Hugging Face's logo

kishan51
/
llm-zero-lite-experiments

Reinforcement Learning
PEFT
Safetensors
grpo
countdown
llm-controller
qwen3
Model card Files
xet
 Community
kishan51 commited on
Commit
1552961
·
verified ·
1 Parent(s): 2281119

Add files using upload-large-folder tool

Browse files
Files changed (31) hide show
  1. .gitattributes +6 -0
  2. runs/continuous_long_seed42/trainer_output/checkpoint-1000/optimizer.pt +3 -0
  3. runs/continuous_long_seed42/trainer_output/checkpoint-400/optimizer.pt +3 -0
  4. runs/continuous_long_seed42/trainer_output/checkpoint-600/optimizer.pt +3 -0
  5. runs/continuous_long_seed42/trainer_output/checkpoint-800/optimizer.pt +3 -0
  6. runs/continuous_seed42/trainer_output/checkpoint-100/adapter_model.safetensors +3 -0
  7. runs/continuous_seed42/trainer_output/checkpoint-200/adapter_model.safetensors +3 -0
  8. runs/continuous_seed42/trainer_output/checkpoint-300/adapter_model.safetensors +3 -0
  9. runs/continuous_seed42/trainer_output/checkpoint-400/adapter_model.safetensors +3 -0
  10. runs/llm_long_seed42/stage_0/checkpoint/tokenizer.json +3 -0
  11. runs/llm_long_seed42/stage_0/checkpoint/training_args.bin +3 -0
  12. runs/llm_long_seed42/stage_1/checkpoint/ref/adapter_model.safetensors +3 -0
  13. runs/llm_long_seed42/stage_1/checkpoint/tokenizer.json +3 -0
  14. runs/llm_long_seed42/stage_1/checkpoint/training_args.bin +3 -0
  15. runs/llm_long_seed42/stage_2/checkpoint/tokenizer.json +3 -0
  16. runs/llm_long_seed42/stage_2/checkpoint/training_args.bin +3 -0
  17. runs/llm_long_seed42/stage_3/checkpoint/ref/adapter_model.safetensors +3 -0
  18. runs/llm_long_seed42/stage_3/checkpoint/tokenizer.json +3 -0
  19. runs/llm_long_seed42/stage_4/checkpoint/ref/adapter_model.safetensors +3 -0
  20. runs/llm_long_seed42/stage_4/checkpoint/tokenizer.json +3 -0
  21. runs/llm_long_seed42/stage_4/checkpoint/training_args.bin +3 -0
  22. runs/smoke_continuous/trainer_output/checkpoint-20/optimizer.pt +3 -0
  23. runs/smoke_continuous/trainer_output/checkpoint-20/rng_state.pth +3 -0
  24. runs/smoke_continuous/trainer_output/checkpoint-20/scheduler.pt +3 -0
  25. runs/smoke_continuous/trainer_output/checkpoint-20/training_args.bin +3 -0
  26. runs/smoke_continuous/trainer_output/checkpoint-40/optimizer.pt +3 -0
  27. runs/smoke_continuous/trainer_output/checkpoint-40/scheduler.pt +3 -0
  28. runs/smoke_staged/stage_0/checkpoint/tokenizer.json +3 -0
  29. runs/smoke_staged/stage_0/checkpoint/training_args.bin +3 -0
  30. runs/staged_fixed_long_seed42/stage_1/checkpoint/adapter_model.safetensors +3 -0
  31. runs/staged_fixed_long_seed42/stage_4/checkpoint/adapter_model.safetensors +3 -0
.gitattributes CHANGED
@@ -58,3 +58,9 @@ runs/continuous_seed42/trainer_output/checkpoint-200/tokenizer.json filter=lfs d
58
  runs/continuous_seed42/trainer_output/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
  runs/continuous_seed42/trainer_output/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
60
  runs/continuous_seed42/trainer_output/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
58
  runs/continuous_seed42/trainer_output/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
  runs/continuous_seed42/trainer_output/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
60
  runs/continuous_seed42/trainer_output/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
61
+ runs/llm_long_seed42/stage_3/checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
62
+ runs/llm_long_seed42/stage_1/checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
63
+ runs/llm_long_seed42/stage_4/checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
64
+ runs/llm_long_seed42/stage_2/checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
65
+ runs/llm_long_seed42/stage_0/checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
66
+ runs/smoke_staged/stage_0/checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
runs/continuous_long_seed42/trainer_output/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bf38bcd7bd2e69d3619775d7e78ae5a16e4f664e8af59c30bf2d07299a4045f
3
+ size 279257723
runs/continuous_long_seed42/trainer_output/checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75b1f628d808c5b39f8cbb7f9618be23b89afd9718f857313b6631e0903012b0
3
+ size 279257723
runs/continuous_long_seed42/trainer_output/checkpoint-600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3c42cb62e9b0166d73fe32ff25028f36a5ba7ac432711772665fcec13c79bbe
3
+ size 279257723
runs/continuous_long_seed42/trainer_output/checkpoint-800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c67e5fe2a56270ea0d7ee3efb4600022a2a0a48d8a488f6cb2514e848a723a3
3
+ size 279257723
runs/continuous_seed42/trainer_output/checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda0e21207a6bbb50f7f8fc1ba651d56a83ca8715ab33e5c88ce1a64ad8c9f4d
3
+ size 139512976
runs/continuous_seed42/trainer_output/checkpoint-200/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d8c9cd09bcbc60d928827e0c610340a9c10ea4753507e173c391652cc5bfe0d
3
+ size 139512976
runs/continuous_seed42/trainer_output/checkpoint-300/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4684ec0f4f6aa7d33ffb2a76307f5ad80134ee6f599a484db14f17e57f6ea9c4
3
+ size 139512976
runs/continuous_seed42/trainer_output/checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31cf9fb004d8085d308f5fd5574e26e7dd536e1b3be9cf11f57c90c2e541a6c
3
+ size 139512976
runs/llm_long_seed42/stage_0/checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
3
+ size 11422821
runs/llm_long_seed42/stage_0/checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c270fcea6c80028c2d3188a2486abaafc084a6271c6c53b62a2e459f7a190a42
3
+ size 7889
runs/llm_long_seed42/stage_1/checkpoint/ref/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4300b4519a84cdabc41228250d5995d786f26716f7d52f50cc1cfa6afb95eb5
3
+ size 69782776
runs/llm_long_seed42/stage_1/checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
3
+ size 11422821
runs/llm_long_seed42/stage_1/checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29045672d2b7f8c479d52cc0725f3898781755363e304fe2e2a1888b5006cf3
3
+ size 7889
runs/llm_long_seed42/stage_2/checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
3
+ size 11422821
runs/llm_long_seed42/stage_2/checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd36f9fbad51d09944c480c85cae0cd562e8924f9fec0683adcc3a56482eb55
3
+ size 7889
runs/llm_long_seed42/stage_3/checkpoint/ref/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7d9956a37770e798f4819cc530d45f0ced968b91192e1fd6a5fa034405a625b
3
+ size 69782776
runs/llm_long_seed42/stage_3/checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
3
+ size 11422821
runs/llm_long_seed42/stage_4/checkpoint/ref/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4945934bc34e5b8f6ae5c07ebc31bc431357c80e9dac41ffb91a0b7d02f9134c
3
+ size 69782776
runs/llm_long_seed42/stage_4/checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
3
+ size 11422821
runs/llm_long_seed42/stage_4/checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04294bffdb8f5a9936251140d29bbc07baa14ff8c7b1d18cbfa0789585769bfd
3
+ size 7889
runs/smoke_continuous/trainer_output/checkpoint-20/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a850d8eb66ddcff76a7d5cbbfa2163c8e5b75e2138035f7253c9b94ca2416fa
3
+ size 279257723
runs/smoke_continuous/trainer_output/checkpoint-20/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b5941602ce1dc5d2414eadb44f3c14de4ee9f9399daa0fb67d36877c8c88f5
3
+ size 14581
runs/smoke_continuous/trainer_output/checkpoint-20/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b065d40c66adf857942506e6305b78a47a74d9596ada2628c785bc6786bed5
3
+ size 1465
runs/smoke_continuous/trainer_output/checkpoint-20/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53536b31a2c9395fac3de28a21407723d9eb16f6d2218bed70e37b789c27fae3
3
+ size 7825
runs/smoke_continuous/trainer_output/checkpoint-40/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72a77b6463ce59c64d945e1edb8e013ef2e5b00174e93fabf95befdd207d9e2b
3
+ size 279257723
runs/smoke_continuous/trainer_output/checkpoint-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e07c9166a1deb6063d13ec8260522195b300234dce529e1da112d49243d8b9
3
+ size 1465
runs/smoke_staged/stage_0/checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
3
+ size 11422821
runs/smoke_staged/stage_0/checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5795c3b63551855e7bbb656e34c7c447598e5a04e39a7f6b4bcd0c3d2fcf3be1
3
+ size 7825
runs/staged_fixed_long_seed42/stage_1/checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6706591430acacaeddf23ec450a7f5b4ec5840dffd0857b08b8b102a930a8f
3
+ size 139512976
runs/staged_fixed_long_seed42/stage_4/checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d9a2572c8caa009857002d9e1743a00f15add1a6855312e19eac005b4697c2f
3
+ size 139512976