Hugging Face's logo

gijs
/
astc

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
gijs commited on
Commit
b23f490
·
verified ·
1 Parent(s): ebc504e

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 +26 -0
  2. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/adapter_model.safetensors +3 -0
  3. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/optimizer.pt +3 -0
  4. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/rng_state.pth +3 -0
  5. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/scheduler.pt +3 -0
  6. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/tokenizer.json +3 -0
  7. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/training_args.bin +3 -0
  8. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/adapter_model.safetensors +3 -0
  9. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/optimizer.pt +3 -0
  10. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/rng_state.pth +3 -0
  11. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/scheduler.pt +3 -0
  12. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/tokenizer.json +3 -0
  13. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/training_args.bin +3 -0
  14. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/adapter_model.safetensors +3 -0
  15. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/optimizer.pt +3 -0
  16. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/rng_state.pth +3 -0
  17. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/scheduler.pt +3 -0
  18. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/tokenizer.json +3 -0
  19. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/training_args.bin +3 -0
  20. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/adapter_model.safetensors +3 -0
  21. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/optimizer.pt +3 -0
  22. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/rng_state.pth +3 -0
  23. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/scheduler.pt +3 -0
  24. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/tokenizer.json +3 -0
  25. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/training_args.bin +3 -0
  26. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/adapter_model.safetensors +3 -0
  27. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/optimizer.pt +3 -0
  28. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/rng_state.pth +3 -0
  29. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/scheduler.pt +3 -0
  30. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/tokenizer.json +3 -0
  31. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/training_args.bin +3 -0
  32. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/adapter_model.safetensors +3 -0
  33. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/optimizer.pt +3 -0
  34. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/rng_state.pth +3 -0
  35. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/scheduler.pt +3 -0
  36. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/tokenizer.json +3 -0
  37. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/training_args.bin +3 -0
  38. sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/runs/Mar06_07-54-35_gcn120.local.snellius.surf.nl/events.out.tfevents.1741244077.gcn120.local.snellius.surf.nl.538532.0 +3 -0
  39. sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/adapter_model.safetensors +3 -0
  40. sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/optimizer.pt +3 -0
  41. sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/rng_state.pth +3 -0
  42. sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/scheduler.pt +3 -0
  43. sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/tokenizer.json +3 -0
  44. sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/training_args.bin +3 -0
  45. sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/adapter_model.safetensors +3 -0
  46. sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/optimizer.pt +3 -0
  47. sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/rng_state.pth +3 -0
  48. sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/scheduler.pt +3 -0
  49. sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/tokenizer.json +3 -0
  50. sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/training_args.bin +3 -0
.gitattributes CHANGED
@@ -951,3 +951,29 @@ sft/20250428_122030_sftqwen2a-semantic-fullyscratch-loraopt-5e-8bs-0.0002/checkp
951
  sft/20250428_122030_sftqwen2a-semantic-fullyscratch-loraopt-5e-8bs-0.0002/checkpoint-4989/tokenizer.json filter=lfs diff=lfs merge=lfs -text
952
  sft/20250428_122030_sftqwen2a-semantic-fullyscratch-loraopt-5e-8bs-0.0002/checkpoint-23282/tokenizer.json filter=lfs diff=lfs merge=lfs -text
953
  sft/20250428_122030_sftqwen2a-semantic-fullyscratch-loraopt-5e-8bs-0.0002/checkpoint-21619/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
951
  sft/20250428_122030_sftqwen2a-semantic-fullyscratch-loraopt-5e-8bs-0.0002/checkpoint-4989/tokenizer.json filter=lfs diff=lfs merge=lfs -text
952
  sft/20250428_122030_sftqwen2a-semantic-fullyscratch-loraopt-5e-8bs-0.0002/checkpoint-23282/tokenizer.json filter=lfs diff=lfs merge=lfs -text
953
  sft/20250428_122030_sftqwen2a-semantic-fullyscratch-loraopt-5e-8bs-0.0002/checkpoint-21619/tokenizer.json filter=lfs diff=lfs merge=lfs -text
954
+ sft/20250429_133137_sftqwenomni-fullsemantic-loraopt-1e-8bs-0.0002/checkpoint-87178/tokenizer.json filter=lfs diff=lfs merge=lfs -text
955
+ sft/20250429_133137_sftqwenomni-fullsemantic-loraopt-1e-8bs-0.0002/checkpoint-24908/tokenizer.json filter=lfs diff=lfs merge=lfs -text
956
+ sft/20250429_133137_sftqwenomni-fullsemantic-loraopt-1e-8bs-0.0002/checkpoint-93405/tokenizer.json filter=lfs diff=lfs merge=lfs -text
957
+ sft/20250422_193550_sftqwen2a-sem-nolora-noneopt-5e-4bs-0.0002/checkpoint-36597/tokenizer.json filter=lfs diff=lfs merge=lfs -text
958
+ sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/tokenizer.json filter=lfs diff=lfs merge=lfs -text
959
+ sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/tokenizer.json filter=lfs diff=lfs merge=lfs -text
960
+ sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/tokenizer.json filter=lfs diff=lfs merge=lfs -text
961
+ sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/tokenizer.json filter=lfs diff=lfs merge=lfs -text
962
+ sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/tokenizer.json filter=lfs diff=lfs merge=lfs -text
963
+ sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/tokenizer.json filter=lfs diff=lfs merge=lfs -text
964
+ sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/tokenizer.json filter=lfs diff=lfs merge=lfs -text
965
+ sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-59238/tokenizer.json filter=lfs diff=lfs merge=lfs -text
966
+ sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/tokenizer.json filter=lfs diff=lfs merge=lfs -text
967
+ sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-49365/tokenizer.json filter=lfs diff=lfs merge=lfs -text
968
+ sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-9873/tokenizer.json filter=lfs diff=lfs merge=lfs -text
969
+ sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-69111/tokenizer.json filter=lfs diff=lfs merge=lfs -text
970
+ sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-39492/tokenizer.json filter=lfs diff=lfs merge=lfs -text
971
+ sft/20250422_192334_sftqwen2a-resume-semantic-loraopt-10e-8bs-1e-05/checkpoint-11641/tokenizer.json filter=lfs diff=lfs merge=lfs -text
972
+ sft/20250422_192334_sftqwen2a-resume-semantic-loraopt-10e-8bs-1e-05/checkpoint-16630/tokenizer.json filter=lfs diff=lfs merge=lfs -text
973
+ sft/20250422_192334_sftqwen2a-resume-semantic-loraopt-10e-8bs-1e-05/checkpoint-1663/tokenizer.json filter=lfs diff=lfs merge=lfs -text
974
+ sft/20250422_192334_sftqwen2a-resume-semantic-loraopt-10e-8bs-1e-05/checkpoint-14967/tokenizer.json filter=lfs diff=lfs merge=lfs -text
975
+ sft/20250422_192334_sftqwen2a-resume-semantic-loraopt-10e-8bs-1e-05/checkpoint-8315/tokenizer.json filter=lfs diff=lfs merge=lfs -text
976
+ sft/20250422_192334_sftqwen2a-resume-semantic-loraopt-10e-8bs-1e-05/checkpoint-24945/tokenizer.json filter=lfs diff=lfs merge=lfs -text
977
+ sft/20250422_192334_sftqwen2a-resume-semantic-loraopt-10e-8bs-1e-05/checkpoint-3326/tokenizer.json filter=lfs diff=lfs merge=lfs -text
978
+ sft/20250422_192334_sftqwen2a-resume-semantic-loraopt-10e-8bs-1e-05/checkpoint-19956/tokenizer.json filter=lfs diff=lfs merge=lfs -text
979
+ sft/20250422_192334_sftqwen2a-resume-semantic-loraopt-10e-8bs-1e-05/checkpoint-4989/tokenizer.json filter=lfs diff=lfs merge=lfs -text
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660ef5b561a8996a7b4714653010347c5c80b7fa4f516187d14b6e86ce7824c2
3
+ size 22056664
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eccd355d7df733a942224be1a56a7b434462cb70da3b1486964a6b478832ff31
3
+ size 44254970
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf82c94f7efbe943489a6b705dfdc6f64ecbd05f9f6647f40c3c1981b81c83b6
3
+ size 14244
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44227b061f4948a26b828d1b5f0cb00b3ad435aa83f0c9eb0514020a1d776260
3
+ size 1064
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-1856/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae6fa5711d8aa22f48fb9238292035fa3d9a34fb0b637bcb7b170f9129168d4b
3
+ size 5880
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee825acd71357e202dacbd421f8faf47efd30c210c6db0e94d04a858a75e65b2
3
+ size 22056664
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac59d4f64701ae2e9b69506a7c4f94ed05aa7bb2f39722a42abf423c61e17778
3
+ size 44254970
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ca1c02fb06427cc45af59f5b872aab7bbdeea9048a5f93279af167e5d7e3908
3
+ size 14244
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c9407c24ff791b760d181c94873b360e1930dd88e14ababffc107a48ee14856
3
+ size 1064
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-3712/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae6fa5711d8aa22f48fb9238292035fa3d9a34fb0b637bcb7b170f9129168d4b
3
+ size 5880
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c23cf3066c06e25299c1b1d8ee2983c03d2fc01b078f1307cf4b92acb83ab95
3
+ size 22056664
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343262e8c66ed54b3ef1d4d5cbba9ebbf167932bc0990ac4a3edfbf9e3c61c04
3
+ size 44254970
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16647c07cf93fb7f2a66737a419ebf0bbe188b47bffdba8afe8b82c1491e778f
3
+ size 14244
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a82dec750182aed3b47eb6532f4e332681c09277e8b114aa8414430b7ce8116
3
+ size 1064
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-5568/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae6fa5711d8aa22f48fb9238292035fa3d9a34fb0b637bcb7b170f9129168d4b
3
+ size 5880
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3013ab451a9a15abcc34d0cd2cbe7c9eaab5136a57c8053b94aa3701f6491772
3
+ size 22056664
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd1767266864d847db675da4affd7e3d7c31589f1c39ed435ec2a897487222d
3
+ size 44254970
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6ab1a1b05f28b8dc057aaf48ec573a563c80e3ac4d0c567992a684dcbaf4607
3
+ size 14244
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce1b52f2d0d0672e7a488e92988265a1ede8a4844e69c77fc17053899d682895
3
+ size 1064
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-7424/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae6fa5711d8aa22f48fb9238292035fa3d9a34fb0b637bcb7b170f9129168d4b
3
+ size 5880
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2720257feb4ab20b26cff01523b6b4abc657abb34e9590145295674feff35ccc
3
+ size 22056664
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f39bc4004941b3a89534de0a213c667a0f7e46b583b59524d8f02f4be04fe89
3
+ size 44254970
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa6695ad240c6b489663337e6db10d40887d4cb8c4b22a6cde2f29a43a050bf
3
+ size 14244
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba7d3458e9fdcfaa3bebca6bb524367c0027f2eac98c18a87debdfd5a7445887
3
+ size 1064
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9280/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae6fa5711d8aa22f48fb9238292035fa3d9a34fb0b637bcb7b170f9129168d4b
3
+ size 5880
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78746238dc22092f8fef322d70e668ffb55077b46c4b22e8b935e3f8e6ff9560
3
+ size 22056664
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7b6027164767903af25d2a0a197c5e044d1676157e60b7ddebb45b7f29f818e
3
+ size 44254970
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92face340385cb92a7402cb2a5346e3946c7ff303ba8f7fcd18de6b45d008c66
3
+ size 14244
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d052ec9e86fd391d22fb127798597d25ea705dbddc399d6f36c1e83059261c20
3
+ size 1064
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/checkpoint-9283/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae6fa5711d8aa22f48fb9238292035fa3d9a34fb0b637bcb7b170f9129168d4b
3
+ size 5880
sft/20250306_075435_sfttraining_qwen2.5_simple_0_20000-loraopt-5e-10bs-0.0002/runs/Mar06_07-54-35_gcn120.local.snellius.surf.nl/events.out.tfevents.1741244077.gcn120.local.snellius.surf.nl.538532.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf4e8c3e537ede126002e0ef361ef590f234ba0f5e639d99db5a57ef966b817
3
+ size 151794
sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ce63425300cd2087c2b8bb73c970da593f5e902a78ee37b3d08adc44d45c967
3
+ size 22056664
sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd14218867e410b7e3adc42e9951ab4363d433d76c846828514fd496785586d1
3
+ size 44254970
sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e310de5c6ab5416e68a174d3a198733f27092cecbb2ada7f84277e2914b7002
3
+ size 14244
sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ff1b37e185dc00b5d4496f77e0376c1ad61e819595c7678b7d23e73a14f429
3
+ size 1064
sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-19746/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f979924fd4d8336365c917d21afaa4a3950602a3ab8c2913ec9b0311467cd8dd
3
+ size 5944
sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:383396a4b5479bef1ba037f17730dc9170540b2c7ac9eee7336320b1afd37c48
3
+ size 22056664
sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adedd6393ecec758c3f9eaa22b66aaee054fdfa9327aa3e0889c432fee60a818
3
+ size 44254970
sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84555b5913a59f11b6ffc6b91ba976bd1c9529d73f17af2adfc62661baa1dc79
3
+ size 14244
sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c51a4425530c878b21176aa94a91eb4ced2973961cc3adfc233885cd3ad39f
3
+ size 1064
sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
3
+ size 12030779
sft/20250406_220017_sfttraining_qwen2.5_simple_qa-loraopt-3e-8bs-0.0002/checkpoint-29619/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f979924fd4d8336365c917d21afaa4a3950602a3ab8c2913ec9b0311467cd8dd
3
+ size 5944