_validity_reward_func": 0.04462500102818012,
|
5192 |
+
"rewards/lorem_picsum_reward_func": 0.003750000090803951,
|
5193 |
+
"rewards/mobile_responsiveness_reward_func": 0.012000000569969416,
|
5194 |
+
"rewards/section_size_reward_func": 0.0,
|
5195 |
+
"rewards/tailwind_cdn_reward_func": 0.06708333361893892,
|
5196 |
+
"rewards/text_contrast_reward_func": 0.020833332557231188,
|
5197 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5198 |
+
"rewards/visual_hierarchy_reward_func": 0.06566663645207882,
|
5199 |
+
"step": 173
|
5200 |
+
},
|
5201 |
+
{
|
5202 |
+
"completion_length": 5261.2501220703125,
|
5203 |
+
"epoch": 0.9003880983182406,
|
5204 |
+
"grad_norm": 0.09748656302690506,
|
5205 |
+
"kl": 0.004026910872198641,
|
5206 |
+
"learning_rate": 4.9226027120148195e-06,
|
5207 |
+
"loss": 0.0002,
|
5208 |
+
"reward": 4.045217156410217,
|
5209 |
+
"reward_std": 0.47231714613735676,
|
5210 |
+
"rewards/accessibility_reward_func": 0.3400833532214165,
|
5211 |
+
"rewards/animation_reward_func": 0.3216666728258133,
|
5212 |
+
"rewards/color_theory_reward_func": 0.294000007212162,
|
5213 |
+
"rewards/design_system_reward_func": 0.9583333432674408,
|
5214 |
+
"rewards/element_spacing_reward_func": 0.1636057049036026,
|
5215 |
+
"rewards/enhanced_html_validity_reward_func": 0.08841667138040066,
|
5216 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.7787500396370888,
|
5217 |
+
"rewards/general_responsiveness_reward_func": 0.06225000228732824,
|
5218 |
+
"rewards/hover_reward_func": 0.17100000753998756,
|
5219 |
+
"rewards/image_size_reward_func": 0.05887500289827585,
|
5220 |
+
"rewards/interactivity_reward_func": 0.5750000178813934,
|
5221 |
+
"rewards/link_validity_reward_func": 0.03600000170990825,
|
5222 |
+
"rewards/lorem_picsum_reward_func": 0.004208333266433328,
|
5223 |
+
"rewards/mobile_responsiveness_reward_func": 0.008000000438187271,
|
5224 |
+
"rewards/section_size_reward_func": 0.0,
|
5225 |
+
"rewards/tailwind_cdn_reward_func": 0.06708333361893892,
|
5226 |
+
"rewards/text_contrast_reward_func": 0.015000000246800482,
|
5227 |
+
"rewards/think_tag_reward_func": 0.038333332166075706,
|
5228 |
+
"rewards/visual_hierarchy_reward_func": 0.06461138278245926,
|
5229 |
+
"step": 174
|
5230 |
+
},
|
5231 |
+
{
|
5232 |
+
"completion_length": 5887.08349609375,
|
5233 |
+
"epoch": 0.9055627425614489,
|
5234 |
+
"grad_norm": 0.1503657102584839,
|
5235 |
+
"kl": 0.00428128446219489,
|
5236 |
+
"learning_rate": 4.919725184968307e-06,
|
5237 |
+
"loss": 0.0002,
|
5238 |
+
"reward": 4.075552523136139,
|
5239 |
+
"reward_std": 0.5442621223628521,
|
5240 |
+
"rewards/accessibility_reward_func": 0.2940000109374523,
|
5241 |
+
"rewards/animation_reward_func": 0.32766667008399963,
|
5242 |
+
"rewards/color_theory_reward_func": 0.30391666293144226,
|
5243 |
+
"rewards/design_system_reward_func": 0.9583333432674408,
|
5244 |
+
"rewards/element_spacing_reward_func": 0.1572103016078472,
|
5245 |
+
"rewards/enhanced_html_validity_reward_func": 0.08700000308454037,
|
5246 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8475000411272049,
|
5247 |
+
"rewards/general_responsiveness_reward_func": 0.05299999937415123,
|
5248 |
+
"rewards/hover_reward_func": 0.17250000685453415,
|
5249 |
+
"rewards/image_size_reward_func": 0.05487500177696347,
|
5250 |
+
"rewards/interactivity_reward_func": 0.5750000178813934,
|
5251 |
+
"rewards/link_validity_reward_func": 0.0448750015348196,
|
5252 |
+
"rewards/lorem_picsum_reward_func": 0.003958333341870457,
|
5253 |
+
"rewards/mobile_responsiveness_reward_func": 0.004000000131782144,
|
5254 |
+
"rewards/section_size_reward_func": 0.0,
|
5255 |
+
"rewards/tailwind_cdn_reward_func": 0.06708333361893892,
|
5256 |
+
"rewards/text_contrast_reward_func": 0.025833331514149904,
|
5257 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5258 |
+
"rewards/visual_hierarchy_reward_func": 0.058800602331757545,
|
5259 |
+
"step": 175
|
5260 |
+
},
|
5261 |
+
{
|
5262 |
+
"completion_length": 5057.541748046875,
|
5263 |
+
"epoch": 0.9107373868046572,
|
5264 |
+
"grad_norm": 0.09359525144100189,
|
5265 |
+
"kl": 0.004141130950301886,
|
5266 |
+
"learning_rate": 4.916796010672969e-06,
|
5267 |
+
"loss": 0.0002,
|
5268 |
+
"reward": 4.123052597045898,
|
5269 |
+
"reward_std": 0.18103181943297386,
|
5270 |
+
"rewards/accessibility_reward_func": 0.23100000619888306,
|
5271 |
+
"rewards/animation_reward_func": 0.33899998664855957,
|
5272 |
+
"rewards/color_theory_reward_func": 0.3511666804552078,
|
5273 |
+
"rewards/design_system_reward_func": 1.0,
|
5274 |
+
"rewards/element_spacing_reward_func": 0.1697884202003479,
|
5275 |
+
"rewards/enhanced_html_validity_reward_func": 0.08741667121648788,
|
5276 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8087500333786011,
|
5277 |
+
"rewards/general_responsiveness_reward_func": 0.0637500025331974,
|
5278 |
+
"rewards/hover_reward_func": 0.18000000715255737,
|
5279 |
+
"rewards/image_size_reward_func": 0.05262500001117587,
|
5280 |
+
"rewards/interactivity_reward_func": 0.6000000238418579,
|
5281 |
+
"rewards/link_validity_reward_func": 0.04225000087171793,
|
5282 |
+
"rewards/lorem_picsum_reward_func": 0.003874999994877726,
|
5283 |
+
"rewards/mobile_responsiveness_reward_func": 0.0020000001532025635,
|
5284 |
+
"rewards/section_size_reward_func": 0.0011666667414829135,
|
5285 |
+
"rewards/tailwind_cdn_reward_func": 0.06708333361893892,
|
5286 |
+
"rewards/text_contrast_reward_func": 0.02249999949708581,
|
5287 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5288 |
+
"rewards/visual_hierarchy_reward_func": 0.06068058591336012,
|
5289 |
+
"step": 176
|
5290 |
+
},
|
5291 |
+
{
|
5292 |
+
"completion_length": 5363.625244140625,
|
5293 |
+
"epoch": 0.9159120310478654,
|
5294 |
+
"grad_norm": 0.09246963262557983,
|
5295 |
+
"kl": 0.00423932250123471,
|
5296 |
+
"learning_rate": 4.913815251649871e-06,
|
5297 |
+
"loss": 0.0002,
|
5298 |
+
"reward": 4.37037193775177,
|
5299 |
+
"reward_std": 0.18096685782074928,
|
5300 |
+
"rewards/accessibility_reward_func": 0.40133335441350937,
|
5301 |
+
"rewards/animation_reward_func": 0.33766666054725647,
|
5302 |
+
"rewards/color_theory_reward_func": 0.35233333706855774,
|
5303 |
+
"rewards/design_system_reward_func": 1.0,
|
5304 |
+
"rewards/element_spacing_reward_func": 0.16700442135334015,
|
5305 |
+
"rewards/enhanced_html_validity_reward_func": 0.0899166688323021,
|
5306 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8825000524520874,
|
5307 |
+
"rewards/general_responsiveness_reward_func": 0.0559999980032444,
|
5308 |
+
"rewards/hover_reward_func": 0.18000000715255737,
|
5309 |
+
"rewards/image_size_reward_func": 0.061625005677342415,
|
5310 |
+
"rewards/interactivity_reward_func": 0.6000000238418579,
|
5311 |
+
"rewards/link_validity_reward_func": 0.04824999999254942,
|
5312 |
+
"rewards/lorem_picsum_reward_func": 0.004833333310671151,
|
5313 |
+
"rewards/mobile_responsiveness_reward_func": 0.003333333588670939,
|
5314 |
+
"rewards/section_size_reward_func": 0.0,
|
5315 |
+
"rewards/tailwind_cdn_reward_func": 0.06708333361893892,
|
5316 |
+
"rewards/text_contrast_reward_func": 0.019999999552965164,
|
5317 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5318 |
+
"rewards/visual_hierarchy_reward_func": 0.05849242024123669,
|
5319 |
+
"step": 177
|
5320 |
+
},
|
5321 |
+
{
|
5322 |
+
"completion_length": 5246.70849609375,
|
5323 |
+
"epoch": 0.9210866752910737,
|
5324 |
+
"grad_norm": 0.11369979381561279,
|
5325 |
+
"kl": 0.004419789183884859,
|
5326 |
+
"learning_rate": 4.910782971521112e-06,
|
5327 |
+
"loss": 0.0002,
|
5328 |
+
"reward": 3.9619848132133484,
|
5329 |
+
"reward_std": 0.33289995416998863,
|
5330 |
+
"rewards/accessibility_reward_func": 0.18958332668989897,
|
5331 |
+
"rewards/animation_reward_func": 0.31033332645893097,
|
5332 |
+
"rewards/color_theory_reward_func": 0.32725001126527786,
|
5333 |
+
"rewards/design_system_reward_func": 1.0,
|
5334 |
+
"rewards/element_spacing_reward_func": 0.1716996617615223,
|
5335 |
+
"rewards/enhanced_html_validity_reward_func": 0.0865000020712614,
|
5336 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8175000101327896,
|
5337 |
+
"rewards/general_responsiveness_reward_func": 0.049999999813735485,
|
5338 |
+
"rewards/hover_reward_func": 0.17250000685453415,
|
5339 |
+
"rewards/image_size_reward_func": 0.03262500185519457,
|
5340 |
+
"rewards/interactivity_reward_func": 0.5750000178813934,
|
5341 |
+
"rewards/link_validity_reward_func": 0.034625000320374966,
|
5342 |
+
"rewards/lorem_picsum_reward_func": 0.0028749999910360202,
|
5343 |
+
"rewards/mobile_responsiveness_reward_func": 0.0,
|
5344 |
+
"rewards/section_size_reward_func": 0.0,
|
5345 |
+
"rewards/tailwind_cdn_reward_func": 0.07000000029802322,
|
5346 |
+
"rewards/text_contrast_reward_func": 0.020833332557231188,
|
5347 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5348 |
+
"rewards/visual_hierarchy_reward_func": 0.06065995804965496,
|
5349 |
+
"step": 178
|
5350 |
+
},
|
5351 |
+
{
|
5352 |
+
"completion_length": 5445.7501220703125,
|
5353 |
+
"epoch": 0.926261319534282,
|
5354 |
+
"grad_norm": 0.0990913063287735,
|
5355 |
+
"kl": 0.003973092301748693,
|
5356 |
+
"learning_rate": 4.907699235008478e-06,
|
5357 |
+
"loss": 0.0002,
|
5358 |
+
"reward": 4.126912832260132,
|
5359 |
+
"reward_std": 0.5524152405560017,
|
5360 |
+
"rewards/accessibility_reward_func": 0.3360000289976597,
|
5361 |
+
"rewards/animation_reward_func": 0.31866665184497833,
|
5362 |
+
"rewards/color_theory_reward_func": 0.32083334028720856,
|
5363 |
+
"rewards/design_system_reward_func": 0.9583333432674408,
|
5364 |
+
"rewards/element_spacing_reward_func": 0.1595384944230318,
|
5365 |
+
"rewards/enhanced_html_validity_reward_func": 0.09016667306423187,
|
5366 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8450000286102295,
|
5367 |
+
"rewards/general_responsiveness_reward_func": 0.053999999538064,
|
5368 |
+
"rewards/hover_reward_func": 0.17250000685453415,
|
5369 |
+
"rewards/image_size_reward_func": 0.06037500314414501,
|
5370 |
+
"rewards/interactivity_reward_func": 0.5750000178813934,
|
5371 |
+
"rewards/link_validity_reward_func": 0.04312500124797225,
|
5372 |
+
"rewards/lorem_picsum_reward_func": 0.004666666500270367,
|
5373 |
+
"rewards/mobile_responsiveness_reward_func": 0.0013333334354683757,
|
5374 |
+
"rewards/section_size_reward_func": 0.0,
|
5375 |
+
"rewards/tailwind_cdn_reward_func": 0.06708333361893892,
|
5376 |
+
"rewards/text_contrast_reward_func": 0.024999999441206455,
|
5377 |
+
"rewards/think_tag_reward_func": 0.038333332166075706,
|
5378 |
+
"rewards/visual_hierarchy_reward_func": 0.056957339867949486,
|
5379 |
+
"step": 179
|
5380 |
+
},
|
5381 |
+
{
|
5382 |
+
"completion_length": 5843.2918701171875,
|
5383 |
+
"epoch": 0.9314359637774903,
|
5384 |
+
"grad_norm": 0.09346303343772888,
|
5385 |
+
"kl": 0.004328261537011713,
|
5386 |
+
"learning_rate": 4.904564107932048e-06,
|
5387 |
+
"loss": 0.0002,
|
5388 |
+
"reward": 4.295399785041809,
|
5389 |
+
"reward_std": 0.25310972332954407,
|
5390 |
+
"rewards/accessibility_reward_func": 0.3490833453834057,
|
5391 |
+
"rewards/animation_reward_func": 0.37300001084804535,
|
5392 |
+
"rewards/color_theory_reward_func": 0.32199999690055847,
|
5393 |
+
"rewards/design_system_reward_func": 1.0,
|
5394 |
+
"rewards/element_spacing_reward_func": 0.16697118431329727,
|
5395 |
+
"rewards/enhanced_html_validity_reward_func": 0.0879166703671217,
|
5396 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8525000065565109,
|
5397 |
+
"rewards/general_responsiveness_reward_func": 0.0605000015348196,
|
5398 |
+
"rewards/hover_reward_func": 0.18000000715255737,
|
5399 |
+
"rewards/image_size_reward_func": 0.06025000289082527,
|
5400 |
+
"rewards/interactivity_reward_func": 0.6000000238418579,
|
5401 |
+
"rewards/link_validity_reward_func": 0.04237500112503767,
|
5402 |
+
"rewards/lorem_picsum_reward_func": 0.004291666729841381,
|
5403 |
+
"rewards/mobile_responsiveness_reward_func": 0.010000000416766852,
|
5404 |
+
"rewards/section_size_reward_func": 0.0,
|
5405 |
+
"rewards/tailwind_cdn_reward_func": 0.06416666693985462,
|
5406 |
+
"rewards/text_contrast_reward_func": 0.024999999441206455,
|
5407 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5408 |
+
"rewards/visual_hierarchy_reward_func": 0.05734516493976116,
|
5409 |
+
"step": 180
|
5410 |
}
|
5411 |
],
|
5412 |
"logging_steps": 1,
|