Hugging Face's logo

gijs
/
astc

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
gijs commited on
Commit
7b58d27
·
verified ·
1 Parent(s): 9e9ddb6

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +57 -0
  2. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/adapter_model.safetensors +3 -0
  3. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/optimizer.pt +3 -0
  4. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/rng_state.pth +3 -0
  5. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/scheduler.pt +3 -0
  6. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/tokenizer.json +3 -0
  7. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/training_args.bin +3 -0
  8. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/adapter_model.safetensors +3 -0
  9. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/optimizer.pt +3 -0
  10. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/rng_state.pth +3 -0
  11. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/scheduler.pt +3 -0
  12. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/tokenizer.json +3 -0
  13. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/training_args.bin +3 -0
  14. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/adapter_model.safetensors +3 -0
  15. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/optimizer.pt +3 -0
  16. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/rng_state.pth +3 -0
  17. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/scheduler.pt +3 -0
  18. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/tokenizer.json +3 -0
  19. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/training_args.bin +3 -0
  20. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/adapter_model.safetensors +3 -0
  21. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/optimizer.pt +3 -0
  22. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/rng_state.pth +3 -0
  23. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/scheduler.pt +3 -0
  24. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/tokenizer.json +3 -0
  25. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/training_args.bin +3 -0
  26. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/adapter_model.safetensors +3 -0
  27. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/optimizer.pt +3 -0
  28. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/rng_state.pth +3 -0
  29. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/scheduler.pt +3 -0
  30. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/tokenizer.json +3 -0
  31. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/training_args.bin +3 -0
  32. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/adapter_model.safetensors +3 -0
  33. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/optimizer.pt +3 -0
  34. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/rng_state.pth +3 -0
  35. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/scheduler.pt +3 -0
  36. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/tokenizer.json +3 -0
  37. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/training_args.bin +3 -0
  38. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/adapter_model.safetensors +3 -0
  39. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/optimizer.pt +3 -0
  40. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/rng_state.pth +3 -0
  41. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/scheduler.pt +3 -0
  42. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/tokenizer.json +3 -0
  43. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/training_args.bin +3 -0
  44. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/adapter_model.safetensors +3 -0
  45. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/optimizer.pt +3 -0
  46. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/rng_state.pth +3 -0
  47. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/scheduler.pt +3 -0
  48. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/tokenizer.json +3 -0
  49. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/training_args.bin +3 -0
  50. sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-45280/adapter_model.safetensors +3 -0
.gitattributes CHANGED
@@ -345,3 +345,60 @@ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-26608/
345
  sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-53216/tokenizer.json filter=lfs diff=lfs merge=lfs -text
346
  sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-46564/tokenizer.json filter=lfs diff=lfs merge=lfs -text
347
  sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-21619/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
345
  sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-53216/tokenizer.json filter=lfs diff=lfs merge=lfs -text
346
  sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-46564/tokenizer.json filter=lfs diff=lfs merge=lfs -text
347
  sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-21619/tokenizer.json filter=lfs diff=lfs merge=lfs -text
348
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-36586/tokenizer.json filter=lfs diff=lfs merge=lfs -text
349
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-6652/tokenizer.json filter=lfs diff=lfs merge=lfs -text
350
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-29934/tokenizer.json filter=lfs diff=lfs merge=lfs -text
351
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-48227/tokenizer.json filter=lfs diff=lfs merge=lfs -text
352
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-13304/tokenizer.json filter=lfs diff=lfs merge=lfs -text
353
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-69846/tokenizer.json filter=lfs diff=lfs merge=lfs -text
354
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-56542/tokenizer.json filter=lfs diff=lfs merge=lfs -text
355
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-59868/tokenizer.json filter=lfs diff=lfs merge=lfs -text
356
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-61531/tokenizer.json filter=lfs diff=lfs merge=lfs -text
357
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-74835/tokenizer.json filter=lfs diff=lfs merge=lfs -text
358
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-78161/tokenizer.json filter=lfs diff=lfs merge=lfs -text
359
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-31597/tokenizer.json filter=lfs diff=lfs merge=lfs -text
360
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-79868/tokenizer.json filter=lfs diff=lfs merge=lfs -text
361
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-18293/tokenizer.json filter=lfs diff=lfs merge=lfs -text
362
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-38249/tokenizer.json filter=lfs diff=lfs merge=lfs -text
363
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-9978/tokenizer.json filter=lfs diff=lfs merge=lfs -text
364
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-43238/tokenizer.json filter=lfs diff=lfs merge=lfs -text
365
+ sft/20250428_225638_sftqwenomni-semantic-loraopt-3e-8bs-0.0002/checkpoint-71509/tokenizer.json filter=lfs diff=lfs merge=lfs -text
366
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-16635/tokenizer.json filter=lfs diff=lfs merge=lfs -text
367
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-9981/tokenizer.json filter=lfs diff=lfs merge=lfs -text
368
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-11090/tokenizer.json filter=lfs diff=lfs merge=lfs -text
369
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-15526/tokenizer.json filter=lfs diff=lfs merge=lfs -text
370
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-7763/tokenizer.json filter=lfs diff=lfs merge=lfs -text
371
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-6654/tokenizer.json filter=lfs diff=lfs merge=lfs -text
372
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-12199/tokenizer.json filter=lfs diff=lfs merge=lfs -text
373
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-3327/tokenizer.json filter=lfs diff=lfs merge=lfs -text
374
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-2218/tokenizer.json filter=lfs diff=lfs merge=lfs -text
375
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-17744/tokenizer.json filter=lfs diff=lfs merge=lfs -text
376
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-14417/tokenizer.json filter=lfs diff=lfs merge=lfs -text
377
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-1109/tokenizer.json filter=lfs diff=lfs merge=lfs -text
378
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-4436/tokenizer.json filter=lfs diff=lfs merge=lfs -text
379
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-13308/tokenizer.json filter=lfs diff=lfs merge=lfs -text
380
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-8872/tokenizer.json filter=lfs diff=lfs merge=lfs -text
381
+ sft/20250428_140002_sftqwenomni-semantic-loraopt-3e-12bs-0.0002/checkpoint-5545/tokenizer.json filter=lfs diff=lfs merge=lfs -text
382
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-81514/tokenizer.json filter=lfs diff=lfs merge=lfs -text
383
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/tokenizer.json filter=lfs diff=lfs merge=lfs -text
384
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-49808/tokenizer.json filter=lfs diff=lfs merge=lfs -text
385
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-72448/tokenizer.json filter=lfs diff=lfs merge=lfs -text
386
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/tokenizer.json filter=lfs diff=lfs merge=lfs -text
387
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-58864/tokenizer.json filter=lfs diff=lfs merge=lfs -text
388
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/tokenizer.json filter=lfs diff=lfs merge=lfs -text
389
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-67920/tokenizer.json filter=lfs diff=lfs merge=lfs -text
390
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/tokenizer.json filter=lfs diff=lfs merge=lfs -text
391
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-54336/tokenizer.json filter=lfs diff=lfs merge=lfs -text
392
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-63392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
393
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-45280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
394
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/tokenizer.json filter=lfs diff=lfs merge=lfs -text
395
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-76976/tokenizer.json filter=lfs diff=lfs merge=lfs -text
396
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
397
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/tokenizer.json filter=lfs diff=lfs merge=lfs -text
398
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/tokenizer.json filter=lfs diff=lfs merge=lfs -text
399
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-9056/tokenizer.json filter=lfs diff=lfs merge=lfs -text
400
+ sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-81504/tokenizer.json filter=lfs diff=lfs merge=lfs -text
401
+ sft/20250419_012050_sftqwen2a-full-resume-goodcpkt-loraopt-5e-16bs-0.0002/checkpoint-43582/tokenizer.json filter=lfs diff=lfs merge=lfs -text
402
+ sft/20250419_012050_sftqwen2a-full-resume-goodcpkt-loraopt-5e-16bs-0.0002/checkpoint-9339/tokenizer.json filter=lfs diff=lfs merge=lfs -text
403
+ sft/20250419_012050_sftqwen2a-full-resume-goodcpkt-loraopt-5e-16bs-0.0002/checkpoint-12452/tokenizer.json filter=lfs diff=lfs merge=lfs -text
404
+ sft/20250419_012050_sftqwen2a-full-resume-goodcpkt-loraopt-5e-16bs-0.0002/checkpoint-40469/tokenizer.json filter=lfs diff=lfs merge=lfs -text
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adc894660846e98b941e10fd422b225e5e52e659c533846f911a78fb625803b9
3
+ size 22056664
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9310a00f80e53e9d3d920df91e7016a2691f194c1a818dc6049e29a06f4f69f
3
+ size 44254970
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21958c3b1bf9bff58f45fc448034997067095aff0a65e4d309420654d1d65bac
3
+ size 14244
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab96993d5b37027193b6b9ea7c4227be08a18653086bc70b05c0c67675d94647
3
+ size 1064
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-13584/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7d7c38e0bf12e73877227de39489b726d8b17c6cd96fc1bbd07e52eec663e8
3
+ size 5944
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e26973e5e9a4d771080de79f04a1da29fb4bdbff07caf7048efbe09ca135bc40
3
+ size 22056664
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfbfc9f1eb13e293f7b33e1acc4e2ae1113b96d27d2a51a9ead105c030e48d42
3
+ size 44254970
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e679042e73c4268dbc2dee6e305ab35cb9f2a17ffba488606fd7e57cf1c0e615
3
+ size 14244
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88ed2193548c2f6a6cdda456b7a63b7ebdab0112ae79b61b277bc8a0c6a0752d
3
+ size 1064
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-18112/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7d7c38e0bf12e73877227de39489b726d8b17c6cd96fc1bbd07e52eec663e8
3
+ size 5944
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e211ba09daf707fe2df198d1625ad4623b628eb64331c2d93701ffe44772c569
3
+ size 22056664
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c45edde3d082b1d1969badfc809b684b42a494e37f46061003e97a88be2cddc6
3
+ size 44254970
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c902e6e8b413fe9d314896e1e71b138f7bd32367a98b69beeac55b77f5740677
3
+ size 14244
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c241da0edeb46c419466d9adb8d8cbae7efcb277dd36303dc16d0c180d931f8f
3
+ size 1064
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-22640/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7d7c38e0bf12e73877227de39489b726d8b17c6cd96fc1bbd07e52eec663e8
3
+ size 5944
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddab17c4ab1e7e80be8554b4536d805d4d1abb7ef849e46a8d3cc90e4e483019
3
+ size 22056664
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37997deb591131777f0e97fe491e6e67f3ec7d41bd0e53f12235758f0ae86b9
3
+ size 44254970
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2f8f4c024377bea3da18e01af63be4b15ff9c307b33027e7dc929cbabc98af9
3
+ size 14244
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9555c5dc016aafd702a8ba32ff226df5e38292139b047c42b1c561e48eb271a8
3
+ size 1064
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-27168/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7d7c38e0bf12e73877227de39489b726d8b17c6cd96fc1bbd07e52eec663e8
3
+ size 5944
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c8ce64ca6f1b1a36f26b453992a8b320d65d6de6d47e0623dd6d7d34198ef3
3
+ size 22056664
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da93615366d77de706356569930be5e45ffa5df799a405d229c9024aa3740baf
3
+ size 44254970
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30de274f8e1790813404088ebf558a743a849eae852687891435328da4382241
3
+ size 14244
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4e48950bb7b116c29facba11760a6cdd2a09f3c6ca51a48a92511874fcda08
3
+ size 1064
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-31696/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7d7c38e0bf12e73877227de39489b726d8b17c6cd96fc1bbd07e52eec663e8
3
+ size 5944
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd24337ffdd3a406971a2c5104c62b973bbb0749830042a3c1a9da3ea0adf5ee
3
+ size 22056664
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386f1cfeda1fdd9d955ed398536cfe661b74d6c9e20682ce1854596b6aaceb13
3
+ size 44254970
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384777b3e7a198e15a18acfb6533db1449f17743c2456b6bcb8f8e86c0ad0fba
3
+ size 14244
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:594948abdc0233ecece11ac308e08ce5e2875920c98f7bcb8a6d4f0ddf7b8f66
3
+ size 1064
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-36224/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7d7c38e0bf12e73877227de39489b726d8b17c6cd96fc1bbd07e52eec663e8
3
+ size 5944
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece1c1de04ef119b6443798d3659e22c9a5943caa217f2f29c0d95cfb3814d23
3
+ size 22056664
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229431d5915cd7922daa26ea8248d9c573c81bbd50e73ab3a86cfa67aafd252e
3
+ size 44254970
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a623b11aa1522aa8a7326f47b3d34cc8abbd5623a4d60607da8ad908745e8cc4
3
+ size 14244
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c07cc96b5002e3c882caaa466a44d1992c538a9ec7381c1206c29a9431180d13
3
+ size 1064
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-40752/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7d7c38e0bf12e73877227de39489b726d8b17c6cd96fc1bbd07e52eec663e8
3
+ size 5944
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce7a48968e3b76a8db472c0afb59aef1bd5970cd8add7f89c2837661f743487b
3
+ size 22056664
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f2c16e7673ff1c12863a8e4a5f895fa73e4ab2e813288b207bd9fa296a8d7c5
3
+ size 44254970
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b079252cf403360800949ec2834862f97cd2e7d781aab7888d978d03969bc5e
3
+ size 14244
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f565192a2b9c1d775727fa4d3fcdd3184ad367691d420435866209618f364817
3
+ size 1064
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-4528/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7d7c38e0bf12e73877227de39489b726d8b17c6cd96fc1bbd07e52eec663e8
3
+ size 5944
sft/20250407_113205_sfttraining_qwen2.5_semantic-loraopt-3e-6bs-0.0002/checkpoint-45280/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a098934adc225ef31dc14b559a3fe85bf6911397b4c160cf031d94e3fb40e8c
3
+ size 22056664