Upload checkpoint 200
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 200 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: 25.00%; 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: 200 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 sha256:83edfbec31bc138afcd4a385a824886df5cc233930ef3e96064586de6186285b
|
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 sha256:01ff8f56517ff84c2c5047e4445886a6f70094f37ce685b67ca53931f3666a5a
|
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 sha256:487c4c47d02d79b8025fc6b315931e5f1c680fb2ad382403f3b38a103c733c95
|
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:ee2939feb65937e01d09eb1f8fbad884be28f2c6572e4ffba06471add86d5d69
|
3 |
size 1064
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
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,
|
@@ -5707,6 +5707,306 @@
|
|
5707 |
"rewards/think_tag_reward_func": 0.038333332166075706,
|
5708 |
"rewards/visual_hierarchy_reward_func": 0.056508997455239296,
|
5709 |
"step": 190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5710 |
}
|
5711 |
],
|
5712 |
"logging_steps": 1,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.036222509702458,
|
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,
|
|
|
5707 |
"rewards/think_tag_reward_func": 0.038333332166075706,
|
5708 |
"rewards/visual_hierarchy_reward_func": 0.056508997455239296,
|
5709 |
"step": 190
|
5710 |
+
},
|
5711 |
+
{
|
5712 |
+
"completion_length": 5357.7086181640625,
|
5713 |
+
"epoch": 0.9883570504527813,
|
5714 |
+
"grad_norm": 0.22252987325191498,
|
5715 |
+
"kl": 0.006184103433042765,
|
5716 |
+
"learning_rate": 4.866705852484877e-06,
|
5717 |
+
"loss": 0.0002,
|
5718 |
+
"reward": 3.9356017112731934,
|
5719 |
+
"reward_std": 0.9688514210283756,
|
5720 |
+
"rewards/accessibility_reward_func": 0.32608334720134735,
|
5721 |
+
"rewards/animation_reward_func": 0.3243333175778389,
|
5722 |
+
"rewards/color_theory_reward_func": 0.30391667038202286,
|
5723 |
+
"rewards/design_system_reward_func": 0.9166666865348816,
|
5724 |
+
"rewards/element_spacing_reward_func": 0.15892905369400978,
|
5725 |
+
"rewards/enhanced_html_validity_reward_func": 0.08291667327284813,
|
5726 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.7599999904632568,
|
5727 |
+
"rewards/general_responsiveness_reward_func": 0.05550000071525574,
|
5728 |
+
"rewards/hover_reward_func": 0.16500000655651093,
|
5729 |
+
"rewards/image_size_reward_func": 0.06950000114738941,
|
5730 |
+
"rewards/interactivity_reward_func": 0.550000011920929,
|
5731 |
+
"rewards/link_validity_reward_func": 0.03800000064074993,
|
5732 |
+
"rewards/lorem_picsum_reward_func": 0.00437499990221113,
|
5733 |
+
"rewards/mobile_responsiveness_reward_func": 0.005333333683665842,
|
5734 |
+
"rewards/section_size_reward_func": 0.0011666667414829135,
|
5735 |
+
"rewards/tailwind_cdn_reward_func": 0.06125000026077032,
|
5736 |
+
"rewards/text_contrast_reward_func": 0.0216666660271585,
|
5737 |
+
"rewards/think_tag_reward_func": 0.036666665226221085,
|
5738 |
+
"rewards/visual_hierarchy_reward_func": 0.05429751332849264,
|
5739 |
+
"step": 191
|
5740 |
+
},
|
5741 |
+
{
|
5742 |
+
"completion_length": 5209.7918701171875,
|
5743 |
+
"epoch": 0.9935316946959897,
|
5744 |
+
"grad_norm": 0.09440814703702927,
|
5745 |
+
"kl": 0.005323882447555661,
|
5746 |
+
"learning_rate": 4.86295957040205e-06,
|
5747 |
+
"loss": 0.0002,
|
5748 |
+
"reward": 4.011856138706207,
|
5749 |
+
"reward_std": 0.3229644186794758,
|
5750 |
+
"rewards/accessibility_reward_func": 0.28816668316721916,
|
5751 |
+
"rewards/animation_reward_func": 0.32733333110809326,
|
5752 |
+
"rewards/color_theory_reward_func": 0.31733333319425583,
|
5753 |
+
"rewards/design_system_reward_func": 1.0,
|
5754 |
+
"rewards/element_spacing_reward_func": 0.17185210809111595,
|
5755 |
+
"rewards/enhanced_html_validity_reward_func": 0.08433333411812782,
|
5756 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.7250000238418579,
|
5757 |
+
"rewards/general_responsiveness_reward_func": 0.053500003181397915,
|
5758 |
+
"rewards/hover_reward_func": 0.17100000753998756,
|
5759 |
+
"rewards/image_size_reward_func": 0.041500001156236976,
|
5760 |
+
"rewards/interactivity_reward_func": 0.5985000282526016,
|
5761 |
+
"rewards/link_validity_reward_func": 0.0332500000949949,
|
5762 |
+
"rewards/lorem_picsum_reward_func": 0.0037916665751254186,
|
5763 |
+
"rewards/mobile_responsiveness_reward_func": 0.00533333356725052,
|
5764 |
+
"rewards/section_size_reward_func": 0.0,
|
5765 |
+
"rewards/tailwind_cdn_reward_func": 0.06708333361893892,
|
5766 |
+
"rewards/text_contrast_reward_func": 0.02416666643694043,
|
5767 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5768 |
+
"rewards/visual_hierarchy_reward_func": 0.05971211567521095,
|
5769 |
+
"step": 192
|
5770 |
+
},
|
5771 |
+
{
|
5772 |
+
"completion_length": 5611.916748046875,
|
5773 |
+
"epoch": 0.9987063389391979,
|
5774 |
+
"grad_norm": 0.09559457004070282,
|
5775 |
+
"kl": 0.0055139511823654175,
|
5776 |
+
"learning_rate": 4.8591628526905575e-06,
|
5777 |
+
"loss": 0.0002,
|
5778 |
+
"reward": 4.19249427318573,
|
5779 |
+
"reward_std": 0.24222454987466335,
|
5780 |
+
"rewards/accessibility_reward_func": 0.333083339035511,
|
5781 |
+
"rewards/animation_reward_func": 0.291333332657814,
|
5782 |
+
"rewards/color_theory_reward_func": 0.3243333473801613,
|
5783 |
+
"rewards/design_system_reward_func": 1.0,
|
5784 |
+
"rewards/element_spacing_reward_func": 0.16802729293704033,
|
5785 |
+
"rewards/enhanced_html_validity_reward_func": 0.09150000475347042,
|
5786 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8425000309944153,
|
5787 |
+
"rewards/general_responsiveness_reward_func": 0.05825000163167715,
|
5788 |
+
"rewards/hover_reward_func": 0.18000000715255737,
|
5789 |
+
"rewards/image_size_reward_func": 0.060250003822147846,
|
5790 |
+
"rewards/interactivity_reward_func": 0.6000000238418579,
|
5791 |
+
"rewards/link_validity_reward_func": 0.044375001452863216,
|
5792 |
+
"rewards/lorem_picsum_reward_func": 0.004333333345130086,
|
5793 |
+
"rewards/mobile_responsiveness_reward_func": 0.004666666907723993,
|
5794 |
+
"rewards/section_size_reward_func": 0.0,
|
5795 |
+
"rewards/tailwind_cdn_reward_func": 0.07000000029802322,
|
5796 |
+
"rewards/text_contrast_reward_func": 0.01916666654869914,
|
5797 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5798 |
+
"rewards/visual_hierarchy_reward_func": 0.06067483313381672,
|
5799 |
+
"step": 193
|
5800 |
+
},
|
5801 |
+
{
|
5802 |
+
"completion_length": 5751.43349609375,
|
5803 |
+
"epoch": 1.0051746442432083,
|
5804 |
+
"grad_norm": 0.10521108657121658,
|
5805 |
+
"kl": 0.005599316302686929,
|
5806 |
+
"learning_rate": 4.855315780388541e-06,
|
5807 |
+
"loss": 0.0003,
|
5808 |
+
"reward": 4.110462188720703,
|
5809 |
+
"reward_std": 0.2812949061393738,
|
5810 |
+
"rewards/accessibility_reward_func": 0.2730000078678131,
|
5811 |
+
"rewards/animation_reward_func": 0.32426666021347045,
|
5812 |
+
"rewards/color_theory_reward_func": 0.3378666818141937,
|
5813 |
+
"rewards/design_system_reward_func": 1.0,
|
5814 |
+
"rewards/element_spacing_reward_func": 0.1681518077850342,
|
5815 |
+
"rewards/enhanced_html_validity_reward_func": 0.08706667274236679,
|
5816 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.7970000147819519,
|
5817 |
+
"rewards/general_responsiveness_reward_func": 0.06080000251531601,
|
5818 |
+
"rewards/hover_reward_func": 0.17720000743865966,
|
5819 |
+
"rewards/image_size_reward_func": 0.047100001759827134,
|
5820 |
+
"rewards/interactivity_reward_func": 0.5968000292778015,
|
5821 |
+
"rewards/link_validity_reward_func": 0.04230000041425228,
|
5822 |
+
"rewards/lorem_picsum_reward_func": 0.003866666741669178,
|
5823 |
+
"rewards/mobile_responsiveness_reward_func": 0.007200000248849392,
|
5824 |
+
"rewards/section_size_reward_func": 0.0,
|
5825 |
+
"rewards/tailwind_cdn_reward_func": 0.06766666695475579,
|
5826 |
+
"rewards/text_contrast_reward_func": 0.0193333325907588,
|
5827 |
+
"rewards/think_tag_reward_func": 0.03866666555404663,
|
5828 |
+
"rewards/visual_hierarchy_reward_func": 0.06217685043811798,
|
5829 |
+
"step": 194
|
5830 |
+
},
|
5831 |
+
{
|
5832 |
+
"completion_length": 5326.625183105469,
|
5833 |
+
"epoch": 1.0103492884864165,
|
5834 |
+
"grad_norm": 0.10344433039426804,
|
5835 |
+
"kl": 0.005389054538682103,
|
5836 |
+
"learning_rate": 4.851418435608919e-06,
|
5837 |
+
"loss": 0.0002,
|
5838 |
+
"reward": 3.8954920172691345,
|
5839 |
+
"reward_std": 0.22136176005005836,
|
5840 |
+
"rewards/accessibility_reward_func": 0.2642500102519989,
|
5841 |
+
"rewards/animation_reward_func": 0.2906666658818722,
|
5842 |
+
"rewards/color_theory_reward_func": 0.22341667860746384,
|
5843 |
+
"rewards/design_system_reward_func": 1.0,
|
5844 |
+
"rewards/element_spacing_reward_func": 0.16264517977833748,
|
5845 |
+
"rewards/enhanced_html_validity_reward_func": 0.08641666918992996,
|
5846 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.7912500202655792,
|
5847 |
+
"rewards/general_responsiveness_reward_func": 0.05575000122189522,
|
5848 |
+
"rewards/hover_reward_func": 0.16750001162290573,
|
5849 |
+
"rewards/image_size_reward_func": 0.0533750019967556,
|
5850 |
+
"rewards/interactivity_reward_func": 0.5805000215768814,
|
5851 |
+
"rewards/link_validity_reward_func": 0.02499999979045242,
|
5852 |
+
"rewards/lorem_picsum_reward_func": 0.0037916666478849947,
|
5853 |
+
"rewards/mobile_responsiveness_reward_func": 0.0006666667177341878,
|
5854 |
+
"rewards/section_size_reward_func": 0.0,
|
5855 |
+
"rewards/tailwind_cdn_reward_func": 0.07000000029802322,
|
5856 |
+
"rewards/text_contrast_reward_func": 0.01916666643228382,
|
5857 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5858 |
+
"rewards/visual_hierarchy_reward_func": 0.06109676789492369,
|
5859 |
+
"step": 195
|
5860 |
+
},
|
5861 |
+
{
|
5862 |
+
"completion_length": 5799.0418701171875,
|
5863 |
+
"epoch": 1.0155239327296248,
|
5864 |
+
"grad_norm": 0.10122188925743103,
|
5865 |
+
"kl": 0.005780180799774826,
|
5866 |
+
"learning_rate": 4.847470901537642e-06,
|
5867 |
+
"loss": 0.0002,
|
5868 |
+
"reward": 4.02301698923111,
|
5869 |
+
"reward_std": 0.26710568740963936,
|
5870 |
+
"rewards/accessibility_reward_func": 0.24383333697915077,
|
5871 |
+
"rewards/animation_reward_func": 0.35466666519641876,
|
5872 |
+
"rewards/color_theory_reward_func": 0.31966667622327805,
|
5873 |
+
"rewards/design_system_reward_func": 1.0,
|
5874 |
+
"rewards/element_spacing_reward_func": 0.16675950959324837,
|
5875 |
+
"rewards/enhanced_html_validity_reward_func": 0.08350000344216824,
|
5876 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.7687500566244125,
|
5877 |
+
"rewards/general_responsiveness_reward_func": 0.049750001169741154,
|
5878 |
+
"rewards/hover_reward_func": 0.18000000715255737,
|
5879 |
+
"rewards/image_size_reward_func": 0.03712500096298754,
|
5880 |
+
"rewards/interactivity_reward_func": 0.6000000238418579,
|
5881 |
+
"rewards/link_validity_reward_func": 0.034750000573694706,
|
5882 |
+
"rewards/lorem_picsum_reward_func": 0.0030000000551808625,
|
5883 |
+
"rewards/mobile_responsiveness_reward_func": 0.0013333334354683757,
|
5884 |
+
"rewards/section_size_reward_func": 0.0,
|
5885 |
+
"rewards/tailwind_cdn_reward_func": 0.06416666693985462,
|
5886 |
+
"rewards/text_contrast_reward_func": 0.02166666556149721,
|
5887 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5888 |
+
"rewards/visual_hierarchy_reward_func": 0.05404897406697273,
|
5889 |
+
"step": 196
|
5890 |
+
},
|
5891 |
+
{
|
5892 |
+
"completion_length": 6178.875244140625,
|
5893 |
+
"epoch": 1.0206985769728332,
|
5894 |
+
"grad_norm": 1.192289113998413,
|
5895 |
+
"kl": 0.13257847575005144,
|
5896 |
+
"learning_rate": 4.843473262431911e-06,
|
5897 |
+
"loss": 0.0053,
|
5898 |
+
"reward": 3.8458264470100403,
|
5899 |
+
"reward_std": 0.9682719632983208,
|
5900 |
+
"rewards/accessibility_reward_func": 0.2759166732430458,
|
5901 |
+
"rewards/animation_reward_func": 0.32066667079925537,
|
5902 |
+
"rewards/color_theory_reward_func": 0.28700000420212746,
|
5903 |
+
"rewards/design_system_reward_func": 0.9166666865348816,
|
5904 |
+
"rewards/element_spacing_reward_func": 0.14859908819198608,
|
5905 |
+
"rewards/enhanced_html_validity_reward_func": 0.08008333668112755,
|
5906 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.7950000166893005,
|
5907 |
+
"rewards/general_responsiveness_reward_func": 0.05000000074505806,
|
5908 |
+
"rewards/hover_reward_func": 0.16500000655651093,
|
5909 |
+
"rewards/image_size_reward_func": 0.04137500189244747,
|
5910 |
+
"rewards/interactivity_reward_func": 0.550000011920929,
|
5911 |
+
"rewards/link_validity_reward_func": 0.038250000681728125,
|
5912 |
+
"rewards/lorem_picsum_reward_func": 0.003166666632751003,
|
5913 |
+
"rewards/mobile_responsiveness_reward_func": 0.004666666907723993,
|
5914 |
+
"rewards/section_size_reward_func": 0.0,
|
5915 |
+
"rewards/tailwind_cdn_reward_func": 0.05833333358168602,
|
5916 |
+
"rewards/text_contrast_reward_func": 0.02333333238493651,
|
5917 |
+
"rewards/think_tag_reward_func": 0.03666666615754366,
|
5918 |
+
"rewards/visual_hierarchy_reward_func": 0.05110215209424496,
|
5919 |
+
"step": 197
|
5920 |
+
},
|
5921 |
+
{
|
5922 |
+
"completion_length": 6442.875244140625,
|
5923 |
+
"epoch": 1.0258732212160413,
|
5924 |
+
"grad_norm": 1.857179045677185,
|
5925 |
+
"kl": 0.1313048725714907,
|
5926 |
+
"learning_rate": 4.839425603618382e-06,
|
5927 |
+
"loss": 0.0053,
|
5928 |
+
"reward": 4.115786373615265,
|
5929 |
+
"reward_std": 0.5695532448589802,
|
5930 |
+
"rewards/accessibility_reward_func": 0.35233334451913834,
|
5931 |
+
"rewards/animation_reward_func": 0.35233330726623535,
|
5932 |
+
"rewards/color_theory_reward_func": 0.26775000244379044,
|
5933 |
+
"rewards/design_system_reward_func": 0.9583333432674408,
|
5934 |
+
"rewards/element_spacing_reward_func": 0.16129610687494278,
|
5935 |
+
"rewards/enhanced_html_validity_reward_func": 0.08741666935384274,
|
5936 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.846250057220459,
|
5937 |
+
"rewards/general_responsiveness_reward_func": 0.05200000200420618,
|
5938 |
+
"rewards/hover_reward_func": 0.17250000685453415,
|
5939 |
+
"rewards/image_size_reward_func": 0.057125003077089787,
|
5940 |
+
"rewards/interactivity_reward_func": 0.5750000178813934,
|
5941 |
+
"rewards/link_validity_reward_func": 0.0432500010356307,
|
5942 |
+
"rewards/lorem_picsum_reward_func": 0.004541666596196592,
|
5943 |
+
"rewards/mobile_responsiveness_reward_func": 0.0020000001532025635,
|
5944 |
+
"rewards/section_size_reward_func": 0.0,
|
5945 |
+
"rewards/tailwind_cdn_reward_func": 0.06416666693985462,
|
5946 |
+
"rewards/text_contrast_reward_func": 0.027500000782310963,
|
5947 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5948 |
+
"rewards/visual_hierarchy_reward_func": 0.05199005175381899,
|
5949 |
+
"step": 198
|
5950 |
+
},
|
5951 |
+
{
|
5952 |
+
"completion_length": 5621.0836181640625,
|
5953 |
+
"epoch": 1.0310478654592496,
|
5954 |
+
"grad_norm": 0.21412530541419983,
|
5955 |
+
"kl": 0.0061011165380477905,
|
5956 |
+
"learning_rate": 4.835328011491348e-06,
|
5957 |
+
"loss": 0.0002,
|
5958 |
+
"reward": 4.242915034294128,
|
5959 |
+
"reward_std": 0.22091838344931602,
|
5960 |
+
"rewards/accessibility_reward_func": 0.32375000230968,
|
5961 |
+
"rewards/animation_reward_func": 0.3436666652560234,
|
5962 |
+
"rewards/color_theory_reward_func": 0.30275000631809235,
|
5963 |
+
"rewards/design_system_reward_func": 1.0,
|
5964 |
+
"rewards/element_spacing_reward_func": 0.1666652373969555,
|
5965 |
+
"rewards/enhanced_html_validity_reward_func": 0.08966667205095291,
|
5966 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8750000447034836,
|
5967 |
+
"rewards/general_responsiveness_reward_func": 0.06300000008195639,
|
5968 |
+
"rewards/hover_reward_func": 0.18000000715255737,
|
5969 |
+
"rewards/image_size_reward_func": 0.05737500265240669,
|
5970 |
+
"rewards/interactivity_reward_func": 0.6000000238418579,
|
5971 |
+
"rewards/link_validity_reward_func": 0.04587499983608723,
|
5972 |
+
"rewards/lorem_picsum_reward_func": 0.00437499990221113,
|
5973 |
+
"rewards/mobile_responsiveness_reward_func": 0.0006666667177341878,
|
5974 |
+
"rewards/section_size_reward_func": 0.0,
|
5975 |
+
"rewards/tailwind_cdn_reward_func": 0.07000000029802322,
|
5976 |
+
"rewards/text_contrast_reward_func": 0.023333333432674408,
|
5977 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5978 |
+
"rewards/visual_hierarchy_reward_func": 0.056791260838508606,
|
5979 |
+
"step": 199
|
5980 |
+
},
|
5981 |
+
{
|
5982 |
+
"completion_length": 6027.33349609375,
|
5983 |
+
"epoch": 1.036222509702458,
|
5984 |
+
"grad_norm": 13.110360145568848,
|
5985 |
+
"kl": 0.2326243775896728,
|
5986 |
+
"learning_rate": 4.83118057351089e-06,
|
5987 |
+
"loss": 0.0093,
|
5988 |
+
"reward": 4.089508891105652,
|
5989 |
+
"reward_std": 0.6124457716941833,
|
5990 |
+
"rewards/accessibility_reward_func": 0.2957500070333481,
|
5991 |
+
"rewards/animation_reward_func": 0.3176666721701622,
|
5992 |
+
"rewards/color_theory_reward_func": 0.31325000524520874,
|
5993 |
+
"rewards/design_system_reward_func": 0.9583333432674408,
|
5994 |
+
"rewards/element_spacing_reward_func": 0.16081713140010834,
|
5995 |
+
"rewards/enhanced_html_validity_reward_func": 0.08891667053103447,
|
5996 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8500000387430191,
|
5997 |
+
"rewards/general_responsiveness_reward_func": 0.05075000040233135,
|
5998 |
+
"rewards/hover_reward_func": 0.17250000685453415,
|
5999 |
+
"rewards/image_size_reward_func": 0.061125000938773155,
|
6000 |
+
"rewards/interactivity_reward_func": 0.5750000178813934,
|
6001 |
+
"rewards/link_validity_reward_func": 0.04337500128895044,
|
6002 |
+
"rewards/lorem_picsum_reward_func": 0.004208333324640989,
|
6003 |
+
"rewards/mobile_responsiveness_reward_func": 0.004666666965931654,
|
6004 |
+
"rewards/section_size_reward_func": 0.0,
|
6005 |
+
"rewards/tailwind_cdn_reward_func": 0.06708333361893892,
|
6006 |
+
"rewards/text_contrast_reward_func": 0.026666666381061077,
|
6007 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
6008 |
+
"rewards/visual_hierarchy_reward_func": 0.059399841353297234,
|
6009 |
+
"step": 200
|
6010 |
}
|
6011 |
],
|
6012 |
"logging_steps": 1,
|