Upload checkpoint 190
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 190 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: 23.75%; 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: 190 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 sha256:973862e771dde9eb18cf7e96b0350bf3e13296808e9bf2c46a67894bdeb36437
|
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:ef73b674df50a7f2f639bda1db64056f5a81ecd690f1e63ad178cf9d0cfb32e6
|
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 sha256:1b8a0c25402114801551f4ff2a66f07e2d289c99502fe3684d5ecd0cc9f10335
|
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:de248bf4d61031a3cd35a483be2fd33d71c9679b1acab148cdd2178dd81ff54d
|
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,
|
@@ -5407,6 +5407,306 @@
|
|
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,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9831824062095731,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 190,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
5407 |
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5408 |
"rewards/visual_hierarchy_reward_func": 0.05734516493976116,
|
5409 |
"step": 180
|
5410 |
+
},
|
5411 |
+
{
|
5412 |
+
"completion_length": 5991.541748046875,
|
5413 |
+
"epoch": 0.9366106080206986,
|
5414 |
+
"grad_norm": 0.08011792600154877,
|
5415 |
+
"kl": 0.004481432610191405,
|
5416 |
+
"learning_rate": 4.901377657208796e-06,
|
5417 |
+
"loss": 0.0002,
|
5418 |
+
"reward": 4.011803984642029,
|
5419 |
+
"reward_std": 0.525986410677433,
|
5420 |
+
"rewards/accessibility_reward_func": 0.26775000616908073,
|
5421 |
+
"rewards/animation_reward_func": 0.3556666597723961,
|
5422 |
+
"rewards/color_theory_reward_func": 0.3161666765809059,
|
5423 |
+
"rewards/design_system_reward_func": 0.9583333432674408,
|
5424 |
+
"rewards/element_spacing_reward_func": 0.16377569362521172,
|
5425 |
+
"rewards/enhanced_html_validity_reward_func": 0.08275000378489494,
|
5426 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.7925000339746475,
|
5427 |
+
"rewards/general_responsiveness_reward_func": 0.05775000248104334,
|
5428 |
+
"rewards/hover_reward_func": 0.16900000721216202,
|
5429 |
+
"rewards/image_size_reward_func": 0.0456250028219074,
|
5430 |
+
"rewards/interactivity_reward_func": 0.5710000321269035,
|
5431 |
+
"rewards/link_validity_reward_func": 0.03924999921582639,
|
5432 |
+
"rewards/lorem_picsum_reward_func": 0.0038333333213813603,
|
5433 |
+
"rewards/mobile_responsiveness_reward_func": 0.006666667235549539,
|
5434 |
+
"rewards/section_size_reward_func": 0.001500000013038516,
|
5435 |
+
"rewards/tailwind_cdn_reward_func": 0.06416666693985462,
|
5436 |
+
"rewards/text_contrast_reward_func": 0.02249999949708581,
|
5437 |
+
"rewards/think_tag_reward_func": 0.038333332166075706,
|
5438 |
+
"rewards/visual_hierarchy_reward_func": 0.05523636098951101,
|
5439 |
+
"step": 181
|
5440 |
+
},
|
5441 |
+
{
|
5442 |
+
"completion_length": 4912.5001220703125,
|
5443 |
+
"epoch": 0.9417852522639069,
|
5444 |
+
"grad_norm": 0.09984100610017776,
|
5445 |
+
"kl": 0.004854657920077443,
|
5446 |
+
"learning_rate": 4.898139950851163e-06,
|
5447 |
+
"loss": 0.0002,
|
5448 |
+
"reward": 4.082658231258392,
|
5449 |
+
"reward_std": 0.2283327281475067,
|
5450 |
+
"rewards/accessibility_reward_func": 0.29108333587646484,
|
5451 |
+
"rewards/animation_reward_func": 0.2983333319425583,
|
5452 |
+
"rewards/color_theory_reward_func": 0.34708333760499954,
|
5453 |
+
"rewards/design_system_reward_func": 1.0,
|
5454 |
+
"rewards/element_spacing_reward_func": 0.1674305535852909,
|
5455 |
+
"rewards/enhanced_html_validity_reward_func": 0.09066666848957539,
|
5456 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.7875000387430191,
|
5457 |
+
"rewards/general_responsiveness_reward_func": 0.04475000128149986,
|
5458 |
+
"rewards/hover_reward_func": 0.18000000715255737,
|
5459 |
+
"rewards/image_size_reward_func": 0.04537500184960663,
|
5460 |
+
"rewards/interactivity_reward_func": 0.6000000238418579,
|
5461 |
+
"rewards/link_validity_reward_func": 0.029875002102926373,
|
5462 |
+
"rewards/lorem_picsum_reward_func": 0.0039166665810626,
|
5463 |
+
"rewards/mobile_responsiveness_reward_func": 0.004666667024139315,
|
5464 |
+
"rewards/section_size_reward_func": 0.0,
|
5465 |
+
"rewards/tailwind_cdn_reward_func": 0.07000000029802322,
|
5466 |
+
"rewards/text_contrast_reward_func": 0.019166665617376566,
|
5467 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5468 |
+
"rewards/visual_hierarchy_reward_func": 0.06281090062111616,
|
5469 |
+
"step": 182
|
5470 |
+
},
|
5471 |
+
{
|
5472 |
+
"completion_length": 5891.875244140625,
|
5473 |
+
"epoch": 0.9469598965071151,
|
5474 |
+
"grad_norm": 0.08798679709434509,
|
5475 |
+
"kl": 0.004506548517383635,
|
5476 |
+
"learning_rate": 4.894851057965601e-06,
|
5477 |
+
"loss": 0.0002,
|
5478 |
+
"reward": 4.273834705352783,
|
5479 |
+
"reward_std": 0.23263845220208168,
|
5480 |
+
"rewards/accessibility_reward_func": 0.35466667264699936,
|
5481 |
+
"rewards/animation_reward_func": 0.316333319991827,
|
5482 |
+
"rewards/color_theory_reward_func": 0.34066667407751083,
|
5483 |
+
"rewards/design_system_reward_func": 1.0,
|
5484 |
+
"rewards/element_spacing_reward_func": 0.16662172600626945,
|
5485 |
+
"rewards/enhanced_html_validity_reward_func": 0.09033333696424961,
|
5486 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8625000417232513,
|
5487 |
+
"rewards/general_responsiveness_reward_func": 0.058999999426305294,
|
5488 |
+
"rewards/hover_reward_func": 0.1785000078380108,
|
5489 |
+
"rewards/image_size_reward_func": 0.06812500208616257,
|
5490 |
+
"rewards/interactivity_reward_func": 0.6000000238418579,
|
5491 |
+
"rewards/link_validity_reward_func": 0.03862500190734863,
|
5492 |
+
"rewards/lorem_picsum_reward_func": 0.004708333290182054,
|
5493 |
+
"rewards/mobile_responsiveness_reward_func": 0.00600000040140003,
|
5494 |
+
"rewards/section_size_reward_func": 0.0,
|
5495 |
+
"rewards/tailwind_cdn_reward_func": 0.06708333361893892,
|
5496 |
+
"rewards/text_contrast_reward_func": 0.018333333544433117,
|
5497 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5498 |
+
"rewards/visual_hierarchy_reward_func": 0.06233790144324303,
|
5499 |
+
"step": 183
|
5500 |
+
},
|
5501 |
+
{
|
5502 |
+
"completion_length": 6260.3336181640625,
|
5503 |
+
"epoch": 0.9521345407503234,
|
5504 |
+
"grad_norm": 2.4132983684539795,
|
5505 |
+
"kl": 0.09769216005224735,
|
5506 |
+
"learning_rate": 4.891511048751102e-06,
|
5507 |
+
"loss": 0.0039,
|
5508 |
+
"reward": 4.15910667181015,
|
5509 |
+
"reward_std": 0.5679790638387203,
|
5510 |
+
"rewards/accessibility_reward_func": 0.40708332508802414,
|
5511 |
+
"rewards/animation_reward_func": 0.3320000022649765,
|
5512 |
+
"rewards/color_theory_reward_func": 0.31441666930913925,
|
5513 |
+
"rewards/design_system_reward_func": 0.9583333432674408,
|
5514 |
+
"rewards/element_spacing_reward_func": 0.16063417866826057,
|
5515 |
+
"rewards/enhanced_html_validity_reward_func": 0.08775000460445881,
|
5516 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.798750028014183,
|
5517 |
+
"rewards/general_responsiveness_reward_func": 0.06050000060349703,
|
5518 |
+
"rewards/hover_reward_func": 0.17250000685453415,
|
5519 |
+
"rewards/image_size_reward_func": 0.06250000279396772,
|
5520 |
+
"rewards/interactivity_reward_func": 0.5750000178813934,
|
5521 |
+
"rewards/link_validity_reward_func": 0.0413750009611249,
|
5522 |
+
"rewards/lorem_picsum_reward_func": 0.004499999922700226,
|
5523 |
+
"rewards/mobile_responsiveness_reward_func": 0.006000000459607691,
|
5524 |
+
"rewards/section_size_reward_func": 0.0,
|
5525 |
+
"rewards/tailwind_cdn_reward_func": 0.06416666693985462,
|
5526 |
+
"rewards/text_contrast_reward_func": 0.020833333488553762,
|
5527 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5528 |
+
"rewards/visual_hierarchy_reward_func": 0.05276394169777632,
|
5529 |
+
"step": 184
|
5530 |
+
},
|
5531 |
+
{
|
5532 |
+
"completion_length": 5694.750244140625,
|
5533 |
+
"epoch": 0.9573091849935317,
|
5534 |
+
"grad_norm": 0.09554839134216309,
|
5535 |
+
"kl": 0.004761494696140289,
|
5536 |
+
"learning_rate": 4.888119994497701e-06,
|
5537 |
+
"loss": 0.0002,
|
5538 |
+
"reward": 4.096001923084259,
|
5539 |
+
"reward_std": 0.18258628249168396,
|
5540 |
+
"rewards/accessibility_reward_func": 0.24150000512599945,
|
5541 |
+
"rewards/animation_reward_func": 0.33666665107011795,
|
5542 |
+
"rewards/color_theory_reward_func": 0.29983334988355637,
|
5543 |
+
"rewards/design_system_reward_func": 1.0,
|
5544 |
+
"rewards/element_spacing_reward_func": 0.17044252157211304,
|
5545 |
+
"rewards/enhanced_html_validity_reward_func": 0.08416666649281979,
|
5546 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8537500500679016,
|
5547 |
+
"rewards/general_responsiveness_reward_func": 0.04800000134855509,
|
5548 |
+
"rewards/hover_reward_func": 0.1785000078380108,
|
5549 |
+
"rewards/image_size_reward_func": 0.037250002613291144,
|
5550 |
+
"rewards/interactivity_reward_func": 0.6000000238418579,
|
5551 |
+
"rewards/link_validity_reward_func": 0.043499999679625034,
|
5552 |
+
"rewards/lorem_picsum_reward_func": 0.003083333300310187,
|
5553 |
+
"rewards/mobile_responsiveness_reward_func": 0.0,
|
5554 |
+
"rewards/section_size_reward_func": 0.001500000013038516,
|
5555 |
+
"rewards/tailwind_cdn_reward_func": 0.06416666693985462,
|
5556 |
+
"rewards/text_contrast_reward_func": 0.030833333730697632,
|
5557 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5558 |
+
"rewards/visual_hierarchy_reward_func": 0.06280925683677197,
|
5559 |
+
"step": 185
|
5560 |
+
},
|
5561 |
+
{
|
5562 |
+
"completion_length": 6461.2918701171875,
|
5563 |
+
"epoch": 0.96248382923674,
|
5564 |
+
"grad_norm": 0.07830818742513657,
|
5565 |
+
"kl": 0.0042079652193933725,
|
5566 |
+
"learning_rate": 4.884677967584945e-06,
|
5567 |
+
"loss": 0.0002,
|
5568 |
+
"reward": 4.416837811470032,
|
5569 |
+
"reward_std": 0.15833609364926815,
|
5570 |
+
"rewards/accessibility_reward_func": 0.4546666815876961,
|
5571 |
+
"rewards/animation_reward_func": 0.34933333843946457,
|
5572 |
+
"rewards/color_theory_reward_func": 0.2939999997615814,
|
5573 |
+
"rewards/design_system_reward_func": 1.0,
|
5574 |
+
"rewards/element_spacing_reward_func": 0.17040946707129478,
|
5575 |
+
"rewards/enhanced_html_validity_reward_func": 0.08908333443105221,
|
5576 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8925000429153442,
|
5577 |
+
"rewards/general_responsiveness_reward_func": 0.05975000187754631,
|
5578 |
+
"rewards/hover_reward_func": 0.18000000715255737,
|
5579 |
+
"rewards/image_size_reward_func": 0.0768750049173832,
|
5580 |
+
"rewards/interactivity_reward_func": 0.6000000238418579,
|
5581 |
+
"rewards/link_validity_reward_func": 0.047125001437962055,
|
5582 |
+
"rewards/lorem_picsum_reward_func": 0.004999999888241291,
|
5583 |
+
"rewards/mobile_responsiveness_reward_func": 0.006666667060926557,
|
5584 |
+
"rewards/section_size_reward_func": 0.0,
|
5585 |
+
"rewards/tailwind_cdn_reward_func": 0.07000000029802322,
|
5586 |
+
"rewards/text_contrast_reward_func": 0.022499999846331775,
|
5587 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5588 |
+
"rewards/visual_hierarchy_reward_func": 0.05892826709896326,
|
5589 |
+
"step": 186
|
5590 |
+
},
|
5591 |
+
{
|
5592 |
+
"completion_length": 5713.7083740234375,
|
5593 |
+
"epoch": 0.9676584734799483,
|
5594 |
+
"grad_norm": 0.8684507012367249,
|
5595 |
+
"kl": 0.11184422404039651,
|
5596 |
+
"learning_rate": 4.881185041480364e-06,
|
5597 |
+
"loss": 0.0045,
|
5598 |
+
"reward": 4.099178194999695,
|
5599 |
+
"reward_std": 0.5730939134955406,
|
5600 |
+
"rewards/accessibility_reward_func": 0.3529166840016842,
|
5601 |
+
"rewards/animation_reward_func": 0.31333331763744354,
|
5602 |
+
"rewards/color_theory_reward_func": 0.32491666823625565,
|
5603 |
+
"rewards/design_system_reward_func": 0.9583333432674408,
|
5604 |
+
"rewards/element_spacing_reward_func": 0.16266172751784325,
|
5605 |
+
"rewards/enhanced_html_validity_reward_func": 0.08733333647251129,
|
5606 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.7975000143051147,
|
5607 |
+
"rewards/general_responsiveness_reward_func": 0.06200000271201134,
|
5608 |
+
"rewards/hover_reward_func": 0.17250000685453415,
|
5609 |
+
"rewards/image_size_reward_func": 0.06237500533461571,
|
5610 |
+
"rewards/interactivity_reward_func": 0.5750000178813934,
|
5611 |
+
"rewards/link_validity_reward_func": 0.045125000178813934,
|
5612 |
+
"rewards/lorem_picsum_reward_func": 0.004125000152271241,
|
5613 |
+
"rewards/mobile_responsiveness_reward_func": 0.004666667082346976,
|
5614 |
+
"rewards/section_size_reward_func": 0.0,
|
5615 |
+
"rewards/tailwind_cdn_reward_func": 0.06416666693985462,
|
5616 |
+
"rewards/text_contrast_reward_func": 0.014999999199062586,
|
5617 |
+
"rewards/think_tag_reward_func": 0.038333332166075706,
|
5618 |
+
"rewards/visual_hierarchy_reward_func": 0.05889130849391222,
|
5619 |
+
"step": 187
|
5620 |
+
},
|
5621 |
+
{
|
5622 |
+
"completion_length": 4366.58349609375,
|
5623 |
+
"epoch": 0.9728331177231565,
|
5624 |
+
"grad_norm": 0.12027338892221451,
|
5625 |
+
"kl": 0.00580338086001575,
|
5626 |
+
"learning_rate": 4.8776412907378845e-06,
|
5627 |
+
"loss": 0.0002,
|
5628 |
+
"reward": 3.818458616733551,
|
5629 |
+
"reward_std": 0.35089266300201416,
|
5630 |
+
"rewards/accessibility_reward_func": 0.2689166683703661,
|
5631 |
+
"rewards/animation_reward_func": 0.2656666599214077,
|
5632 |
+
"rewards/color_theory_reward_func": 0.3505833372473717,
|
5633 |
+
"rewards/design_system_reward_func": 1.0,
|
5634 |
+
"rewards/element_spacing_reward_func": 0.16488546878099442,
|
5635 |
+
"rewards/enhanced_html_validity_reward_func": 0.08216667175292969,
|
5636 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.6625000312924385,
|
5637 |
+
"rewards/general_responsiveness_reward_func": 0.040750001557171345,
|
5638 |
+
"rewards/hover_reward_func": 0.15050000697374344,
|
5639 |
+
"rewards/image_size_reward_func": 0.05187500035390258,
|
5640 |
+
"rewards/interactivity_reward_func": 0.5675000175833702,
|
5641 |
+
"rewards/link_validity_reward_func": 0.02700000023469329,
|
5642 |
+
"rewards/lorem_picsum_reward_func": 0.0037083333008922637,
|
5643 |
+
"rewards/mobile_responsiveness_reward_func": 0.0020000001532025635,
|
5644 |
+
"rewards/section_size_reward_func": 0.0011666667414829135,
|
5645 |
+
"rewards/tailwind_cdn_reward_func": 0.06416666693985462,
|
5646 |
+
"rewards/text_contrast_reward_func": 0.01249999925494194,
|
5647 |
+
"rewards/think_tag_reward_func": 0.03999999910593033,
|
5648 |
+
"rewards/visual_hierarchy_reward_func": 0.06257313303649426,
|
5649 |
+
"step": 188
|
5650 |
+
},
|
5651 |
+
{
|
5652 |
+
"completion_length": 5808.95849609375,
|
5653 |
+
"epoch": 0.9780077619663649,
|
5654 |
+
"grad_norm": 0.14726081490516663,
|
5655 |
+
"kl": 0.006095506600104272,
|
5656 |
+
"learning_rate": 4.874046790996253e-06,
|
5657 |
+
"loss": 0.0002,
|
5658 |
+
"reward": 3.9704654812812805,
|
5659 |
+
"reward_std": 0.6006486788392067,
|
5660 |
+
"rewards/accessibility_reward_func": 0.27533334121108055,
|
5661 |
+
"rewards/animation_reward_func": 0.3293333239853382,
|
5662 |
+
"rewards/color_theory_reward_func": 0.29225000739097595,
|
5663 |
+
"rewards/design_system_reward_func": 0.9583333432674408,
|
5664 |
+
"rewards/element_spacing_reward_func": 0.15639718621969223,
|
5665 |
+
"rewards/enhanced_html_validity_reward_func": 0.08550000190734863,
|
5666 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8187500387430191,
|
5667 |
+
"rewards/general_responsiveness_reward_func": 0.05500000063329935,
|
5668 |
+
"rewards/hover_reward_func": 0.16700001060962677,
|
5669 |
+
"rewards/image_size_reward_func": 0.03050000173971057,
|
5670 |
+
"rewards/interactivity_reward_func": 0.5735000297427177,
|
5671 |
+
"rewards/link_validity_reward_func": 0.03525000158697367,
|
5672 |
+
"rewards/lorem_picsum_reward_func": 0.00320833339355886,
|
5673 |
+
"rewards/mobile_responsiveness_reward_func": 0.0,
|
5674 |
+
"rewards/section_size_reward_func": 0.0,
|
5675 |
+
"rewards/tailwind_cdn_reward_func": 0.06708333361893892,
|
5676 |
+
"rewards/text_contrast_reward_func": 0.028333333786576986,
|
5677 |
+
"rewards/think_tag_reward_func": 0.038333332166075706,
|
5678 |
+
"rewards/visual_hierarchy_reward_func": 0.05635991599410772,
|
5679 |
+
"step": 189
|
5680 |
+
},
|
5681 |
+
{
|
5682 |
+
"completion_length": 5225.416748046875,
|
5683 |
+
"epoch": 0.9831824062095731,
|
5684 |
+
"grad_norm": 0.1431666761636734,
|
5685 |
+
"kl": 0.005931958789005876,
|
5686 |
+
"learning_rate": 4.870401618977415e-06,
|
5687 |
+
"loss": 0.0002,
|
5688 |
+
"reward": 3.9108617305755615,
|
5689 |
+
"reward_std": 0.5758266597986221,
|
5690 |
+
"rewards/accessibility_reward_func": 0.23741666786372662,
|
5691 |
+
"rewards/animation_reward_func": 0.29100000113248825,
|
5692 |
+
"rewards/color_theory_reward_func": 0.3045000061392784,
|
5693 |
+
"rewards/design_system_reward_func": 0.9583333432674408,
|
5694 |
+
"rewards/element_spacing_reward_func": 0.15568608790636063,
|
5695 |
+
"rewards/enhanced_html_validity_reward_func": 0.08291667141020298,
|
5696 |
+
"rewards/framer_aesthetic_bonus_reward_func": 0.8087500184774399,
|
5697 |
+
"rewards/general_responsiveness_reward_func": 0.059250001795589924,
|
5698 |
+
"rewards/hover_reward_func": 0.17250000685453415,
|
5699 |
+
"rewards/image_size_reward_func": 0.04575000191107392,
|
5700 |
+
"rewards/interactivity_reward_func": 0.5740000009536743,
|
5701 |
+
"rewards/link_validity_reward_func": 0.03550000116229057,
|
5702 |
+
"rewards/lorem_picsum_reward_func": 0.003249999979743734,
|
5703 |
+
"rewards/mobile_responsiveness_reward_func": 0.004666666965931654,
|
5704 |
+
"rewards/section_size_reward_func": 0.0,
|
5705 |
+
"rewards/tailwind_cdn_reward_func": 0.05833333358168602,
|
5706 |
+
"rewards/text_contrast_reward_func": 0.02416666503995657,
|
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,
|