MilaWang commited on
Commit
c905549
·
verified ·
1 Parent(s): 0dcbbc7

Upload folder using huggingface_hub

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 +9 -0
  2. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/README.md +202 -0
  3. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/adapter_config.json +29 -0
  4. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/adapter_model.safetensors +3 -0
  5. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/README.md +202 -0
  6. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/adapter_config.json +29 -0
  7. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/adapter_model.safetensors +3 -0
  8. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/optimizer.pt +3 -0
  9. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/rng_state.pth +3 -0
  10. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/scheduler.pt +3 -0
  11. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/special_tokens_map.json +17 -0
  12. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/tokenizer.json +3 -0
  13. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/tokenizer_config.json +2063 -0
  14. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/trainer_state.json +988 -0
  15. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/training_args.bin +3 -0
  16. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/README.md +202 -0
  17. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/adapter_config.json +29 -0
  18. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/adapter_model.safetensors +3 -0
  19. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/optimizer.pt +3 -0
  20. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/rng_state.pth +3 -0
  21. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/scheduler.pt +3 -0
  22. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/special_tokens_map.json +17 -0
  23. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/tokenizer.json +3 -0
  24. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/tokenizer_config.json +2063 -0
  25. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/trainer_state.json +1311 -0
  26. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/training_args.bin +3 -0
  27. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/README.md +202 -0
  28. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/adapter_config.json +29 -0
  29. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/adapter_model.safetensors +3 -0
  30. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/optimizer.pt +3 -0
  31. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/rng_state.pth +3 -0
  32. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/scheduler.pt +3 -0
  33. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/special_tokens_map.json +17 -0
  34. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/tokenizer.json +3 -0
  35. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/tokenizer_config.json +2063 -0
  36. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/trainer_state.json +1627 -0
  37. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/training_args.bin +3 -0
  38. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/README.md +202 -0
  39. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/adapter_config.json +29 -0
  40. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/adapter_model.safetensors +3 -0
  41. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/optimizer.pt +3 -0
  42. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/rng_state.pth +3 -0
  43. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/scheduler.pt +3 -0
  44. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/special_tokens_map.json +17 -0
  45. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/tokenizer.json +3 -0
  46. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/tokenizer_config.json +2063 -0
  47. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/trainer_state.json +1950 -0
  48. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/training_args.bin +3 -0
  49. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-3115/README.md +202 -0
  50. Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-3115/adapter_config.json +29 -0
.gitattributes CHANGED
@@ -3323,3 +3323,12 @@ Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_
3323
  Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.4-num-1240-sd-10000/checkpoint-608/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3324
  Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.4-num-1240-sd-10000/checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3325
  Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.4-num-1240-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
3323
  Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.4-num-1240-sd-10000/checkpoint-608/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3324
  Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.4-num-1240-sd-10000/checkpoint-76/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3325
  Qwen2-7B-Instruct_int4_flare-en-fpb_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.4-num-1240-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3326
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3327
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3328
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3329
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3330
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-3115/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3331
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-3560/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3332
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-445/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3333
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-890/tokenizer.json filter=lfs diff=lfs merge=lfs -text
3334
+ Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb792913929eda104a0d024225eab18b7b5190693541ec708d9f75df70492fa
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:182f3b6ebce83eeb8eb4ab1cdd5f62427bb8e097be45a754250c8aa4c2f7e21b
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472f05fc05f4ecfa2d72dd6e7b3d9853f839831cbf8a804dca7492e2af787e45
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:170dd6ad89f51d3935667b1d0ef3e2f12c90a001ce35bec4266b1b03cafe9493
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6b0e61d15a1763753a55888a7a3cb3bb7bfecbc9ed692af7994aab2823d99eb
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/trainer_state.json ADDED
@@ -0,0 +1,988 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8264012336730957,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-890",
4
+ "epoch": 3.0,
5
+ "eval_steps": 10,
6
+ "global_step": 1335,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02247191011235955,
13
+ "grad_norm": 0.541088342666626,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.6217,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0449438202247191,
20
+ "grad_norm": 0.606726348400116,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.309,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06741573033707865,
27
+ "grad_norm": 0.5244829058647156,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.0677,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0898876404494382,
34
+ "grad_norm": 0.6728479862213135,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.9807,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.11235955056179775,
41
+ "grad_norm": 0.8560609221458435,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.944,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.1348314606741573,
48
+ "grad_norm": 0.49180933833122253,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9372,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15730337078651685,
55
+ "grad_norm": 0.49781936407089233,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.9051,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1797752808988764,
62
+ "grad_norm": 0.5396708846092224,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.7978,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.20224719101123595,
69
+ "grad_norm": 0.478624552488327,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.8758,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2247191011235955,
76
+ "grad_norm": 0.8880449533462524,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8928,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.24719101123595505,
83
+ "grad_norm": 0.43290555477142334,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.8504,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2696629213483146,
90
+ "grad_norm": 0.438387006521225,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8536,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.29213483146067415,
97
+ "grad_norm": 0.4131482243537903,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.8655,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.3146067415730337,
104
+ "grad_norm": 0.5160607099533081,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.9063,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.33707865168539325,
111
+ "grad_norm": 0.3617960214614868,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.792,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3595505617977528,
118
+ "grad_norm": 0.5344526767730713,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.9222,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.38202247191011235,
125
+ "grad_norm": 0.37921762466430664,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.8478,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.4044943820224719,
132
+ "grad_norm": 0.431815505027771,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.7882,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.42696629213483145,
139
+ "grad_norm": 0.4125252366065979,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8431,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.449438202247191,
146
+ "grad_norm": 0.45420965552330017,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.7677,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.47191011235955055,
153
+ "grad_norm": 0.471342533826828,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.8083,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4943820224719101,
160
+ "grad_norm": 0.3953711986541748,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.8915,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5168539325842697,
167
+ "grad_norm": 0.3793153166770935,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.8153,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5393258426966292,
174
+ "grad_norm": 0.3719729483127594,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.7948,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5617977528089888,
181
+ "grad_norm": 0.4091097116470337,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.8293,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5842696629213483,
188
+ "grad_norm": 0.38691720366477966,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.8054,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6067415730337079,
195
+ "grad_norm": 0.39904487133026123,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8962,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6292134831460674,
202
+ "grad_norm": 0.36792582273483276,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.862,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.651685393258427,
209
+ "grad_norm": 0.3575645685195923,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8117,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6741573033707865,
216
+ "grad_norm": 0.34943437576293945,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.7338,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6966292134831461,
223
+ "grad_norm": 0.4369798004627228,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.7357,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7191011235955056,
230
+ "grad_norm": 0.4053204357624054,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.8257,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7415730337078652,
237
+ "grad_norm": 0.4032869338989258,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.7936,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7640449438202247,
244
+ "grad_norm": 0.393141508102417,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.9005,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7865168539325843,
251
+ "grad_norm": 0.3401991128921509,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.8525,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8089887640449438,
258
+ "grad_norm": 0.3157802224159241,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.7811,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8314606741573034,
265
+ "grad_norm": 0.34539058804512024,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.766,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8539325842696629,
272
+ "grad_norm": 0.3391708731651306,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.7687,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8764044943820225,
279
+ "grad_norm": 0.37594684958457947,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.7749,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.898876404494382,
286
+ "grad_norm": 0.387704461812973,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.7805,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9213483146067416,
293
+ "grad_norm": 0.5300629138946533,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.8255,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9438202247191011,
300
+ "grad_norm": 0.35356250405311584,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.7229,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9662921348314607,
307
+ "grad_norm": 0.3641810119152069,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.8647,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9887640449438202,
314
+ "grad_norm": 0.3925739824771881,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.7762,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 1.0,
321
+ "eval_loss": 1.829880714416504,
322
+ "eval_runtime": 38.6272,
323
+ "eval_samples_per_second": 13.333,
324
+ "eval_steps_per_second": 1.683,
325
+ "step": 445
326
+ },
327
+ {
328
+ "epoch": 1.0112359550561798,
329
+ "grad_norm": 0.324361115694046,
330
+ "learning_rate": 0.0002,
331
+ "loss": 1.7515,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.0337078651685394,
336
+ "grad_norm": 0.37567344307899475,
337
+ "learning_rate": 0.0002,
338
+ "loss": 1.7803,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.0561797752808988,
343
+ "grad_norm": 0.336347758769989,
344
+ "learning_rate": 0.0002,
345
+ "loss": 1.8442,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0786516853932584,
350
+ "grad_norm": 0.39281758666038513,
351
+ "learning_rate": 0.0002,
352
+ "loss": 1.7169,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.101123595505618,
357
+ "grad_norm": 0.348486989736557,
358
+ "learning_rate": 0.0002,
359
+ "loss": 1.803,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.1235955056179776,
364
+ "grad_norm": 0.3939574062824249,
365
+ "learning_rate": 0.0002,
366
+ "loss": 1.6511,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.146067415730337,
371
+ "grad_norm": 0.3566303849220276,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.692,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.1685393258426966,
378
+ "grad_norm": 0.44443410634994507,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.7093,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1910112359550562,
385
+ "grad_norm": 0.40352755784988403,
386
+ "learning_rate": 0.0002,
387
+ "loss": 1.7204,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.2134831460674158,
392
+ "grad_norm": 0.393235445022583,
393
+ "learning_rate": 0.0002,
394
+ "loss": 1.7693,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.2359550561797752,
399
+ "grad_norm": 0.38268715143203735,
400
+ "learning_rate": 0.0002,
401
+ "loss": 1.7402,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2584269662921348,
406
+ "grad_norm": 0.40748143196105957,
407
+ "learning_rate": 0.0002,
408
+ "loss": 1.8007,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2808988764044944,
413
+ "grad_norm": 0.46578362584114075,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.7096,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.303370786516854,
420
+ "grad_norm": 0.4152059853076935,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.753,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.3258426966292136,
427
+ "grad_norm": 0.39794254302978516,
428
+ "learning_rate": 0.0002,
429
+ "loss": 1.7658,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.348314606741573,
434
+ "grad_norm": 0.3964073359966278,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.683,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3707865168539326,
441
+ "grad_norm": 0.37973660230636597,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.7464,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.3932584269662922,
448
+ "grad_norm": 0.4126802384853363,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.6766,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.4157303370786516,
455
+ "grad_norm": 0.3873387575149536,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.7876,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.4382022471910112,
462
+ "grad_norm": 0.39390191435813904,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.7841,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.4606741573033708,
469
+ "grad_norm": 0.4302954375743866,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.7482,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4831460674157304,
476
+ "grad_norm": 0.3631756901741028,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.7608,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.50561797752809,
483
+ "grad_norm": 0.3835321366786957,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.7266,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.5280898876404494,
490
+ "grad_norm": 0.45179641246795654,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.7254,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.550561797752809,
497
+ "grad_norm": 0.4173226058483124,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.7541,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5730337078651684,
504
+ "grad_norm": 0.35887855291366577,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.7895,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.595505617977528,
511
+ "grad_norm": 0.40731844305992126,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.7209,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.6179775280898876,
518
+ "grad_norm": 0.4147540330886841,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.6606,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.6404494382022472,
525
+ "grad_norm": 0.37640494108200073,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.7385,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.6629213483146068,
532
+ "grad_norm": 0.3784808814525604,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.7021,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6853932584269664,
539
+ "grad_norm": 0.4551489055156708,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.7411,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.7078651685393258,
546
+ "grad_norm": 0.3906891345977783,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.7814,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.7303370786516854,
553
+ "grad_norm": 0.3876253664493561,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.7622,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.7528089887640448,
560
+ "grad_norm": 0.36962684988975525,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.7727,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.7752808988764044,
567
+ "grad_norm": 0.392286092042923,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.7796,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.797752808988764,
574
+ "grad_norm": 0.368129700422287,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.7455,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.8202247191011236,
581
+ "grad_norm": 0.42102697491645813,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7808,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.8426966292134832,
588
+ "grad_norm": 0.4314707815647125,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.7688,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.8651685393258428,
595
+ "grad_norm": 0.3763786554336548,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.7465,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8876404494382022,
602
+ "grad_norm": 0.34446850419044495,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.7291,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.9101123595505618,
609
+ "grad_norm": 0.3806961476802826,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.7014,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.9325842696629212,
616
+ "grad_norm": 0.38291847705841064,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.6652,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.9550561797752808,
623
+ "grad_norm": 0.4361240565776825,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.6964,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9775280898876404,
630
+ "grad_norm": 0.39230653643608093,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.7818,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 2.0,
637
+ "grad_norm": 0.3856890797615051,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.7174,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 2.0,
644
+ "eval_loss": 1.8264012336730957,
645
+ "eval_runtime": 38.4572,
646
+ "eval_samples_per_second": 13.392,
647
+ "eval_steps_per_second": 1.69,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.0224719101123596,
652
+ "grad_norm": 0.37172746658325195,
653
+ "learning_rate": 0.0002,
654
+ "loss": 1.5571,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.044943820224719,
659
+ "grad_norm": 0.4285264313220978,
660
+ "learning_rate": 0.0002,
661
+ "loss": 1.7088,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.067415730337079,
666
+ "grad_norm": 0.4178760051727295,
667
+ "learning_rate": 0.0002,
668
+ "loss": 1.6465,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.0898876404494384,
673
+ "grad_norm": 0.41439080238342285,
674
+ "learning_rate": 0.0002,
675
+ "loss": 1.6718,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.1123595505617976,
680
+ "grad_norm": 0.44750887155532837,
681
+ "learning_rate": 0.0002,
682
+ "loss": 1.6632,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.134831460674157,
687
+ "grad_norm": 0.47943830490112305,
688
+ "learning_rate": 0.0002,
689
+ "loss": 1.6886,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.157303370786517,
694
+ "grad_norm": 0.41972824931144714,
695
+ "learning_rate": 0.0002,
696
+ "loss": 1.7143,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.1797752808988764,
701
+ "grad_norm": 0.45687606930732727,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.6282,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.202247191011236,
708
+ "grad_norm": 3.270933151245117,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.6293,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.2247191011235956,
715
+ "grad_norm": 0.5009722709655762,
716
+ "learning_rate": 0.0002,
717
+ "loss": 1.6667,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.247191011235955,
722
+ "grad_norm": 0.47534242272377014,
723
+ "learning_rate": 0.0002,
724
+ "loss": 1.6737,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.2696629213483144,
729
+ "grad_norm": 0.4659167230129242,
730
+ "learning_rate": 0.0002,
731
+ "loss": 1.6121,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.292134831460674,
736
+ "grad_norm": 0.4227055013179779,
737
+ "learning_rate": 0.0002,
738
+ "loss": 1.6565,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.3146067415730336,
743
+ "grad_norm": 0.4480970799922943,
744
+ "learning_rate": 0.0002,
745
+ "loss": 1.6358,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.337078651685393,
750
+ "grad_norm": 0.46239933371543884,
751
+ "learning_rate": 0.0002,
752
+ "loss": 1.6459,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.359550561797753,
757
+ "grad_norm": 0.4576965570449829,
758
+ "learning_rate": 0.0002,
759
+ "loss": 1.7212,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.3820224719101124,
764
+ "grad_norm": 0.48324525356292725,
765
+ "learning_rate": 0.0002,
766
+ "loss": 1.6787,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.404494382022472,
771
+ "grad_norm": 0.4669286906719208,
772
+ "learning_rate": 0.0002,
773
+ "loss": 1.6773,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.4269662921348316,
778
+ "grad_norm": 0.5118905901908875,
779
+ "learning_rate": 0.0002,
780
+ "loss": 1.5971,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.449438202247191,
785
+ "grad_norm": 0.4905109405517578,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.6652,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.4719101123595504,
792
+ "grad_norm": 0.5466307401657104,
793
+ "learning_rate": 0.0002,
794
+ "loss": 1.6569,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.49438202247191,
799
+ "grad_norm": 0.483541876077652,
800
+ "learning_rate": 0.0002,
801
+ "loss": 1.6324,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.5168539325842696,
806
+ "grad_norm": 0.4115655720233917,
807
+ "learning_rate": 0.0002,
808
+ "loss": 1.6144,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.539325842696629,
813
+ "grad_norm": 0.45315614342689514,
814
+ "learning_rate": 0.0002,
815
+ "loss": 1.5999,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.561797752808989,
820
+ "grad_norm": 0.48349013924598694,
821
+ "learning_rate": 0.0002,
822
+ "loss": 1.654,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.5842696629213484,
827
+ "grad_norm": 0.4827800691127777,
828
+ "learning_rate": 0.0002,
829
+ "loss": 1.6688,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.606741573033708,
834
+ "grad_norm": 0.4685794711112976,
835
+ "learning_rate": 0.0002,
836
+ "loss": 1.6993,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.629213483146067,
841
+ "grad_norm": 0.46395015716552734,
842
+ "learning_rate": 0.0002,
843
+ "loss": 1.616,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.6516853932584272,
848
+ "grad_norm": 0.4605198800563812,
849
+ "learning_rate": 0.0002,
850
+ "loss": 1.5945,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.6741573033707864,
855
+ "grad_norm": 0.4916316270828247,
856
+ "learning_rate": 0.0002,
857
+ "loss": 1.6542,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.696629213483146,
862
+ "grad_norm": 0.4382898807525635,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.6414,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.7191011235955056,
869
+ "grad_norm": 0.4522838592529297,
870
+ "learning_rate": 0.0002,
871
+ "loss": 1.6681,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.741573033707865,
876
+ "grad_norm": 0.5802963376045227,
877
+ "learning_rate": 0.0002,
878
+ "loss": 1.6566,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.764044943820225,
883
+ "grad_norm": 0.44280654191970825,
884
+ "learning_rate": 0.0002,
885
+ "loss": 1.6628,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.7865168539325844,
890
+ "grad_norm": 0.4436502456665039,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.6967,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.808988764044944,
897
+ "grad_norm": 0.4817657768726349,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.5711,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.831460674157303,
904
+ "grad_norm": 0.46678975224494934,
905
+ "learning_rate": 0.0002,
906
+ "loss": 1.6143,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.853932584269663,
911
+ "grad_norm": 0.5505899786949158,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.5848,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.8764044943820224,
918
+ "grad_norm": 0.46449190378189087,
919
+ "learning_rate": 0.0002,
920
+ "loss": 1.6445,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.898876404494382,
925
+ "grad_norm": 0.5431554913520813,
926
+ "learning_rate": 0.0002,
927
+ "loss": 1.616,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.9213483146067416,
932
+ "grad_norm": 0.44165968894958496,
933
+ "learning_rate": 0.0002,
934
+ "loss": 1.69,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.943820224719101,
939
+ "grad_norm": 0.5253956317901611,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.6961,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.966292134831461,
946
+ "grad_norm": 0.42881500720977783,
947
+ "learning_rate": 0.0002,
948
+ "loss": 1.6085,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.98876404494382,
953
+ "grad_norm": 0.4666648507118225,
954
+ "learning_rate": 0.0002,
955
+ "loss": 1.5666,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 3.0,
960
+ "eval_loss": 1.841871976852417,
961
+ "eval_runtime": 38.4576,
962
+ "eval_samples_per_second": 13.391,
963
+ "eval_steps_per_second": 1.69,
964
+ "step": 1335
965
+ }
966
+ ],
967
+ "logging_steps": 10,
968
+ "max_steps": 3560,
969
+ "num_input_tokens_seen": 0,
970
+ "num_train_epochs": 8,
971
+ "save_steps": 200,
972
+ "stateful_callbacks": {
973
+ "TrainerControl": {
974
+ "args": {
975
+ "should_epoch_stop": false,
976
+ "should_evaluate": false,
977
+ "should_log": false,
978
+ "should_save": true,
979
+ "should_training_stop": false
980
+ },
981
+ "attributes": {}
982
+ }
983
+ },
984
+ "total_flos": 6.178081081393152e+16,
985
+ "train_batch_size": 1,
986
+ "trial_name": null,
987
+ "trial_params": null
988
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1335/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70bb087d22fb0995345805c545302523633dddfce545390f986898a00d9c23d9
3
+ size 5560
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2b0275980f49394149d0af53cba38a69477ceb30da328bb1938d3ed47deaf3
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5118bbd2990dfcc19286b20ab6cd24222c61d60356978859e4668780142457e0
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef93c50a9ed605d1b2bc45e8c195923f1c966ba10785b0e42bd90ddf2d19da1
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c467b720e16a0542bfa6f6cfbc0006b3809ce8043f7c57b200dde2f783288138
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/trainer_state.json ADDED
@@ -0,0 +1,1311 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8264012336730957,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-890",
4
+ "epoch": 4.0,
5
+ "eval_steps": 10,
6
+ "global_step": 1780,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02247191011235955,
13
+ "grad_norm": 0.541088342666626,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.6217,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0449438202247191,
20
+ "grad_norm": 0.606726348400116,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.309,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06741573033707865,
27
+ "grad_norm": 0.5244829058647156,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.0677,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0898876404494382,
34
+ "grad_norm": 0.6728479862213135,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.9807,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.11235955056179775,
41
+ "grad_norm": 0.8560609221458435,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.944,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.1348314606741573,
48
+ "grad_norm": 0.49180933833122253,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9372,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15730337078651685,
55
+ "grad_norm": 0.49781936407089233,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.9051,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1797752808988764,
62
+ "grad_norm": 0.5396708846092224,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.7978,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.20224719101123595,
69
+ "grad_norm": 0.478624552488327,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.8758,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2247191011235955,
76
+ "grad_norm": 0.8880449533462524,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8928,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.24719101123595505,
83
+ "grad_norm": 0.43290555477142334,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.8504,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2696629213483146,
90
+ "grad_norm": 0.438387006521225,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8536,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.29213483146067415,
97
+ "grad_norm": 0.4131482243537903,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.8655,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.3146067415730337,
104
+ "grad_norm": 0.5160607099533081,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.9063,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.33707865168539325,
111
+ "grad_norm": 0.3617960214614868,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.792,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3595505617977528,
118
+ "grad_norm": 0.5344526767730713,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.9222,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.38202247191011235,
125
+ "grad_norm": 0.37921762466430664,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.8478,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.4044943820224719,
132
+ "grad_norm": 0.431815505027771,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.7882,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.42696629213483145,
139
+ "grad_norm": 0.4125252366065979,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8431,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.449438202247191,
146
+ "grad_norm": 0.45420965552330017,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.7677,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.47191011235955055,
153
+ "grad_norm": 0.471342533826828,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.8083,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4943820224719101,
160
+ "grad_norm": 0.3953711986541748,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.8915,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5168539325842697,
167
+ "grad_norm": 0.3793153166770935,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.8153,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5393258426966292,
174
+ "grad_norm": 0.3719729483127594,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.7948,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5617977528089888,
181
+ "grad_norm": 0.4091097116470337,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.8293,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5842696629213483,
188
+ "grad_norm": 0.38691720366477966,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.8054,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6067415730337079,
195
+ "grad_norm": 0.39904487133026123,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8962,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6292134831460674,
202
+ "grad_norm": 0.36792582273483276,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.862,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.651685393258427,
209
+ "grad_norm": 0.3575645685195923,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8117,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6741573033707865,
216
+ "grad_norm": 0.34943437576293945,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.7338,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6966292134831461,
223
+ "grad_norm": 0.4369798004627228,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.7357,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7191011235955056,
230
+ "grad_norm": 0.4053204357624054,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.8257,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7415730337078652,
237
+ "grad_norm": 0.4032869338989258,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.7936,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7640449438202247,
244
+ "grad_norm": 0.393141508102417,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.9005,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7865168539325843,
251
+ "grad_norm": 0.3401991128921509,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.8525,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8089887640449438,
258
+ "grad_norm": 0.3157802224159241,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.7811,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8314606741573034,
265
+ "grad_norm": 0.34539058804512024,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.766,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8539325842696629,
272
+ "grad_norm": 0.3391708731651306,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.7687,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8764044943820225,
279
+ "grad_norm": 0.37594684958457947,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.7749,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.898876404494382,
286
+ "grad_norm": 0.387704461812973,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.7805,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9213483146067416,
293
+ "grad_norm": 0.5300629138946533,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.8255,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9438202247191011,
300
+ "grad_norm": 0.35356250405311584,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.7229,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9662921348314607,
307
+ "grad_norm": 0.3641810119152069,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.8647,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9887640449438202,
314
+ "grad_norm": 0.3925739824771881,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.7762,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 1.0,
321
+ "eval_loss": 1.829880714416504,
322
+ "eval_runtime": 38.6272,
323
+ "eval_samples_per_second": 13.333,
324
+ "eval_steps_per_second": 1.683,
325
+ "step": 445
326
+ },
327
+ {
328
+ "epoch": 1.0112359550561798,
329
+ "grad_norm": 0.324361115694046,
330
+ "learning_rate": 0.0002,
331
+ "loss": 1.7515,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.0337078651685394,
336
+ "grad_norm": 0.37567344307899475,
337
+ "learning_rate": 0.0002,
338
+ "loss": 1.7803,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.0561797752808988,
343
+ "grad_norm": 0.336347758769989,
344
+ "learning_rate": 0.0002,
345
+ "loss": 1.8442,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0786516853932584,
350
+ "grad_norm": 0.39281758666038513,
351
+ "learning_rate": 0.0002,
352
+ "loss": 1.7169,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.101123595505618,
357
+ "grad_norm": 0.348486989736557,
358
+ "learning_rate": 0.0002,
359
+ "loss": 1.803,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.1235955056179776,
364
+ "grad_norm": 0.3939574062824249,
365
+ "learning_rate": 0.0002,
366
+ "loss": 1.6511,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.146067415730337,
371
+ "grad_norm": 0.3566303849220276,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.692,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.1685393258426966,
378
+ "grad_norm": 0.44443410634994507,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.7093,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1910112359550562,
385
+ "grad_norm": 0.40352755784988403,
386
+ "learning_rate": 0.0002,
387
+ "loss": 1.7204,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.2134831460674158,
392
+ "grad_norm": 0.393235445022583,
393
+ "learning_rate": 0.0002,
394
+ "loss": 1.7693,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.2359550561797752,
399
+ "grad_norm": 0.38268715143203735,
400
+ "learning_rate": 0.0002,
401
+ "loss": 1.7402,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2584269662921348,
406
+ "grad_norm": 0.40748143196105957,
407
+ "learning_rate": 0.0002,
408
+ "loss": 1.8007,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2808988764044944,
413
+ "grad_norm": 0.46578362584114075,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.7096,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.303370786516854,
420
+ "grad_norm": 0.4152059853076935,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.753,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.3258426966292136,
427
+ "grad_norm": 0.39794254302978516,
428
+ "learning_rate": 0.0002,
429
+ "loss": 1.7658,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.348314606741573,
434
+ "grad_norm": 0.3964073359966278,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.683,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3707865168539326,
441
+ "grad_norm": 0.37973660230636597,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.7464,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.3932584269662922,
448
+ "grad_norm": 0.4126802384853363,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.6766,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.4157303370786516,
455
+ "grad_norm": 0.3873387575149536,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.7876,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.4382022471910112,
462
+ "grad_norm": 0.39390191435813904,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.7841,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.4606741573033708,
469
+ "grad_norm": 0.4302954375743866,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.7482,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4831460674157304,
476
+ "grad_norm": 0.3631756901741028,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.7608,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.50561797752809,
483
+ "grad_norm": 0.3835321366786957,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.7266,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.5280898876404494,
490
+ "grad_norm": 0.45179641246795654,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.7254,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.550561797752809,
497
+ "grad_norm": 0.4173226058483124,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.7541,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5730337078651684,
504
+ "grad_norm": 0.35887855291366577,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.7895,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.595505617977528,
511
+ "grad_norm": 0.40731844305992126,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.7209,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.6179775280898876,
518
+ "grad_norm": 0.4147540330886841,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.6606,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.6404494382022472,
525
+ "grad_norm": 0.37640494108200073,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.7385,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.6629213483146068,
532
+ "grad_norm": 0.3784808814525604,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.7021,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6853932584269664,
539
+ "grad_norm": 0.4551489055156708,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.7411,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.7078651685393258,
546
+ "grad_norm": 0.3906891345977783,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.7814,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.7303370786516854,
553
+ "grad_norm": 0.3876253664493561,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.7622,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.7528089887640448,
560
+ "grad_norm": 0.36962684988975525,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.7727,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.7752808988764044,
567
+ "grad_norm": 0.392286092042923,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.7796,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.797752808988764,
574
+ "grad_norm": 0.368129700422287,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.7455,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.8202247191011236,
581
+ "grad_norm": 0.42102697491645813,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7808,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.8426966292134832,
588
+ "grad_norm": 0.4314707815647125,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.7688,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.8651685393258428,
595
+ "grad_norm": 0.3763786554336548,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.7465,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8876404494382022,
602
+ "grad_norm": 0.34446850419044495,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.7291,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.9101123595505618,
609
+ "grad_norm": 0.3806961476802826,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.7014,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.9325842696629212,
616
+ "grad_norm": 0.38291847705841064,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.6652,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.9550561797752808,
623
+ "grad_norm": 0.4361240565776825,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.6964,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9775280898876404,
630
+ "grad_norm": 0.39230653643608093,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.7818,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 2.0,
637
+ "grad_norm": 0.3856890797615051,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.7174,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 2.0,
644
+ "eval_loss": 1.8264012336730957,
645
+ "eval_runtime": 38.4572,
646
+ "eval_samples_per_second": 13.392,
647
+ "eval_steps_per_second": 1.69,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.0224719101123596,
652
+ "grad_norm": 0.37172746658325195,
653
+ "learning_rate": 0.0002,
654
+ "loss": 1.5571,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.044943820224719,
659
+ "grad_norm": 0.4285264313220978,
660
+ "learning_rate": 0.0002,
661
+ "loss": 1.7088,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.067415730337079,
666
+ "grad_norm": 0.4178760051727295,
667
+ "learning_rate": 0.0002,
668
+ "loss": 1.6465,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.0898876404494384,
673
+ "grad_norm": 0.41439080238342285,
674
+ "learning_rate": 0.0002,
675
+ "loss": 1.6718,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.1123595505617976,
680
+ "grad_norm": 0.44750887155532837,
681
+ "learning_rate": 0.0002,
682
+ "loss": 1.6632,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.134831460674157,
687
+ "grad_norm": 0.47943830490112305,
688
+ "learning_rate": 0.0002,
689
+ "loss": 1.6886,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.157303370786517,
694
+ "grad_norm": 0.41972824931144714,
695
+ "learning_rate": 0.0002,
696
+ "loss": 1.7143,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.1797752808988764,
701
+ "grad_norm": 0.45687606930732727,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.6282,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.202247191011236,
708
+ "grad_norm": 3.270933151245117,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.6293,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.2247191011235956,
715
+ "grad_norm": 0.5009722709655762,
716
+ "learning_rate": 0.0002,
717
+ "loss": 1.6667,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.247191011235955,
722
+ "grad_norm": 0.47534242272377014,
723
+ "learning_rate": 0.0002,
724
+ "loss": 1.6737,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.2696629213483144,
729
+ "grad_norm": 0.4659167230129242,
730
+ "learning_rate": 0.0002,
731
+ "loss": 1.6121,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.292134831460674,
736
+ "grad_norm": 0.4227055013179779,
737
+ "learning_rate": 0.0002,
738
+ "loss": 1.6565,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.3146067415730336,
743
+ "grad_norm": 0.4480970799922943,
744
+ "learning_rate": 0.0002,
745
+ "loss": 1.6358,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.337078651685393,
750
+ "grad_norm": 0.46239933371543884,
751
+ "learning_rate": 0.0002,
752
+ "loss": 1.6459,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.359550561797753,
757
+ "grad_norm": 0.4576965570449829,
758
+ "learning_rate": 0.0002,
759
+ "loss": 1.7212,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.3820224719101124,
764
+ "grad_norm": 0.48324525356292725,
765
+ "learning_rate": 0.0002,
766
+ "loss": 1.6787,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.404494382022472,
771
+ "grad_norm": 0.4669286906719208,
772
+ "learning_rate": 0.0002,
773
+ "loss": 1.6773,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.4269662921348316,
778
+ "grad_norm": 0.5118905901908875,
779
+ "learning_rate": 0.0002,
780
+ "loss": 1.5971,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.449438202247191,
785
+ "grad_norm": 0.4905109405517578,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.6652,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.4719101123595504,
792
+ "grad_norm": 0.5466307401657104,
793
+ "learning_rate": 0.0002,
794
+ "loss": 1.6569,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.49438202247191,
799
+ "grad_norm": 0.483541876077652,
800
+ "learning_rate": 0.0002,
801
+ "loss": 1.6324,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.5168539325842696,
806
+ "grad_norm": 0.4115655720233917,
807
+ "learning_rate": 0.0002,
808
+ "loss": 1.6144,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.539325842696629,
813
+ "grad_norm": 0.45315614342689514,
814
+ "learning_rate": 0.0002,
815
+ "loss": 1.5999,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.561797752808989,
820
+ "grad_norm": 0.48349013924598694,
821
+ "learning_rate": 0.0002,
822
+ "loss": 1.654,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.5842696629213484,
827
+ "grad_norm": 0.4827800691127777,
828
+ "learning_rate": 0.0002,
829
+ "loss": 1.6688,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.606741573033708,
834
+ "grad_norm": 0.4685794711112976,
835
+ "learning_rate": 0.0002,
836
+ "loss": 1.6993,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.629213483146067,
841
+ "grad_norm": 0.46395015716552734,
842
+ "learning_rate": 0.0002,
843
+ "loss": 1.616,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.6516853932584272,
848
+ "grad_norm": 0.4605198800563812,
849
+ "learning_rate": 0.0002,
850
+ "loss": 1.5945,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.6741573033707864,
855
+ "grad_norm": 0.4916316270828247,
856
+ "learning_rate": 0.0002,
857
+ "loss": 1.6542,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.696629213483146,
862
+ "grad_norm": 0.4382898807525635,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.6414,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.7191011235955056,
869
+ "grad_norm": 0.4522838592529297,
870
+ "learning_rate": 0.0002,
871
+ "loss": 1.6681,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.741573033707865,
876
+ "grad_norm": 0.5802963376045227,
877
+ "learning_rate": 0.0002,
878
+ "loss": 1.6566,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.764044943820225,
883
+ "grad_norm": 0.44280654191970825,
884
+ "learning_rate": 0.0002,
885
+ "loss": 1.6628,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.7865168539325844,
890
+ "grad_norm": 0.4436502456665039,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.6967,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.808988764044944,
897
+ "grad_norm": 0.4817657768726349,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.5711,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.831460674157303,
904
+ "grad_norm": 0.46678975224494934,
905
+ "learning_rate": 0.0002,
906
+ "loss": 1.6143,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.853932584269663,
911
+ "grad_norm": 0.5505899786949158,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.5848,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.8764044943820224,
918
+ "grad_norm": 0.46449190378189087,
919
+ "learning_rate": 0.0002,
920
+ "loss": 1.6445,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.898876404494382,
925
+ "grad_norm": 0.5431554913520813,
926
+ "learning_rate": 0.0002,
927
+ "loss": 1.616,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.9213483146067416,
932
+ "grad_norm": 0.44165968894958496,
933
+ "learning_rate": 0.0002,
934
+ "loss": 1.69,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.943820224719101,
939
+ "grad_norm": 0.5253956317901611,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.6961,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.966292134831461,
946
+ "grad_norm": 0.42881500720977783,
947
+ "learning_rate": 0.0002,
948
+ "loss": 1.6085,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.98876404494382,
953
+ "grad_norm": 0.4666648507118225,
954
+ "learning_rate": 0.0002,
955
+ "loss": 1.5666,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 3.0,
960
+ "eval_loss": 1.841871976852417,
961
+ "eval_runtime": 38.4576,
962
+ "eval_samples_per_second": 13.391,
963
+ "eval_steps_per_second": 1.69,
964
+ "step": 1335
965
+ },
966
+ {
967
+ "epoch": 3.0112359550561796,
968
+ "grad_norm": 0.4540881812572479,
969
+ "learning_rate": 0.0002,
970
+ "loss": 1.4981,
971
+ "step": 1340
972
+ },
973
+ {
974
+ "epoch": 3.033707865168539,
975
+ "grad_norm": 0.5289544463157654,
976
+ "learning_rate": 0.0002,
977
+ "loss": 1.4593,
978
+ "step": 1350
979
+ },
980
+ {
981
+ "epoch": 3.056179775280899,
982
+ "grad_norm": 0.5404762029647827,
983
+ "learning_rate": 0.0002,
984
+ "loss": 1.5181,
985
+ "step": 1360
986
+ },
987
+ {
988
+ "epoch": 3.0786516853932584,
989
+ "grad_norm": 0.606574535369873,
990
+ "learning_rate": 0.0002,
991
+ "loss": 1.5327,
992
+ "step": 1370
993
+ },
994
+ {
995
+ "epoch": 3.101123595505618,
996
+ "grad_norm": 0.6293940544128418,
997
+ "learning_rate": 0.0002,
998
+ "loss": 1.5418,
999
+ "step": 1380
1000
+ },
1001
+ {
1002
+ "epoch": 3.1235955056179776,
1003
+ "grad_norm": 0.5431684851646423,
1004
+ "learning_rate": 0.0002,
1005
+ "loss": 1.4522,
1006
+ "step": 1390
1007
+ },
1008
+ {
1009
+ "epoch": 3.146067415730337,
1010
+ "grad_norm": 0.5571810007095337,
1011
+ "learning_rate": 0.0002,
1012
+ "loss": 1.6047,
1013
+ "step": 1400
1014
+ },
1015
+ {
1016
+ "epoch": 3.168539325842697,
1017
+ "grad_norm": 0.5232224464416504,
1018
+ "learning_rate": 0.0002,
1019
+ "loss": 1.5709,
1020
+ "step": 1410
1021
+ },
1022
+ {
1023
+ "epoch": 3.191011235955056,
1024
+ "grad_norm": 0.6176348924636841,
1025
+ "learning_rate": 0.0002,
1026
+ "loss": 1.5014,
1027
+ "step": 1420
1028
+ },
1029
+ {
1030
+ "epoch": 3.2134831460674156,
1031
+ "grad_norm": 0.5267609357833862,
1032
+ "learning_rate": 0.0002,
1033
+ "loss": 1.5398,
1034
+ "step": 1430
1035
+ },
1036
+ {
1037
+ "epoch": 3.235955056179775,
1038
+ "grad_norm": 0.6405419707298279,
1039
+ "learning_rate": 0.0002,
1040
+ "loss": 1.4821,
1041
+ "step": 1440
1042
+ },
1043
+ {
1044
+ "epoch": 3.258426966292135,
1045
+ "grad_norm": 0.6280969977378845,
1046
+ "learning_rate": 0.0002,
1047
+ "loss": 1.5365,
1048
+ "step": 1450
1049
+ },
1050
+ {
1051
+ "epoch": 3.2808988764044944,
1052
+ "grad_norm": 0.594437837600708,
1053
+ "learning_rate": 0.0002,
1054
+ "loss": 1.4962,
1055
+ "step": 1460
1056
+ },
1057
+ {
1058
+ "epoch": 3.303370786516854,
1059
+ "grad_norm": 0.5297112464904785,
1060
+ "learning_rate": 0.0002,
1061
+ "loss": 1.4714,
1062
+ "step": 1470
1063
+ },
1064
+ {
1065
+ "epoch": 3.3258426966292136,
1066
+ "grad_norm": 0.6481576561927795,
1067
+ "learning_rate": 0.0002,
1068
+ "loss": 1.5163,
1069
+ "step": 1480
1070
+ },
1071
+ {
1072
+ "epoch": 3.348314606741573,
1073
+ "grad_norm": 0.6006230711936951,
1074
+ "learning_rate": 0.0002,
1075
+ "loss": 1.5198,
1076
+ "step": 1490
1077
+ },
1078
+ {
1079
+ "epoch": 3.370786516853933,
1080
+ "grad_norm": 0.6718862652778625,
1081
+ "learning_rate": 0.0002,
1082
+ "loss": 1.5476,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 3.393258426966292,
1087
+ "grad_norm": 0.5663893222808838,
1088
+ "learning_rate": 0.0002,
1089
+ "loss": 1.484,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 3.4157303370786516,
1094
+ "grad_norm": 0.6176982522010803,
1095
+ "learning_rate": 0.0002,
1096
+ "loss": 1.4779,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 3.438202247191011,
1101
+ "grad_norm": 0.5643916130065918,
1102
+ "learning_rate": 0.0002,
1103
+ "loss": 1.5449,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 3.460674157303371,
1108
+ "grad_norm": 0.6312360763549805,
1109
+ "learning_rate": 0.0002,
1110
+ "loss": 1.5071,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 3.4831460674157304,
1115
+ "grad_norm": 0.6003469824790955,
1116
+ "learning_rate": 0.0002,
1117
+ "loss": 1.4793,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 3.50561797752809,
1122
+ "grad_norm": 0.635564923286438,
1123
+ "learning_rate": 0.0002,
1124
+ "loss": 1.5,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 3.5280898876404496,
1129
+ "grad_norm": 0.6120123863220215,
1130
+ "learning_rate": 0.0002,
1131
+ "loss": 1.5442,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 3.550561797752809,
1136
+ "grad_norm": 0.6079851388931274,
1137
+ "learning_rate": 0.0002,
1138
+ "loss": 1.5652,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 3.5730337078651684,
1143
+ "grad_norm": 0.5879889726638794,
1144
+ "learning_rate": 0.0002,
1145
+ "loss": 1.5934,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 3.595505617977528,
1150
+ "grad_norm": 0.618109405040741,
1151
+ "learning_rate": 0.0002,
1152
+ "loss": 1.5611,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 3.6179775280898876,
1157
+ "grad_norm": 0.608756422996521,
1158
+ "learning_rate": 0.0002,
1159
+ "loss": 1.4971,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 3.640449438202247,
1164
+ "grad_norm": 0.554905116558075,
1165
+ "learning_rate": 0.0002,
1166
+ "loss": 1.491,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 3.662921348314607,
1171
+ "grad_norm": 0.5828419327735901,
1172
+ "learning_rate": 0.0002,
1173
+ "loss": 1.5821,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 3.6853932584269664,
1178
+ "grad_norm": 0.655953049659729,
1179
+ "learning_rate": 0.0002,
1180
+ "loss": 1.5573,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 3.7078651685393256,
1185
+ "grad_norm": 0.5976583361625671,
1186
+ "learning_rate": 0.0002,
1187
+ "loss": 1.5455,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 3.7303370786516856,
1192
+ "grad_norm": 0.5679733157157898,
1193
+ "learning_rate": 0.0002,
1194
+ "loss": 1.599,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 3.752808988764045,
1199
+ "grad_norm": 0.6647416353225708,
1200
+ "learning_rate": 0.0002,
1201
+ "loss": 1.4749,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 3.7752808988764044,
1206
+ "grad_norm": 0.6381834745407104,
1207
+ "learning_rate": 0.0002,
1208
+ "loss": 1.5356,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 3.797752808988764,
1213
+ "grad_norm": 0.6131210327148438,
1214
+ "learning_rate": 0.0002,
1215
+ "loss": 1.4792,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 3.8202247191011236,
1220
+ "grad_norm": 0.6219302415847778,
1221
+ "learning_rate": 0.0002,
1222
+ "loss": 1.6249,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 3.842696629213483,
1227
+ "grad_norm": 0.5793370604515076,
1228
+ "learning_rate": 0.0002,
1229
+ "loss": 1.4764,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 3.865168539325843,
1234
+ "grad_norm": 0.5806208848953247,
1235
+ "learning_rate": 0.0002,
1236
+ "loss": 1.5534,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 3.8876404494382024,
1241
+ "grad_norm": 0.5671854019165039,
1242
+ "learning_rate": 0.0002,
1243
+ "loss": 1.556,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 3.9101123595505616,
1248
+ "grad_norm": 0.5803307890892029,
1249
+ "learning_rate": 0.0002,
1250
+ "loss": 1.6529,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 3.932584269662921,
1255
+ "grad_norm": 0.5710529088973999,
1256
+ "learning_rate": 0.0002,
1257
+ "loss": 1.4725,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 3.955056179775281,
1262
+ "grad_norm": 0.5724003314971924,
1263
+ "learning_rate": 0.0002,
1264
+ "loss": 1.5023,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 3.9775280898876404,
1269
+ "grad_norm": 0.556728184223175,
1270
+ "learning_rate": 0.0002,
1271
+ "loss": 1.4568,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 4.0,
1276
+ "grad_norm": 0.5443143248558044,
1277
+ "learning_rate": 0.0002,
1278
+ "loss": 1.5052,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 4.0,
1283
+ "eval_loss": 1.8935941457748413,
1284
+ "eval_runtime": 38.4958,
1285
+ "eval_samples_per_second": 13.378,
1286
+ "eval_steps_per_second": 1.688,
1287
+ "step": 1780
1288
+ }
1289
+ ],
1290
+ "logging_steps": 10,
1291
+ "max_steps": 3560,
1292
+ "num_input_tokens_seen": 0,
1293
+ "num_train_epochs": 8,
1294
+ "save_steps": 200,
1295
+ "stateful_callbacks": {
1296
+ "TrainerControl": {
1297
+ "args": {
1298
+ "should_epoch_stop": false,
1299
+ "should_evaluate": false,
1300
+ "should_log": false,
1301
+ "should_save": true,
1302
+ "should_training_stop": false
1303
+ },
1304
+ "attributes": {}
1305
+ }
1306
+ },
1307
+ "total_flos": 8.237441441857536e+16,
1308
+ "train_batch_size": 1,
1309
+ "trial_name": null,
1310
+ "trial_params": null
1311
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-1780/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70bb087d22fb0995345805c545302523633dddfce545390f986898a00d9c23d9
3
+ size 5560
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4320db2710305d10a9b0a5253a40d9c26063d88039617ccc37b7828db96a9d2a
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c6458bd72931f51deefeeff9dfe8f81746fc0c4872b22f3d73b0d2564899fa
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d877588998e19692dc76d0491396c932b5eb69535519652a846f44c38f4a08
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fcebe102fa96e32ebaad912cd7a2e27e70801f419a263550b01e53741128636
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/trainer_state.json ADDED
@@ -0,0 +1,1627 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8264012336730957,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-890",
4
+ "epoch": 5.0,
5
+ "eval_steps": 10,
6
+ "global_step": 2225,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02247191011235955,
13
+ "grad_norm": 0.541088342666626,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.6217,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0449438202247191,
20
+ "grad_norm": 0.606726348400116,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.309,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06741573033707865,
27
+ "grad_norm": 0.5244829058647156,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.0677,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0898876404494382,
34
+ "grad_norm": 0.6728479862213135,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.9807,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.11235955056179775,
41
+ "grad_norm": 0.8560609221458435,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.944,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.1348314606741573,
48
+ "grad_norm": 0.49180933833122253,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9372,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15730337078651685,
55
+ "grad_norm": 0.49781936407089233,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.9051,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1797752808988764,
62
+ "grad_norm": 0.5396708846092224,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.7978,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.20224719101123595,
69
+ "grad_norm": 0.478624552488327,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.8758,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2247191011235955,
76
+ "grad_norm": 0.8880449533462524,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8928,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.24719101123595505,
83
+ "grad_norm": 0.43290555477142334,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.8504,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2696629213483146,
90
+ "grad_norm": 0.438387006521225,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8536,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.29213483146067415,
97
+ "grad_norm": 0.4131482243537903,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.8655,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.3146067415730337,
104
+ "grad_norm": 0.5160607099533081,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.9063,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.33707865168539325,
111
+ "grad_norm": 0.3617960214614868,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.792,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3595505617977528,
118
+ "grad_norm": 0.5344526767730713,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.9222,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.38202247191011235,
125
+ "grad_norm": 0.37921762466430664,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.8478,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.4044943820224719,
132
+ "grad_norm": 0.431815505027771,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.7882,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.42696629213483145,
139
+ "grad_norm": 0.4125252366065979,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8431,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.449438202247191,
146
+ "grad_norm": 0.45420965552330017,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.7677,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.47191011235955055,
153
+ "grad_norm": 0.471342533826828,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.8083,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4943820224719101,
160
+ "grad_norm": 0.3953711986541748,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.8915,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5168539325842697,
167
+ "grad_norm": 0.3793153166770935,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.8153,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5393258426966292,
174
+ "grad_norm": 0.3719729483127594,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.7948,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5617977528089888,
181
+ "grad_norm": 0.4091097116470337,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.8293,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5842696629213483,
188
+ "grad_norm": 0.38691720366477966,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.8054,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6067415730337079,
195
+ "grad_norm": 0.39904487133026123,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8962,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6292134831460674,
202
+ "grad_norm": 0.36792582273483276,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.862,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.651685393258427,
209
+ "grad_norm": 0.3575645685195923,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8117,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6741573033707865,
216
+ "grad_norm": 0.34943437576293945,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.7338,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6966292134831461,
223
+ "grad_norm": 0.4369798004627228,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.7357,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7191011235955056,
230
+ "grad_norm": 0.4053204357624054,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.8257,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7415730337078652,
237
+ "grad_norm": 0.4032869338989258,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.7936,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7640449438202247,
244
+ "grad_norm": 0.393141508102417,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.9005,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7865168539325843,
251
+ "grad_norm": 0.3401991128921509,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.8525,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8089887640449438,
258
+ "grad_norm": 0.3157802224159241,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.7811,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8314606741573034,
265
+ "grad_norm": 0.34539058804512024,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.766,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8539325842696629,
272
+ "grad_norm": 0.3391708731651306,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.7687,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8764044943820225,
279
+ "grad_norm": 0.37594684958457947,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.7749,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.898876404494382,
286
+ "grad_norm": 0.387704461812973,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.7805,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9213483146067416,
293
+ "grad_norm": 0.5300629138946533,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.8255,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9438202247191011,
300
+ "grad_norm": 0.35356250405311584,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.7229,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9662921348314607,
307
+ "grad_norm": 0.3641810119152069,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.8647,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9887640449438202,
314
+ "grad_norm": 0.3925739824771881,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.7762,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 1.0,
321
+ "eval_loss": 1.829880714416504,
322
+ "eval_runtime": 38.6272,
323
+ "eval_samples_per_second": 13.333,
324
+ "eval_steps_per_second": 1.683,
325
+ "step": 445
326
+ },
327
+ {
328
+ "epoch": 1.0112359550561798,
329
+ "grad_norm": 0.324361115694046,
330
+ "learning_rate": 0.0002,
331
+ "loss": 1.7515,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.0337078651685394,
336
+ "grad_norm": 0.37567344307899475,
337
+ "learning_rate": 0.0002,
338
+ "loss": 1.7803,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.0561797752808988,
343
+ "grad_norm": 0.336347758769989,
344
+ "learning_rate": 0.0002,
345
+ "loss": 1.8442,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0786516853932584,
350
+ "grad_norm": 0.39281758666038513,
351
+ "learning_rate": 0.0002,
352
+ "loss": 1.7169,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.101123595505618,
357
+ "grad_norm": 0.348486989736557,
358
+ "learning_rate": 0.0002,
359
+ "loss": 1.803,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.1235955056179776,
364
+ "grad_norm": 0.3939574062824249,
365
+ "learning_rate": 0.0002,
366
+ "loss": 1.6511,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.146067415730337,
371
+ "grad_norm": 0.3566303849220276,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.692,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.1685393258426966,
378
+ "grad_norm": 0.44443410634994507,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.7093,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1910112359550562,
385
+ "grad_norm": 0.40352755784988403,
386
+ "learning_rate": 0.0002,
387
+ "loss": 1.7204,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.2134831460674158,
392
+ "grad_norm": 0.393235445022583,
393
+ "learning_rate": 0.0002,
394
+ "loss": 1.7693,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.2359550561797752,
399
+ "grad_norm": 0.38268715143203735,
400
+ "learning_rate": 0.0002,
401
+ "loss": 1.7402,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2584269662921348,
406
+ "grad_norm": 0.40748143196105957,
407
+ "learning_rate": 0.0002,
408
+ "loss": 1.8007,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2808988764044944,
413
+ "grad_norm": 0.46578362584114075,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.7096,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.303370786516854,
420
+ "grad_norm": 0.4152059853076935,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.753,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.3258426966292136,
427
+ "grad_norm": 0.39794254302978516,
428
+ "learning_rate": 0.0002,
429
+ "loss": 1.7658,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.348314606741573,
434
+ "grad_norm": 0.3964073359966278,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.683,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3707865168539326,
441
+ "grad_norm": 0.37973660230636597,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.7464,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.3932584269662922,
448
+ "grad_norm": 0.4126802384853363,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.6766,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.4157303370786516,
455
+ "grad_norm": 0.3873387575149536,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.7876,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.4382022471910112,
462
+ "grad_norm": 0.39390191435813904,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.7841,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.4606741573033708,
469
+ "grad_norm": 0.4302954375743866,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.7482,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4831460674157304,
476
+ "grad_norm": 0.3631756901741028,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.7608,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.50561797752809,
483
+ "grad_norm": 0.3835321366786957,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.7266,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.5280898876404494,
490
+ "grad_norm": 0.45179641246795654,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.7254,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.550561797752809,
497
+ "grad_norm": 0.4173226058483124,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.7541,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5730337078651684,
504
+ "grad_norm": 0.35887855291366577,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.7895,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.595505617977528,
511
+ "grad_norm": 0.40731844305992126,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.7209,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.6179775280898876,
518
+ "grad_norm": 0.4147540330886841,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.6606,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.6404494382022472,
525
+ "grad_norm": 0.37640494108200073,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.7385,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.6629213483146068,
532
+ "grad_norm": 0.3784808814525604,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.7021,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6853932584269664,
539
+ "grad_norm": 0.4551489055156708,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.7411,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.7078651685393258,
546
+ "grad_norm": 0.3906891345977783,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.7814,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.7303370786516854,
553
+ "grad_norm": 0.3876253664493561,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.7622,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.7528089887640448,
560
+ "grad_norm": 0.36962684988975525,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.7727,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.7752808988764044,
567
+ "grad_norm": 0.392286092042923,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.7796,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.797752808988764,
574
+ "grad_norm": 0.368129700422287,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.7455,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.8202247191011236,
581
+ "grad_norm": 0.42102697491645813,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7808,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.8426966292134832,
588
+ "grad_norm": 0.4314707815647125,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.7688,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.8651685393258428,
595
+ "grad_norm": 0.3763786554336548,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.7465,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8876404494382022,
602
+ "grad_norm": 0.34446850419044495,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.7291,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.9101123595505618,
609
+ "grad_norm": 0.3806961476802826,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.7014,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.9325842696629212,
616
+ "grad_norm": 0.38291847705841064,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.6652,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.9550561797752808,
623
+ "grad_norm": 0.4361240565776825,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.6964,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9775280898876404,
630
+ "grad_norm": 0.39230653643608093,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.7818,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 2.0,
637
+ "grad_norm": 0.3856890797615051,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.7174,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 2.0,
644
+ "eval_loss": 1.8264012336730957,
645
+ "eval_runtime": 38.4572,
646
+ "eval_samples_per_second": 13.392,
647
+ "eval_steps_per_second": 1.69,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.0224719101123596,
652
+ "grad_norm": 0.37172746658325195,
653
+ "learning_rate": 0.0002,
654
+ "loss": 1.5571,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.044943820224719,
659
+ "grad_norm": 0.4285264313220978,
660
+ "learning_rate": 0.0002,
661
+ "loss": 1.7088,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.067415730337079,
666
+ "grad_norm": 0.4178760051727295,
667
+ "learning_rate": 0.0002,
668
+ "loss": 1.6465,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.0898876404494384,
673
+ "grad_norm": 0.41439080238342285,
674
+ "learning_rate": 0.0002,
675
+ "loss": 1.6718,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.1123595505617976,
680
+ "grad_norm": 0.44750887155532837,
681
+ "learning_rate": 0.0002,
682
+ "loss": 1.6632,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.134831460674157,
687
+ "grad_norm": 0.47943830490112305,
688
+ "learning_rate": 0.0002,
689
+ "loss": 1.6886,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.157303370786517,
694
+ "grad_norm": 0.41972824931144714,
695
+ "learning_rate": 0.0002,
696
+ "loss": 1.7143,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.1797752808988764,
701
+ "grad_norm": 0.45687606930732727,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.6282,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.202247191011236,
708
+ "grad_norm": 3.270933151245117,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.6293,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.2247191011235956,
715
+ "grad_norm": 0.5009722709655762,
716
+ "learning_rate": 0.0002,
717
+ "loss": 1.6667,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.247191011235955,
722
+ "grad_norm": 0.47534242272377014,
723
+ "learning_rate": 0.0002,
724
+ "loss": 1.6737,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.2696629213483144,
729
+ "grad_norm": 0.4659167230129242,
730
+ "learning_rate": 0.0002,
731
+ "loss": 1.6121,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.292134831460674,
736
+ "grad_norm": 0.4227055013179779,
737
+ "learning_rate": 0.0002,
738
+ "loss": 1.6565,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.3146067415730336,
743
+ "grad_norm": 0.4480970799922943,
744
+ "learning_rate": 0.0002,
745
+ "loss": 1.6358,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.337078651685393,
750
+ "grad_norm": 0.46239933371543884,
751
+ "learning_rate": 0.0002,
752
+ "loss": 1.6459,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.359550561797753,
757
+ "grad_norm": 0.4576965570449829,
758
+ "learning_rate": 0.0002,
759
+ "loss": 1.7212,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.3820224719101124,
764
+ "grad_norm": 0.48324525356292725,
765
+ "learning_rate": 0.0002,
766
+ "loss": 1.6787,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.404494382022472,
771
+ "grad_norm": 0.4669286906719208,
772
+ "learning_rate": 0.0002,
773
+ "loss": 1.6773,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.4269662921348316,
778
+ "grad_norm": 0.5118905901908875,
779
+ "learning_rate": 0.0002,
780
+ "loss": 1.5971,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.449438202247191,
785
+ "grad_norm": 0.4905109405517578,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.6652,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.4719101123595504,
792
+ "grad_norm": 0.5466307401657104,
793
+ "learning_rate": 0.0002,
794
+ "loss": 1.6569,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.49438202247191,
799
+ "grad_norm": 0.483541876077652,
800
+ "learning_rate": 0.0002,
801
+ "loss": 1.6324,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.5168539325842696,
806
+ "grad_norm": 0.4115655720233917,
807
+ "learning_rate": 0.0002,
808
+ "loss": 1.6144,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.539325842696629,
813
+ "grad_norm": 0.45315614342689514,
814
+ "learning_rate": 0.0002,
815
+ "loss": 1.5999,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.561797752808989,
820
+ "grad_norm": 0.48349013924598694,
821
+ "learning_rate": 0.0002,
822
+ "loss": 1.654,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.5842696629213484,
827
+ "grad_norm": 0.4827800691127777,
828
+ "learning_rate": 0.0002,
829
+ "loss": 1.6688,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.606741573033708,
834
+ "grad_norm": 0.4685794711112976,
835
+ "learning_rate": 0.0002,
836
+ "loss": 1.6993,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.629213483146067,
841
+ "grad_norm": 0.46395015716552734,
842
+ "learning_rate": 0.0002,
843
+ "loss": 1.616,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.6516853932584272,
848
+ "grad_norm": 0.4605198800563812,
849
+ "learning_rate": 0.0002,
850
+ "loss": 1.5945,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.6741573033707864,
855
+ "grad_norm": 0.4916316270828247,
856
+ "learning_rate": 0.0002,
857
+ "loss": 1.6542,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.696629213483146,
862
+ "grad_norm": 0.4382898807525635,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.6414,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.7191011235955056,
869
+ "grad_norm": 0.4522838592529297,
870
+ "learning_rate": 0.0002,
871
+ "loss": 1.6681,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.741573033707865,
876
+ "grad_norm": 0.5802963376045227,
877
+ "learning_rate": 0.0002,
878
+ "loss": 1.6566,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.764044943820225,
883
+ "grad_norm": 0.44280654191970825,
884
+ "learning_rate": 0.0002,
885
+ "loss": 1.6628,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.7865168539325844,
890
+ "grad_norm": 0.4436502456665039,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.6967,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.808988764044944,
897
+ "grad_norm": 0.4817657768726349,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.5711,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.831460674157303,
904
+ "grad_norm": 0.46678975224494934,
905
+ "learning_rate": 0.0002,
906
+ "loss": 1.6143,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.853932584269663,
911
+ "grad_norm": 0.5505899786949158,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.5848,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.8764044943820224,
918
+ "grad_norm": 0.46449190378189087,
919
+ "learning_rate": 0.0002,
920
+ "loss": 1.6445,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.898876404494382,
925
+ "grad_norm": 0.5431554913520813,
926
+ "learning_rate": 0.0002,
927
+ "loss": 1.616,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.9213483146067416,
932
+ "grad_norm": 0.44165968894958496,
933
+ "learning_rate": 0.0002,
934
+ "loss": 1.69,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.943820224719101,
939
+ "grad_norm": 0.5253956317901611,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.6961,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.966292134831461,
946
+ "grad_norm": 0.42881500720977783,
947
+ "learning_rate": 0.0002,
948
+ "loss": 1.6085,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.98876404494382,
953
+ "grad_norm": 0.4666648507118225,
954
+ "learning_rate": 0.0002,
955
+ "loss": 1.5666,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 3.0,
960
+ "eval_loss": 1.841871976852417,
961
+ "eval_runtime": 38.4576,
962
+ "eval_samples_per_second": 13.391,
963
+ "eval_steps_per_second": 1.69,
964
+ "step": 1335
965
+ },
966
+ {
967
+ "epoch": 3.0112359550561796,
968
+ "grad_norm": 0.4540881812572479,
969
+ "learning_rate": 0.0002,
970
+ "loss": 1.4981,
971
+ "step": 1340
972
+ },
973
+ {
974
+ "epoch": 3.033707865168539,
975
+ "grad_norm": 0.5289544463157654,
976
+ "learning_rate": 0.0002,
977
+ "loss": 1.4593,
978
+ "step": 1350
979
+ },
980
+ {
981
+ "epoch": 3.056179775280899,
982
+ "grad_norm": 0.5404762029647827,
983
+ "learning_rate": 0.0002,
984
+ "loss": 1.5181,
985
+ "step": 1360
986
+ },
987
+ {
988
+ "epoch": 3.0786516853932584,
989
+ "grad_norm": 0.606574535369873,
990
+ "learning_rate": 0.0002,
991
+ "loss": 1.5327,
992
+ "step": 1370
993
+ },
994
+ {
995
+ "epoch": 3.101123595505618,
996
+ "grad_norm": 0.6293940544128418,
997
+ "learning_rate": 0.0002,
998
+ "loss": 1.5418,
999
+ "step": 1380
1000
+ },
1001
+ {
1002
+ "epoch": 3.1235955056179776,
1003
+ "grad_norm": 0.5431684851646423,
1004
+ "learning_rate": 0.0002,
1005
+ "loss": 1.4522,
1006
+ "step": 1390
1007
+ },
1008
+ {
1009
+ "epoch": 3.146067415730337,
1010
+ "grad_norm": 0.5571810007095337,
1011
+ "learning_rate": 0.0002,
1012
+ "loss": 1.6047,
1013
+ "step": 1400
1014
+ },
1015
+ {
1016
+ "epoch": 3.168539325842697,
1017
+ "grad_norm": 0.5232224464416504,
1018
+ "learning_rate": 0.0002,
1019
+ "loss": 1.5709,
1020
+ "step": 1410
1021
+ },
1022
+ {
1023
+ "epoch": 3.191011235955056,
1024
+ "grad_norm": 0.6176348924636841,
1025
+ "learning_rate": 0.0002,
1026
+ "loss": 1.5014,
1027
+ "step": 1420
1028
+ },
1029
+ {
1030
+ "epoch": 3.2134831460674156,
1031
+ "grad_norm": 0.5267609357833862,
1032
+ "learning_rate": 0.0002,
1033
+ "loss": 1.5398,
1034
+ "step": 1430
1035
+ },
1036
+ {
1037
+ "epoch": 3.235955056179775,
1038
+ "grad_norm": 0.6405419707298279,
1039
+ "learning_rate": 0.0002,
1040
+ "loss": 1.4821,
1041
+ "step": 1440
1042
+ },
1043
+ {
1044
+ "epoch": 3.258426966292135,
1045
+ "grad_norm": 0.6280969977378845,
1046
+ "learning_rate": 0.0002,
1047
+ "loss": 1.5365,
1048
+ "step": 1450
1049
+ },
1050
+ {
1051
+ "epoch": 3.2808988764044944,
1052
+ "grad_norm": 0.594437837600708,
1053
+ "learning_rate": 0.0002,
1054
+ "loss": 1.4962,
1055
+ "step": 1460
1056
+ },
1057
+ {
1058
+ "epoch": 3.303370786516854,
1059
+ "grad_norm": 0.5297112464904785,
1060
+ "learning_rate": 0.0002,
1061
+ "loss": 1.4714,
1062
+ "step": 1470
1063
+ },
1064
+ {
1065
+ "epoch": 3.3258426966292136,
1066
+ "grad_norm": 0.6481576561927795,
1067
+ "learning_rate": 0.0002,
1068
+ "loss": 1.5163,
1069
+ "step": 1480
1070
+ },
1071
+ {
1072
+ "epoch": 3.348314606741573,
1073
+ "grad_norm": 0.6006230711936951,
1074
+ "learning_rate": 0.0002,
1075
+ "loss": 1.5198,
1076
+ "step": 1490
1077
+ },
1078
+ {
1079
+ "epoch": 3.370786516853933,
1080
+ "grad_norm": 0.6718862652778625,
1081
+ "learning_rate": 0.0002,
1082
+ "loss": 1.5476,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 3.393258426966292,
1087
+ "grad_norm": 0.5663893222808838,
1088
+ "learning_rate": 0.0002,
1089
+ "loss": 1.484,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 3.4157303370786516,
1094
+ "grad_norm": 0.6176982522010803,
1095
+ "learning_rate": 0.0002,
1096
+ "loss": 1.4779,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 3.438202247191011,
1101
+ "grad_norm": 0.5643916130065918,
1102
+ "learning_rate": 0.0002,
1103
+ "loss": 1.5449,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 3.460674157303371,
1108
+ "grad_norm": 0.6312360763549805,
1109
+ "learning_rate": 0.0002,
1110
+ "loss": 1.5071,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 3.4831460674157304,
1115
+ "grad_norm": 0.6003469824790955,
1116
+ "learning_rate": 0.0002,
1117
+ "loss": 1.4793,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 3.50561797752809,
1122
+ "grad_norm": 0.635564923286438,
1123
+ "learning_rate": 0.0002,
1124
+ "loss": 1.5,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 3.5280898876404496,
1129
+ "grad_norm": 0.6120123863220215,
1130
+ "learning_rate": 0.0002,
1131
+ "loss": 1.5442,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 3.550561797752809,
1136
+ "grad_norm": 0.6079851388931274,
1137
+ "learning_rate": 0.0002,
1138
+ "loss": 1.5652,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 3.5730337078651684,
1143
+ "grad_norm": 0.5879889726638794,
1144
+ "learning_rate": 0.0002,
1145
+ "loss": 1.5934,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 3.595505617977528,
1150
+ "grad_norm": 0.618109405040741,
1151
+ "learning_rate": 0.0002,
1152
+ "loss": 1.5611,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 3.6179775280898876,
1157
+ "grad_norm": 0.608756422996521,
1158
+ "learning_rate": 0.0002,
1159
+ "loss": 1.4971,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 3.640449438202247,
1164
+ "grad_norm": 0.554905116558075,
1165
+ "learning_rate": 0.0002,
1166
+ "loss": 1.491,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 3.662921348314607,
1171
+ "grad_norm": 0.5828419327735901,
1172
+ "learning_rate": 0.0002,
1173
+ "loss": 1.5821,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 3.6853932584269664,
1178
+ "grad_norm": 0.655953049659729,
1179
+ "learning_rate": 0.0002,
1180
+ "loss": 1.5573,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 3.7078651685393256,
1185
+ "grad_norm": 0.5976583361625671,
1186
+ "learning_rate": 0.0002,
1187
+ "loss": 1.5455,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 3.7303370786516856,
1192
+ "grad_norm": 0.5679733157157898,
1193
+ "learning_rate": 0.0002,
1194
+ "loss": 1.599,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 3.752808988764045,
1199
+ "grad_norm": 0.6647416353225708,
1200
+ "learning_rate": 0.0002,
1201
+ "loss": 1.4749,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 3.7752808988764044,
1206
+ "grad_norm": 0.6381834745407104,
1207
+ "learning_rate": 0.0002,
1208
+ "loss": 1.5356,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 3.797752808988764,
1213
+ "grad_norm": 0.6131210327148438,
1214
+ "learning_rate": 0.0002,
1215
+ "loss": 1.4792,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 3.8202247191011236,
1220
+ "grad_norm": 0.6219302415847778,
1221
+ "learning_rate": 0.0002,
1222
+ "loss": 1.6249,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 3.842696629213483,
1227
+ "grad_norm": 0.5793370604515076,
1228
+ "learning_rate": 0.0002,
1229
+ "loss": 1.4764,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 3.865168539325843,
1234
+ "grad_norm": 0.5806208848953247,
1235
+ "learning_rate": 0.0002,
1236
+ "loss": 1.5534,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 3.8876404494382024,
1241
+ "grad_norm": 0.5671854019165039,
1242
+ "learning_rate": 0.0002,
1243
+ "loss": 1.556,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 3.9101123595505616,
1248
+ "grad_norm": 0.5803307890892029,
1249
+ "learning_rate": 0.0002,
1250
+ "loss": 1.6529,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 3.932584269662921,
1255
+ "grad_norm": 0.5710529088973999,
1256
+ "learning_rate": 0.0002,
1257
+ "loss": 1.4725,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 3.955056179775281,
1262
+ "grad_norm": 0.5724003314971924,
1263
+ "learning_rate": 0.0002,
1264
+ "loss": 1.5023,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 3.9775280898876404,
1269
+ "grad_norm": 0.556728184223175,
1270
+ "learning_rate": 0.0002,
1271
+ "loss": 1.4568,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 4.0,
1276
+ "grad_norm": 0.5443143248558044,
1277
+ "learning_rate": 0.0002,
1278
+ "loss": 1.5052,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 4.0,
1283
+ "eval_loss": 1.8935941457748413,
1284
+ "eval_runtime": 38.4958,
1285
+ "eval_samples_per_second": 13.378,
1286
+ "eval_steps_per_second": 1.688,
1287
+ "step": 1780
1288
+ },
1289
+ {
1290
+ "epoch": 4.022471910112359,
1291
+ "grad_norm": 0.7063950300216675,
1292
+ "learning_rate": 0.0002,
1293
+ "loss": 1.4047,
1294
+ "step": 1790
1295
+ },
1296
+ {
1297
+ "epoch": 4.044943820224719,
1298
+ "grad_norm": 0.8538862466812134,
1299
+ "learning_rate": 0.0002,
1300
+ "loss": 1.3516,
1301
+ "step": 1800
1302
+ },
1303
+ {
1304
+ "epoch": 4.067415730337078,
1305
+ "grad_norm": 0.6716609597206116,
1306
+ "learning_rate": 0.0002,
1307
+ "loss": 1.3261,
1308
+ "step": 1810
1309
+ },
1310
+ {
1311
+ "epoch": 4.089887640449438,
1312
+ "grad_norm": 0.8187614679336548,
1313
+ "learning_rate": 0.0002,
1314
+ "loss": 1.3477,
1315
+ "step": 1820
1316
+ },
1317
+ {
1318
+ "epoch": 4.112359550561798,
1319
+ "grad_norm": 0.6903043985366821,
1320
+ "learning_rate": 0.0002,
1321
+ "loss": 1.334,
1322
+ "step": 1830
1323
+ },
1324
+ {
1325
+ "epoch": 4.134831460674158,
1326
+ "grad_norm": 0.6804471611976624,
1327
+ "learning_rate": 0.0002,
1328
+ "loss": 1.3283,
1329
+ "step": 1840
1330
+ },
1331
+ {
1332
+ "epoch": 4.157303370786517,
1333
+ "grad_norm": 0.7785346508026123,
1334
+ "learning_rate": 0.0002,
1335
+ "loss": 1.3487,
1336
+ "step": 1850
1337
+ },
1338
+ {
1339
+ "epoch": 4.179775280898877,
1340
+ "grad_norm": 0.7553297281265259,
1341
+ "learning_rate": 0.0002,
1342
+ "loss": 1.3537,
1343
+ "step": 1860
1344
+ },
1345
+ {
1346
+ "epoch": 4.202247191011236,
1347
+ "grad_norm": 0.7317661643028259,
1348
+ "learning_rate": 0.0002,
1349
+ "loss": 1.3752,
1350
+ "step": 1870
1351
+ },
1352
+ {
1353
+ "epoch": 4.224719101123595,
1354
+ "grad_norm": 0.701454758644104,
1355
+ "learning_rate": 0.0002,
1356
+ "loss": 1.3335,
1357
+ "step": 1880
1358
+ },
1359
+ {
1360
+ "epoch": 4.247191011235955,
1361
+ "grad_norm": 0.7360146045684814,
1362
+ "learning_rate": 0.0002,
1363
+ "loss": 1.345,
1364
+ "step": 1890
1365
+ },
1366
+ {
1367
+ "epoch": 4.269662921348314,
1368
+ "grad_norm": 0.7889209389686584,
1369
+ "learning_rate": 0.0002,
1370
+ "loss": 1.3541,
1371
+ "step": 1900
1372
+ },
1373
+ {
1374
+ "epoch": 4.292134831460674,
1375
+ "grad_norm": 0.7613265514373779,
1376
+ "learning_rate": 0.0002,
1377
+ "loss": 1.3658,
1378
+ "step": 1910
1379
+ },
1380
+ {
1381
+ "epoch": 4.314606741573034,
1382
+ "grad_norm": 0.8249233365058899,
1383
+ "learning_rate": 0.0002,
1384
+ "loss": 1.393,
1385
+ "step": 1920
1386
+ },
1387
+ {
1388
+ "epoch": 4.337078651685394,
1389
+ "grad_norm": 0.7492292523384094,
1390
+ "learning_rate": 0.0002,
1391
+ "loss": 1.3723,
1392
+ "step": 1930
1393
+ },
1394
+ {
1395
+ "epoch": 4.359550561797753,
1396
+ "grad_norm": 0.7631386518478394,
1397
+ "learning_rate": 0.0002,
1398
+ "loss": 1.3372,
1399
+ "step": 1940
1400
+ },
1401
+ {
1402
+ "epoch": 4.382022471910112,
1403
+ "grad_norm": 0.7044921517372131,
1404
+ "learning_rate": 0.0002,
1405
+ "loss": 1.3725,
1406
+ "step": 1950
1407
+ },
1408
+ {
1409
+ "epoch": 4.404494382022472,
1410
+ "grad_norm": 0.7950063943862915,
1411
+ "learning_rate": 0.0002,
1412
+ "loss": 1.3077,
1413
+ "step": 1960
1414
+ },
1415
+ {
1416
+ "epoch": 4.426966292134831,
1417
+ "grad_norm": 0.7764235138893127,
1418
+ "learning_rate": 0.0002,
1419
+ "loss": 1.3728,
1420
+ "step": 1970
1421
+ },
1422
+ {
1423
+ "epoch": 4.449438202247191,
1424
+ "grad_norm": 0.77325040102005,
1425
+ "learning_rate": 0.0002,
1426
+ "loss": 1.3991,
1427
+ "step": 1980
1428
+ },
1429
+ {
1430
+ "epoch": 4.47191011235955,
1431
+ "grad_norm": 0.8376508355140686,
1432
+ "learning_rate": 0.0002,
1433
+ "loss": 1.4062,
1434
+ "step": 1990
1435
+ },
1436
+ {
1437
+ "epoch": 4.49438202247191,
1438
+ "grad_norm": 0.7711764574050903,
1439
+ "learning_rate": 0.0002,
1440
+ "loss": 1.3645,
1441
+ "step": 2000
1442
+ },
1443
+ {
1444
+ "epoch": 4.51685393258427,
1445
+ "grad_norm": 0.766307532787323,
1446
+ "learning_rate": 0.0002,
1447
+ "loss": 1.3447,
1448
+ "step": 2010
1449
+ },
1450
+ {
1451
+ "epoch": 4.539325842696629,
1452
+ "grad_norm": 0.7309888005256653,
1453
+ "learning_rate": 0.0002,
1454
+ "loss": 1.3415,
1455
+ "step": 2020
1456
+ },
1457
+ {
1458
+ "epoch": 4.561797752808989,
1459
+ "grad_norm": 0.7707177400588989,
1460
+ "learning_rate": 0.0002,
1461
+ "loss": 1.4652,
1462
+ "step": 2030
1463
+ },
1464
+ {
1465
+ "epoch": 4.584269662921348,
1466
+ "grad_norm": 0.7972665429115295,
1467
+ "learning_rate": 0.0002,
1468
+ "loss": 1.411,
1469
+ "step": 2040
1470
+ },
1471
+ {
1472
+ "epoch": 4.606741573033708,
1473
+ "grad_norm": 0.8435423374176025,
1474
+ "learning_rate": 0.0002,
1475
+ "loss": 1.3848,
1476
+ "step": 2050
1477
+ },
1478
+ {
1479
+ "epoch": 4.629213483146067,
1480
+ "grad_norm": 0.7513273358345032,
1481
+ "learning_rate": 0.0002,
1482
+ "loss": 1.4464,
1483
+ "step": 2060
1484
+ },
1485
+ {
1486
+ "epoch": 4.651685393258427,
1487
+ "grad_norm": 0.8571695685386658,
1488
+ "learning_rate": 0.0002,
1489
+ "loss": 1.3481,
1490
+ "step": 2070
1491
+ },
1492
+ {
1493
+ "epoch": 4.674157303370786,
1494
+ "grad_norm": 0.7924894690513611,
1495
+ "learning_rate": 0.0002,
1496
+ "loss": 1.3812,
1497
+ "step": 2080
1498
+ },
1499
+ {
1500
+ "epoch": 4.696629213483146,
1501
+ "grad_norm": 0.7428702116012573,
1502
+ "learning_rate": 0.0002,
1503
+ "loss": 1.367,
1504
+ "step": 2090
1505
+ },
1506
+ {
1507
+ "epoch": 4.719101123595506,
1508
+ "grad_norm": 0.7480676174163818,
1509
+ "learning_rate": 0.0002,
1510
+ "loss": 1.4409,
1511
+ "step": 2100
1512
+ },
1513
+ {
1514
+ "epoch": 4.741573033707866,
1515
+ "grad_norm": 0.7893720865249634,
1516
+ "learning_rate": 0.0002,
1517
+ "loss": 1.3731,
1518
+ "step": 2110
1519
+ },
1520
+ {
1521
+ "epoch": 4.764044943820225,
1522
+ "grad_norm": 0.8142390251159668,
1523
+ "learning_rate": 0.0002,
1524
+ "loss": 1.392,
1525
+ "step": 2120
1526
+ },
1527
+ {
1528
+ "epoch": 4.786516853932584,
1529
+ "grad_norm": 0.737934410572052,
1530
+ "learning_rate": 0.0002,
1531
+ "loss": 1.3821,
1532
+ "step": 2130
1533
+ },
1534
+ {
1535
+ "epoch": 4.808988764044944,
1536
+ "grad_norm": 0.799316942691803,
1537
+ "learning_rate": 0.0002,
1538
+ "loss": 1.4404,
1539
+ "step": 2140
1540
+ },
1541
+ {
1542
+ "epoch": 4.831460674157303,
1543
+ "grad_norm": 0.8206349015235901,
1544
+ "learning_rate": 0.0002,
1545
+ "loss": 1.4039,
1546
+ "step": 2150
1547
+ },
1548
+ {
1549
+ "epoch": 4.853932584269663,
1550
+ "grad_norm": 0.8419018387794495,
1551
+ "learning_rate": 0.0002,
1552
+ "loss": 1.3908,
1553
+ "step": 2160
1554
+ },
1555
+ {
1556
+ "epoch": 4.876404494382022,
1557
+ "grad_norm": 0.8047335743904114,
1558
+ "learning_rate": 0.0002,
1559
+ "loss": 1.45,
1560
+ "step": 2170
1561
+ },
1562
+ {
1563
+ "epoch": 4.898876404494382,
1564
+ "grad_norm": 0.7250169515609741,
1565
+ "learning_rate": 0.0002,
1566
+ "loss": 1.4097,
1567
+ "step": 2180
1568
+ },
1569
+ {
1570
+ "epoch": 4.921348314606742,
1571
+ "grad_norm": 0.9156671166419983,
1572
+ "learning_rate": 0.0002,
1573
+ "loss": 1.4198,
1574
+ "step": 2190
1575
+ },
1576
+ {
1577
+ "epoch": 4.943820224719101,
1578
+ "grad_norm": 0.747611403465271,
1579
+ "learning_rate": 0.0002,
1580
+ "loss": 1.4354,
1581
+ "step": 2200
1582
+ },
1583
+ {
1584
+ "epoch": 4.966292134831461,
1585
+ "grad_norm": 0.8482937216758728,
1586
+ "learning_rate": 0.0002,
1587
+ "loss": 1.4381,
1588
+ "step": 2210
1589
+ },
1590
+ {
1591
+ "epoch": 4.98876404494382,
1592
+ "grad_norm": 0.8300044536590576,
1593
+ "learning_rate": 0.0002,
1594
+ "loss": 1.4087,
1595
+ "step": 2220
1596
+ },
1597
+ {
1598
+ "epoch": 5.0,
1599
+ "eval_loss": 1.9691932201385498,
1600
+ "eval_runtime": 38.7832,
1601
+ "eval_samples_per_second": 13.279,
1602
+ "eval_steps_per_second": 1.676,
1603
+ "step": 2225
1604
+ }
1605
+ ],
1606
+ "logging_steps": 10,
1607
+ "max_steps": 3560,
1608
+ "num_input_tokens_seen": 0,
1609
+ "num_train_epochs": 8,
1610
+ "save_steps": 200,
1611
+ "stateful_callbacks": {
1612
+ "TrainerControl": {
1613
+ "args": {
1614
+ "should_epoch_stop": false,
1615
+ "should_evaluate": false,
1616
+ "should_log": false,
1617
+ "should_save": true,
1618
+ "should_training_stop": false
1619
+ },
1620
+ "attributes": {}
1621
+ }
1622
+ },
1623
+ "total_flos": 1.029680180232192e+17,
1624
+ "train_batch_size": 1,
1625
+ "trial_name": null,
1626
+ "trial_params": null
1627
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2225/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70bb087d22fb0995345805c545302523633dddfce545390f986898a00d9c23d9
3
+ size 5560
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c79602428dc60441c6efdc407604d2bbf54bceeaeb4ee58ec87893775f03f1
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9932972e7f8a489063026bbd8b8a8074050938cec8955fb22e0cff992dc52fc
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a824e60c80423253e497d4bd5e427bcecc45201fa4dc0efa470f1518e1c7abf5
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eff5f7e9ad7056d622557a522a13afee4873f62f5fe7f50b82966670933743d7
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/trainer_state.json ADDED
@@ -0,0 +1,1950 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8264012336730957,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-890",
4
+ "epoch": 6.0,
5
+ "eval_steps": 10,
6
+ "global_step": 2670,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02247191011235955,
13
+ "grad_norm": 0.541088342666626,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.6217,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0449438202247191,
20
+ "grad_norm": 0.606726348400116,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.309,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06741573033707865,
27
+ "grad_norm": 0.5244829058647156,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.0677,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0898876404494382,
34
+ "grad_norm": 0.6728479862213135,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.9807,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.11235955056179775,
41
+ "grad_norm": 0.8560609221458435,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.944,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.1348314606741573,
48
+ "grad_norm": 0.49180933833122253,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9372,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15730337078651685,
55
+ "grad_norm": 0.49781936407089233,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.9051,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1797752808988764,
62
+ "grad_norm": 0.5396708846092224,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.7978,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.20224719101123595,
69
+ "grad_norm": 0.478624552488327,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.8758,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2247191011235955,
76
+ "grad_norm": 0.8880449533462524,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8928,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.24719101123595505,
83
+ "grad_norm": 0.43290555477142334,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.8504,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2696629213483146,
90
+ "grad_norm": 0.438387006521225,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8536,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.29213483146067415,
97
+ "grad_norm": 0.4131482243537903,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.8655,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.3146067415730337,
104
+ "grad_norm": 0.5160607099533081,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.9063,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.33707865168539325,
111
+ "grad_norm": 0.3617960214614868,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.792,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.3595505617977528,
118
+ "grad_norm": 0.5344526767730713,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.9222,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.38202247191011235,
125
+ "grad_norm": 0.37921762466430664,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.8478,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.4044943820224719,
132
+ "grad_norm": 0.431815505027771,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.7882,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.42696629213483145,
139
+ "grad_norm": 0.4125252366065979,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8431,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.449438202247191,
146
+ "grad_norm": 0.45420965552330017,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.7677,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.47191011235955055,
153
+ "grad_norm": 0.471342533826828,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.8083,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4943820224719101,
160
+ "grad_norm": 0.3953711986541748,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.8915,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5168539325842697,
167
+ "grad_norm": 0.3793153166770935,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.8153,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5393258426966292,
174
+ "grad_norm": 0.3719729483127594,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.7948,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5617977528089888,
181
+ "grad_norm": 0.4091097116470337,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.8293,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5842696629213483,
188
+ "grad_norm": 0.38691720366477966,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.8054,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6067415730337079,
195
+ "grad_norm": 0.39904487133026123,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8962,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6292134831460674,
202
+ "grad_norm": 0.36792582273483276,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.862,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.651685393258427,
209
+ "grad_norm": 0.3575645685195923,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8117,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6741573033707865,
216
+ "grad_norm": 0.34943437576293945,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.7338,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6966292134831461,
223
+ "grad_norm": 0.4369798004627228,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.7357,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7191011235955056,
230
+ "grad_norm": 0.4053204357624054,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.8257,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7415730337078652,
237
+ "grad_norm": 0.4032869338989258,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.7936,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7640449438202247,
244
+ "grad_norm": 0.393141508102417,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.9005,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7865168539325843,
251
+ "grad_norm": 0.3401991128921509,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.8525,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8089887640449438,
258
+ "grad_norm": 0.3157802224159241,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.7811,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8314606741573034,
265
+ "grad_norm": 0.34539058804512024,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.766,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8539325842696629,
272
+ "grad_norm": 0.3391708731651306,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.7687,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8764044943820225,
279
+ "grad_norm": 0.37594684958457947,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.7749,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.898876404494382,
286
+ "grad_norm": 0.387704461812973,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.7805,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9213483146067416,
293
+ "grad_norm": 0.5300629138946533,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.8255,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9438202247191011,
300
+ "grad_norm": 0.35356250405311584,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.7229,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9662921348314607,
307
+ "grad_norm": 0.3641810119152069,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.8647,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9887640449438202,
314
+ "grad_norm": 0.3925739824771881,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.7762,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 1.0,
321
+ "eval_loss": 1.829880714416504,
322
+ "eval_runtime": 38.6272,
323
+ "eval_samples_per_second": 13.333,
324
+ "eval_steps_per_second": 1.683,
325
+ "step": 445
326
+ },
327
+ {
328
+ "epoch": 1.0112359550561798,
329
+ "grad_norm": 0.324361115694046,
330
+ "learning_rate": 0.0002,
331
+ "loss": 1.7515,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.0337078651685394,
336
+ "grad_norm": 0.37567344307899475,
337
+ "learning_rate": 0.0002,
338
+ "loss": 1.7803,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.0561797752808988,
343
+ "grad_norm": 0.336347758769989,
344
+ "learning_rate": 0.0002,
345
+ "loss": 1.8442,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0786516853932584,
350
+ "grad_norm": 0.39281758666038513,
351
+ "learning_rate": 0.0002,
352
+ "loss": 1.7169,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.101123595505618,
357
+ "grad_norm": 0.348486989736557,
358
+ "learning_rate": 0.0002,
359
+ "loss": 1.803,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.1235955056179776,
364
+ "grad_norm": 0.3939574062824249,
365
+ "learning_rate": 0.0002,
366
+ "loss": 1.6511,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.146067415730337,
371
+ "grad_norm": 0.3566303849220276,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.692,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.1685393258426966,
378
+ "grad_norm": 0.44443410634994507,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.7093,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1910112359550562,
385
+ "grad_norm": 0.40352755784988403,
386
+ "learning_rate": 0.0002,
387
+ "loss": 1.7204,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.2134831460674158,
392
+ "grad_norm": 0.393235445022583,
393
+ "learning_rate": 0.0002,
394
+ "loss": 1.7693,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.2359550561797752,
399
+ "grad_norm": 0.38268715143203735,
400
+ "learning_rate": 0.0002,
401
+ "loss": 1.7402,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.2584269662921348,
406
+ "grad_norm": 0.40748143196105957,
407
+ "learning_rate": 0.0002,
408
+ "loss": 1.8007,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2808988764044944,
413
+ "grad_norm": 0.46578362584114075,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.7096,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.303370786516854,
420
+ "grad_norm": 0.4152059853076935,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.753,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.3258426966292136,
427
+ "grad_norm": 0.39794254302978516,
428
+ "learning_rate": 0.0002,
429
+ "loss": 1.7658,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.348314606741573,
434
+ "grad_norm": 0.3964073359966278,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.683,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.3707865168539326,
441
+ "grad_norm": 0.37973660230636597,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.7464,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.3932584269662922,
448
+ "grad_norm": 0.4126802384853363,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.6766,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.4157303370786516,
455
+ "grad_norm": 0.3873387575149536,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.7876,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.4382022471910112,
462
+ "grad_norm": 0.39390191435813904,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.7841,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.4606741573033708,
469
+ "grad_norm": 0.4302954375743866,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.7482,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.4831460674157304,
476
+ "grad_norm": 0.3631756901741028,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.7608,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.50561797752809,
483
+ "grad_norm": 0.3835321366786957,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.7266,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.5280898876404494,
490
+ "grad_norm": 0.45179641246795654,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.7254,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.550561797752809,
497
+ "grad_norm": 0.4173226058483124,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.7541,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5730337078651684,
504
+ "grad_norm": 0.35887855291366577,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.7895,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.595505617977528,
511
+ "grad_norm": 0.40731844305992126,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.7209,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.6179775280898876,
518
+ "grad_norm": 0.4147540330886841,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.6606,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.6404494382022472,
525
+ "grad_norm": 0.37640494108200073,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.7385,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.6629213483146068,
532
+ "grad_norm": 0.3784808814525604,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.7021,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6853932584269664,
539
+ "grad_norm": 0.4551489055156708,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.7411,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.7078651685393258,
546
+ "grad_norm": 0.3906891345977783,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.7814,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.7303370786516854,
553
+ "grad_norm": 0.3876253664493561,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.7622,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.7528089887640448,
560
+ "grad_norm": 0.36962684988975525,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.7727,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.7752808988764044,
567
+ "grad_norm": 0.392286092042923,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.7796,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.797752808988764,
574
+ "grad_norm": 0.368129700422287,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.7455,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.8202247191011236,
581
+ "grad_norm": 0.42102697491645813,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7808,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.8426966292134832,
588
+ "grad_norm": 0.4314707815647125,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.7688,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.8651685393258428,
595
+ "grad_norm": 0.3763786554336548,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.7465,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.8876404494382022,
602
+ "grad_norm": 0.34446850419044495,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.7291,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.9101123595505618,
609
+ "grad_norm": 0.3806961476802826,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.7014,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.9325842696629212,
616
+ "grad_norm": 0.38291847705841064,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.6652,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.9550561797752808,
623
+ "grad_norm": 0.4361240565776825,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.6964,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9775280898876404,
630
+ "grad_norm": 0.39230653643608093,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.7818,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 2.0,
637
+ "grad_norm": 0.3856890797615051,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.7174,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 2.0,
644
+ "eval_loss": 1.8264012336730957,
645
+ "eval_runtime": 38.4572,
646
+ "eval_samples_per_second": 13.392,
647
+ "eval_steps_per_second": 1.69,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.0224719101123596,
652
+ "grad_norm": 0.37172746658325195,
653
+ "learning_rate": 0.0002,
654
+ "loss": 1.5571,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.044943820224719,
659
+ "grad_norm": 0.4285264313220978,
660
+ "learning_rate": 0.0002,
661
+ "loss": 1.7088,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.067415730337079,
666
+ "grad_norm": 0.4178760051727295,
667
+ "learning_rate": 0.0002,
668
+ "loss": 1.6465,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.0898876404494384,
673
+ "grad_norm": 0.41439080238342285,
674
+ "learning_rate": 0.0002,
675
+ "loss": 1.6718,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.1123595505617976,
680
+ "grad_norm": 0.44750887155532837,
681
+ "learning_rate": 0.0002,
682
+ "loss": 1.6632,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.134831460674157,
687
+ "grad_norm": 0.47943830490112305,
688
+ "learning_rate": 0.0002,
689
+ "loss": 1.6886,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.157303370786517,
694
+ "grad_norm": 0.41972824931144714,
695
+ "learning_rate": 0.0002,
696
+ "loss": 1.7143,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.1797752808988764,
701
+ "grad_norm": 0.45687606930732727,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.6282,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.202247191011236,
708
+ "grad_norm": 3.270933151245117,
709
+ "learning_rate": 0.0002,
710
+ "loss": 1.6293,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.2247191011235956,
715
+ "grad_norm": 0.5009722709655762,
716
+ "learning_rate": 0.0002,
717
+ "loss": 1.6667,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.247191011235955,
722
+ "grad_norm": 0.47534242272377014,
723
+ "learning_rate": 0.0002,
724
+ "loss": 1.6737,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.2696629213483144,
729
+ "grad_norm": 0.4659167230129242,
730
+ "learning_rate": 0.0002,
731
+ "loss": 1.6121,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.292134831460674,
736
+ "grad_norm": 0.4227055013179779,
737
+ "learning_rate": 0.0002,
738
+ "loss": 1.6565,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.3146067415730336,
743
+ "grad_norm": 0.4480970799922943,
744
+ "learning_rate": 0.0002,
745
+ "loss": 1.6358,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.337078651685393,
750
+ "grad_norm": 0.46239933371543884,
751
+ "learning_rate": 0.0002,
752
+ "loss": 1.6459,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.359550561797753,
757
+ "grad_norm": 0.4576965570449829,
758
+ "learning_rate": 0.0002,
759
+ "loss": 1.7212,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.3820224719101124,
764
+ "grad_norm": 0.48324525356292725,
765
+ "learning_rate": 0.0002,
766
+ "loss": 1.6787,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.404494382022472,
771
+ "grad_norm": 0.4669286906719208,
772
+ "learning_rate": 0.0002,
773
+ "loss": 1.6773,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.4269662921348316,
778
+ "grad_norm": 0.5118905901908875,
779
+ "learning_rate": 0.0002,
780
+ "loss": 1.5971,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.449438202247191,
785
+ "grad_norm": 0.4905109405517578,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.6652,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.4719101123595504,
792
+ "grad_norm": 0.5466307401657104,
793
+ "learning_rate": 0.0002,
794
+ "loss": 1.6569,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.49438202247191,
799
+ "grad_norm": 0.483541876077652,
800
+ "learning_rate": 0.0002,
801
+ "loss": 1.6324,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.5168539325842696,
806
+ "grad_norm": 0.4115655720233917,
807
+ "learning_rate": 0.0002,
808
+ "loss": 1.6144,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.539325842696629,
813
+ "grad_norm": 0.45315614342689514,
814
+ "learning_rate": 0.0002,
815
+ "loss": 1.5999,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.561797752808989,
820
+ "grad_norm": 0.48349013924598694,
821
+ "learning_rate": 0.0002,
822
+ "loss": 1.654,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.5842696629213484,
827
+ "grad_norm": 0.4827800691127777,
828
+ "learning_rate": 0.0002,
829
+ "loss": 1.6688,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.606741573033708,
834
+ "grad_norm": 0.4685794711112976,
835
+ "learning_rate": 0.0002,
836
+ "loss": 1.6993,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.629213483146067,
841
+ "grad_norm": 0.46395015716552734,
842
+ "learning_rate": 0.0002,
843
+ "loss": 1.616,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.6516853932584272,
848
+ "grad_norm": 0.4605198800563812,
849
+ "learning_rate": 0.0002,
850
+ "loss": 1.5945,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.6741573033707864,
855
+ "grad_norm": 0.4916316270828247,
856
+ "learning_rate": 0.0002,
857
+ "loss": 1.6542,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.696629213483146,
862
+ "grad_norm": 0.4382898807525635,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.6414,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.7191011235955056,
869
+ "grad_norm": 0.4522838592529297,
870
+ "learning_rate": 0.0002,
871
+ "loss": 1.6681,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.741573033707865,
876
+ "grad_norm": 0.5802963376045227,
877
+ "learning_rate": 0.0002,
878
+ "loss": 1.6566,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.764044943820225,
883
+ "grad_norm": 0.44280654191970825,
884
+ "learning_rate": 0.0002,
885
+ "loss": 1.6628,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.7865168539325844,
890
+ "grad_norm": 0.4436502456665039,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.6967,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.808988764044944,
897
+ "grad_norm": 0.4817657768726349,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.5711,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.831460674157303,
904
+ "grad_norm": 0.46678975224494934,
905
+ "learning_rate": 0.0002,
906
+ "loss": 1.6143,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.853932584269663,
911
+ "grad_norm": 0.5505899786949158,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.5848,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.8764044943820224,
918
+ "grad_norm": 0.46449190378189087,
919
+ "learning_rate": 0.0002,
920
+ "loss": 1.6445,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.898876404494382,
925
+ "grad_norm": 0.5431554913520813,
926
+ "learning_rate": 0.0002,
927
+ "loss": 1.616,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.9213483146067416,
932
+ "grad_norm": 0.44165968894958496,
933
+ "learning_rate": 0.0002,
934
+ "loss": 1.69,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.943820224719101,
939
+ "grad_norm": 0.5253956317901611,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.6961,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.966292134831461,
946
+ "grad_norm": 0.42881500720977783,
947
+ "learning_rate": 0.0002,
948
+ "loss": 1.6085,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.98876404494382,
953
+ "grad_norm": 0.4666648507118225,
954
+ "learning_rate": 0.0002,
955
+ "loss": 1.5666,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 3.0,
960
+ "eval_loss": 1.841871976852417,
961
+ "eval_runtime": 38.4576,
962
+ "eval_samples_per_second": 13.391,
963
+ "eval_steps_per_second": 1.69,
964
+ "step": 1335
965
+ },
966
+ {
967
+ "epoch": 3.0112359550561796,
968
+ "grad_norm": 0.4540881812572479,
969
+ "learning_rate": 0.0002,
970
+ "loss": 1.4981,
971
+ "step": 1340
972
+ },
973
+ {
974
+ "epoch": 3.033707865168539,
975
+ "grad_norm": 0.5289544463157654,
976
+ "learning_rate": 0.0002,
977
+ "loss": 1.4593,
978
+ "step": 1350
979
+ },
980
+ {
981
+ "epoch": 3.056179775280899,
982
+ "grad_norm": 0.5404762029647827,
983
+ "learning_rate": 0.0002,
984
+ "loss": 1.5181,
985
+ "step": 1360
986
+ },
987
+ {
988
+ "epoch": 3.0786516853932584,
989
+ "grad_norm": 0.606574535369873,
990
+ "learning_rate": 0.0002,
991
+ "loss": 1.5327,
992
+ "step": 1370
993
+ },
994
+ {
995
+ "epoch": 3.101123595505618,
996
+ "grad_norm": 0.6293940544128418,
997
+ "learning_rate": 0.0002,
998
+ "loss": 1.5418,
999
+ "step": 1380
1000
+ },
1001
+ {
1002
+ "epoch": 3.1235955056179776,
1003
+ "grad_norm": 0.5431684851646423,
1004
+ "learning_rate": 0.0002,
1005
+ "loss": 1.4522,
1006
+ "step": 1390
1007
+ },
1008
+ {
1009
+ "epoch": 3.146067415730337,
1010
+ "grad_norm": 0.5571810007095337,
1011
+ "learning_rate": 0.0002,
1012
+ "loss": 1.6047,
1013
+ "step": 1400
1014
+ },
1015
+ {
1016
+ "epoch": 3.168539325842697,
1017
+ "grad_norm": 0.5232224464416504,
1018
+ "learning_rate": 0.0002,
1019
+ "loss": 1.5709,
1020
+ "step": 1410
1021
+ },
1022
+ {
1023
+ "epoch": 3.191011235955056,
1024
+ "grad_norm": 0.6176348924636841,
1025
+ "learning_rate": 0.0002,
1026
+ "loss": 1.5014,
1027
+ "step": 1420
1028
+ },
1029
+ {
1030
+ "epoch": 3.2134831460674156,
1031
+ "grad_norm": 0.5267609357833862,
1032
+ "learning_rate": 0.0002,
1033
+ "loss": 1.5398,
1034
+ "step": 1430
1035
+ },
1036
+ {
1037
+ "epoch": 3.235955056179775,
1038
+ "grad_norm": 0.6405419707298279,
1039
+ "learning_rate": 0.0002,
1040
+ "loss": 1.4821,
1041
+ "step": 1440
1042
+ },
1043
+ {
1044
+ "epoch": 3.258426966292135,
1045
+ "grad_norm": 0.6280969977378845,
1046
+ "learning_rate": 0.0002,
1047
+ "loss": 1.5365,
1048
+ "step": 1450
1049
+ },
1050
+ {
1051
+ "epoch": 3.2808988764044944,
1052
+ "grad_norm": 0.594437837600708,
1053
+ "learning_rate": 0.0002,
1054
+ "loss": 1.4962,
1055
+ "step": 1460
1056
+ },
1057
+ {
1058
+ "epoch": 3.303370786516854,
1059
+ "grad_norm": 0.5297112464904785,
1060
+ "learning_rate": 0.0002,
1061
+ "loss": 1.4714,
1062
+ "step": 1470
1063
+ },
1064
+ {
1065
+ "epoch": 3.3258426966292136,
1066
+ "grad_norm": 0.6481576561927795,
1067
+ "learning_rate": 0.0002,
1068
+ "loss": 1.5163,
1069
+ "step": 1480
1070
+ },
1071
+ {
1072
+ "epoch": 3.348314606741573,
1073
+ "grad_norm": 0.6006230711936951,
1074
+ "learning_rate": 0.0002,
1075
+ "loss": 1.5198,
1076
+ "step": 1490
1077
+ },
1078
+ {
1079
+ "epoch": 3.370786516853933,
1080
+ "grad_norm": 0.6718862652778625,
1081
+ "learning_rate": 0.0002,
1082
+ "loss": 1.5476,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 3.393258426966292,
1087
+ "grad_norm": 0.5663893222808838,
1088
+ "learning_rate": 0.0002,
1089
+ "loss": 1.484,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 3.4157303370786516,
1094
+ "grad_norm": 0.6176982522010803,
1095
+ "learning_rate": 0.0002,
1096
+ "loss": 1.4779,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 3.438202247191011,
1101
+ "grad_norm": 0.5643916130065918,
1102
+ "learning_rate": 0.0002,
1103
+ "loss": 1.5449,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 3.460674157303371,
1108
+ "grad_norm": 0.6312360763549805,
1109
+ "learning_rate": 0.0002,
1110
+ "loss": 1.5071,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 3.4831460674157304,
1115
+ "grad_norm": 0.6003469824790955,
1116
+ "learning_rate": 0.0002,
1117
+ "loss": 1.4793,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 3.50561797752809,
1122
+ "grad_norm": 0.635564923286438,
1123
+ "learning_rate": 0.0002,
1124
+ "loss": 1.5,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 3.5280898876404496,
1129
+ "grad_norm": 0.6120123863220215,
1130
+ "learning_rate": 0.0002,
1131
+ "loss": 1.5442,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 3.550561797752809,
1136
+ "grad_norm": 0.6079851388931274,
1137
+ "learning_rate": 0.0002,
1138
+ "loss": 1.5652,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 3.5730337078651684,
1143
+ "grad_norm": 0.5879889726638794,
1144
+ "learning_rate": 0.0002,
1145
+ "loss": 1.5934,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 3.595505617977528,
1150
+ "grad_norm": 0.618109405040741,
1151
+ "learning_rate": 0.0002,
1152
+ "loss": 1.5611,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 3.6179775280898876,
1157
+ "grad_norm": 0.608756422996521,
1158
+ "learning_rate": 0.0002,
1159
+ "loss": 1.4971,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 3.640449438202247,
1164
+ "grad_norm": 0.554905116558075,
1165
+ "learning_rate": 0.0002,
1166
+ "loss": 1.491,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 3.662921348314607,
1171
+ "grad_norm": 0.5828419327735901,
1172
+ "learning_rate": 0.0002,
1173
+ "loss": 1.5821,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 3.6853932584269664,
1178
+ "grad_norm": 0.655953049659729,
1179
+ "learning_rate": 0.0002,
1180
+ "loss": 1.5573,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 3.7078651685393256,
1185
+ "grad_norm": 0.5976583361625671,
1186
+ "learning_rate": 0.0002,
1187
+ "loss": 1.5455,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 3.7303370786516856,
1192
+ "grad_norm": 0.5679733157157898,
1193
+ "learning_rate": 0.0002,
1194
+ "loss": 1.599,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 3.752808988764045,
1199
+ "grad_norm": 0.6647416353225708,
1200
+ "learning_rate": 0.0002,
1201
+ "loss": 1.4749,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 3.7752808988764044,
1206
+ "grad_norm": 0.6381834745407104,
1207
+ "learning_rate": 0.0002,
1208
+ "loss": 1.5356,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 3.797752808988764,
1213
+ "grad_norm": 0.6131210327148438,
1214
+ "learning_rate": 0.0002,
1215
+ "loss": 1.4792,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 3.8202247191011236,
1220
+ "grad_norm": 0.6219302415847778,
1221
+ "learning_rate": 0.0002,
1222
+ "loss": 1.6249,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 3.842696629213483,
1227
+ "grad_norm": 0.5793370604515076,
1228
+ "learning_rate": 0.0002,
1229
+ "loss": 1.4764,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 3.865168539325843,
1234
+ "grad_norm": 0.5806208848953247,
1235
+ "learning_rate": 0.0002,
1236
+ "loss": 1.5534,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 3.8876404494382024,
1241
+ "grad_norm": 0.5671854019165039,
1242
+ "learning_rate": 0.0002,
1243
+ "loss": 1.556,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 3.9101123595505616,
1248
+ "grad_norm": 0.5803307890892029,
1249
+ "learning_rate": 0.0002,
1250
+ "loss": 1.6529,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 3.932584269662921,
1255
+ "grad_norm": 0.5710529088973999,
1256
+ "learning_rate": 0.0002,
1257
+ "loss": 1.4725,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 3.955056179775281,
1262
+ "grad_norm": 0.5724003314971924,
1263
+ "learning_rate": 0.0002,
1264
+ "loss": 1.5023,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 3.9775280898876404,
1269
+ "grad_norm": 0.556728184223175,
1270
+ "learning_rate": 0.0002,
1271
+ "loss": 1.4568,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 4.0,
1276
+ "grad_norm": 0.5443143248558044,
1277
+ "learning_rate": 0.0002,
1278
+ "loss": 1.5052,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 4.0,
1283
+ "eval_loss": 1.8935941457748413,
1284
+ "eval_runtime": 38.4958,
1285
+ "eval_samples_per_second": 13.378,
1286
+ "eval_steps_per_second": 1.688,
1287
+ "step": 1780
1288
+ },
1289
+ {
1290
+ "epoch": 4.022471910112359,
1291
+ "grad_norm": 0.7063950300216675,
1292
+ "learning_rate": 0.0002,
1293
+ "loss": 1.4047,
1294
+ "step": 1790
1295
+ },
1296
+ {
1297
+ "epoch": 4.044943820224719,
1298
+ "grad_norm": 0.8538862466812134,
1299
+ "learning_rate": 0.0002,
1300
+ "loss": 1.3516,
1301
+ "step": 1800
1302
+ },
1303
+ {
1304
+ "epoch": 4.067415730337078,
1305
+ "grad_norm": 0.6716609597206116,
1306
+ "learning_rate": 0.0002,
1307
+ "loss": 1.3261,
1308
+ "step": 1810
1309
+ },
1310
+ {
1311
+ "epoch": 4.089887640449438,
1312
+ "grad_norm": 0.8187614679336548,
1313
+ "learning_rate": 0.0002,
1314
+ "loss": 1.3477,
1315
+ "step": 1820
1316
+ },
1317
+ {
1318
+ "epoch": 4.112359550561798,
1319
+ "grad_norm": 0.6903043985366821,
1320
+ "learning_rate": 0.0002,
1321
+ "loss": 1.334,
1322
+ "step": 1830
1323
+ },
1324
+ {
1325
+ "epoch": 4.134831460674158,
1326
+ "grad_norm": 0.6804471611976624,
1327
+ "learning_rate": 0.0002,
1328
+ "loss": 1.3283,
1329
+ "step": 1840
1330
+ },
1331
+ {
1332
+ "epoch": 4.157303370786517,
1333
+ "grad_norm": 0.7785346508026123,
1334
+ "learning_rate": 0.0002,
1335
+ "loss": 1.3487,
1336
+ "step": 1850
1337
+ },
1338
+ {
1339
+ "epoch": 4.179775280898877,
1340
+ "grad_norm": 0.7553297281265259,
1341
+ "learning_rate": 0.0002,
1342
+ "loss": 1.3537,
1343
+ "step": 1860
1344
+ },
1345
+ {
1346
+ "epoch": 4.202247191011236,
1347
+ "grad_norm": 0.7317661643028259,
1348
+ "learning_rate": 0.0002,
1349
+ "loss": 1.3752,
1350
+ "step": 1870
1351
+ },
1352
+ {
1353
+ "epoch": 4.224719101123595,
1354
+ "grad_norm": 0.701454758644104,
1355
+ "learning_rate": 0.0002,
1356
+ "loss": 1.3335,
1357
+ "step": 1880
1358
+ },
1359
+ {
1360
+ "epoch": 4.247191011235955,
1361
+ "grad_norm": 0.7360146045684814,
1362
+ "learning_rate": 0.0002,
1363
+ "loss": 1.345,
1364
+ "step": 1890
1365
+ },
1366
+ {
1367
+ "epoch": 4.269662921348314,
1368
+ "grad_norm": 0.7889209389686584,
1369
+ "learning_rate": 0.0002,
1370
+ "loss": 1.3541,
1371
+ "step": 1900
1372
+ },
1373
+ {
1374
+ "epoch": 4.292134831460674,
1375
+ "grad_norm": 0.7613265514373779,
1376
+ "learning_rate": 0.0002,
1377
+ "loss": 1.3658,
1378
+ "step": 1910
1379
+ },
1380
+ {
1381
+ "epoch": 4.314606741573034,
1382
+ "grad_norm": 0.8249233365058899,
1383
+ "learning_rate": 0.0002,
1384
+ "loss": 1.393,
1385
+ "step": 1920
1386
+ },
1387
+ {
1388
+ "epoch": 4.337078651685394,
1389
+ "grad_norm": 0.7492292523384094,
1390
+ "learning_rate": 0.0002,
1391
+ "loss": 1.3723,
1392
+ "step": 1930
1393
+ },
1394
+ {
1395
+ "epoch": 4.359550561797753,
1396
+ "grad_norm": 0.7631386518478394,
1397
+ "learning_rate": 0.0002,
1398
+ "loss": 1.3372,
1399
+ "step": 1940
1400
+ },
1401
+ {
1402
+ "epoch": 4.382022471910112,
1403
+ "grad_norm": 0.7044921517372131,
1404
+ "learning_rate": 0.0002,
1405
+ "loss": 1.3725,
1406
+ "step": 1950
1407
+ },
1408
+ {
1409
+ "epoch": 4.404494382022472,
1410
+ "grad_norm": 0.7950063943862915,
1411
+ "learning_rate": 0.0002,
1412
+ "loss": 1.3077,
1413
+ "step": 1960
1414
+ },
1415
+ {
1416
+ "epoch": 4.426966292134831,
1417
+ "grad_norm": 0.7764235138893127,
1418
+ "learning_rate": 0.0002,
1419
+ "loss": 1.3728,
1420
+ "step": 1970
1421
+ },
1422
+ {
1423
+ "epoch": 4.449438202247191,
1424
+ "grad_norm": 0.77325040102005,
1425
+ "learning_rate": 0.0002,
1426
+ "loss": 1.3991,
1427
+ "step": 1980
1428
+ },
1429
+ {
1430
+ "epoch": 4.47191011235955,
1431
+ "grad_norm": 0.8376508355140686,
1432
+ "learning_rate": 0.0002,
1433
+ "loss": 1.4062,
1434
+ "step": 1990
1435
+ },
1436
+ {
1437
+ "epoch": 4.49438202247191,
1438
+ "grad_norm": 0.7711764574050903,
1439
+ "learning_rate": 0.0002,
1440
+ "loss": 1.3645,
1441
+ "step": 2000
1442
+ },
1443
+ {
1444
+ "epoch": 4.51685393258427,
1445
+ "grad_norm": 0.766307532787323,
1446
+ "learning_rate": 0.0002,
1447
+ "loss": 1.3447,
1448
+ "step": 2010
1449
+ },
1450
+ {
1451
+ "epoch": 4.539325842696629,
1452
+ "grad_norm": 0.7309888005256653,
1453
+ "learning_rate": 0.0002,
1454
+ "loss": 1.3415,
1455
+ "step": 2020
1456
+ },
1457
+ {
1458
+ "epoch": 4.561797752808989,
1459
+ "grad_norm": 0.7707177400588989,
1460
+ "learning_rate": 0.0002,
1461
+ "loss": 1.4652,
1462
+ "step": 2030
1463
+ },
1464
+ {
1465
+ "epoch": 4.584269662921348,
1466
+ "grad_norm": 0.7972665429115295,
1467
+ "learning_rate": 0.0002,
1468
+ "loss": 1.411,
1469
+ "step": 2040
1470
+ },
1471
+ {
1472
+ "epoch": 4.606741573033708,
1473
+ "grad_norm": 0.8435423374176025,
1474
+ "learning_rate": 0.0002,
1475
+ "loss": 1.3848,
1476
+ "step": 2050
1477
+ },
1478
+ {
1479
+ "epoch": 4.629213483146067,
1480
+ "grad_norm": 0.7513273358345032,
1481
+ "learning_rate": 0.0002,
1482
+ "loss": 1.4464,
1483
+ "step": 2060
1484
+ },
1485
+ {
1486
+ "epoch": 4.651685393258427,
1487
+ "grad_norm": 0.8571695685386658,
1488
+ "learning_rate": 0.0002,
1489
+ "loss": 1.3481,
1490
+ "step": 2070
1491
+ },
1492
+ {
1493
+ "epoch": 4.674157303370786,
1494
+ "grad_norm": 0.7924894690513611,
1495
+ "learning_rate": 0.0002,
1496
+ "loss": 1.3812,
1497
+ "step": 2080
1498
+ },
1499
+ {
1500
+ "epoch": 4.696629213483146,
1501
+ "grad_norm": 0.7428702116012573,
1502
+ "learning_rate": 0.0002,
1503
+ "loss": 1.367,
1504
+ "step": 2090
1505
+ },
1506
+ {
1507
+ "epoch": 4.719101123595506,
1508
+ "grad_norm": 0.7480676174163818,
1509
+ "learning_rate": 0.0002,
1510
+ "loss": 1.4409,
1511
+ "step": 2100
1512
+ },
1513
+ {
1514
+ "epoch": 4.741573033707866,
1515
+ "grad_norm": 0.7893720865249634,
1516
+ "learning_rate": 0.0002,
1517
+ "loss": 1.3731,
1518
+ "step": 2110
1519
+ },
1520
+ {
1521
+ "epoch": 4.764044943820225,
1522
+ "grad_norm": 0.8142390251159668,
1523
+ "learning_rate": 0.0002,
1524
+ "loss": 1.392,
1525
+ "step": 2120
1526
+ },
1527
+ {
1528
+ "epoch": 4.786516853932584,
1529
+ "grad_norm": 0.737934410572052,
1530
+ "learning_rate": 0.0002,
1531
+ "loss": 1.3821,
1532
+ "step": 2130
1533
+ },
1534
+ {
1535
+ "epoch": 4.808988764044944,
1536
+ "grad_norm": 0.799316942691803,
1537
+ "learning_rate": 0.0002,
1538
+ "loss": 1.4404,
1539
+ "step": 2140
1540
+ },
1541
+ {
1542
+ "epoch": 4.831460674157303,
1543
+ "grad_norm": 0.8206349015235901,
1544
+ "learning_rate": 0.0002,
1545
+ "loss": 1.4039,
1546
+ "step": 2150
1547
+ },
1548
+ {
1549
+ "epoch": 4.853932584269663,
1550
+ "grad_norm": 0.8419018387794495,
1551
+ "learning_rate": 0.0002,
1552
+ "loss": 1.3908,
1553
+ "step": 2160
1554
+ },
1555
+ {
1556
+ "epoch": 4.876404494382022,
1557
+ "grad_norm": 0.8047335743904114,
1558
+ "learning_rate": 0.0002,
1559
+ "loss": 1.45,
1560
+ "step": 2170
1561
+ },
1562
+ {
1563
+ "epoch": 4.898876404494382,
1564
+ "grad_norm": 0.7250169515609741,
1565
+ "learning_rate": 0.0002,
1566
+ "loss": 1.4097,
1567
+ "step": 2180
1568
+ },
1569
+ {
1570
+ "epoch": 4.921348314606742,
1571
+ "grad_norm": 0.9156671166419983,
1572
+ "learning_rate": 0.0002,
1573
+ "loss": 1.4198,
1574
+ "step": 2190
1575
+ },
1576
+ {
1577
+ "epoch": 4.943820224719101,
1578
+ "grad_norm": 0.747611403465271,
1579
+ "learning_rate": 0.0002,
1580
+ "loss": 1.4354,
1581
+ "step": 2200
1582
+ },
1583
+ {
1584
+ "epoch": 4.966292134831461,
1585
+ "grad_norm": 0.8482937216758728,
1586
+ "learning_rate": 0.0002,
1587
+ "loss": 1.4381,
1588
+ "step": 2210
1589
+ },
1590
+ {
1591
+ "epoch": 4.98876404494382,
1592
+ "grad_norm": 0.8300044536590576,
1593
+ "learning_rate": 0.0002,
1594
+ "loss": 1.4087,
1595
+ "step": 2220
1596
+ },
1597
+ {
1598
+ "epoch": 5.0,
1599
+ "eval_loss": 1.9691932201385498,
1600
+ "eval_runtime": 38.7832,
1601
+ "eval_samples_per_second": 13.279,
1602
+ "eval_steps_per_second": 1.676,
1603
+ "step": 2225
1604
+ },
1605
+ {
1606
+ "epoch": 5.01123595505618,
1607
+ "grad_norm": 0.8864650726318359,
1608
+ "learning_rate": 0.0002,
1609
+ "loss": 1.2992,
1610
+ "step": 2230
1611
+ },
1612
+ {
1613
+ "epoch": 5.033707865168539,
1614
+ "grad_norm": 0.7764638662338257,
1615
+ "learning_rate": 0.0002,
1616
+ "loss": 1.1891,
1617
+ "step": 2240
1618
+ },
1619
+ {
1620
+ "epoch": 5.056179775280899,
1621
+ "grad_norm": 1.0742039680480957,
1622
+ "learning_rate": 0.0002,
1623
+ "loss": 1.2006,
1624
+ "step": 2250
1625
+ },
1626
+ {
1627
+ "epoch": 5.078651685393258,
1628
+ "grad_norm": 0.9639642834663391,
1629
+ "learning_rate": 0.0002,
1630
+ "loss": 1.2426,
1631
+ "step": 2260
1632
+ },
1633
+ {
1634
+ "epoch": 5.101123595505618,
1635
+ "grad_norm": 0.8730543851852417,
1636
+ "learning_rate": 0.0002,
1637
+ "loss": 1.1999,
1638
+ "step": 2270
1639
+ },
1640
+ {
1641
+ "epoch": 5.123595505617978,
1642
+ "grad_norm": 0.9389196634292603,
1643
+ "learning_rate": 0.0002,
1644
+ "loss": 1.1738,
1645
+ "step": 2280
1646
+ },
1647
+ {
1648
+ "epoch": 5.146067415730337,
1649
+ "grad_norm": 0.9505519866943359,
1650
+ "learning_rate": 0.0002,
1651
+ "loss": 1.2169,
1652
+ "step": 2290
1653
+ },
1654
+ {
1655
+ "epoch": 5.168539325842697,
1656
+ "grad_norm": 0.9497833847999573,
1657
+ "learning_rate": 0.0002,
1658
+ "loss": 1.1764,
1659
+ "step": 2300
1660
+ },
1661
+ {
1662
+ "epoch": 5.191011235955056,
1663
+ "grad_norm": 0.9583312273025513,
1664
+ "learning_rate": 0.0002,
1665
+ "loss": 1.3072,
1666
+ "step": 2310
1667
+ },
1668
+ {
1669
+ "epoch": 5.213483146067416,
1670
+ "grad_norm": 1.0934582948684692,
1671
+ "learning_rate": 0.0002,
1672
+ "loss": 1.1941,
1673
+ "step": 2320
1674
+ },
1675
+ {
1676
+ "epoch": 5.235955056179775,
1677
+ "grad_norm": 0.8628548383712769,
1678
+ "learning_rate": 0.0002,
1679
+ "loss": 1.1866,
1680
+ "step": 2330
1681
+ },
1682
+ {
1683
+ "epoch": 5.258426966292135,
1684
+ "grad_norm": 1.0275888442993164,
1685
+ "learning_rate": 0.0002,
1686
+ "loss": 1.1946,
1687
+ "step": 2340
1688
+ },
1689
+ {
1690
+ "epoch": 5.280898876404494,
1691
+ "grad_norm": 0.9802590012550354,
1692
+ "learning_rate": 0.0002,
1693
+ "loss": 1.1904,
1694
+ "step": 2350
1695
+ },
1696
+ {
1697
+ "epoch": 5.303370786516854,
1698
+ "grad_norm": 1.023112416267395,
1699
+ "learning_rate": 0.0002,
1700
+ "loss": 1.2168,
1701
+ "step": 2360
1702
+ },
1703
+ {
1704
+ "epoch": 5.325842696629214,
1705
+ "grad_norm": 1.1056345701217651,
1706
+ "learning_rate": 0.0002,
1707
+ "loss": 1.2589,
1708
+ "step": 2370
1709
+ },
1710
+ {
1711
+ "epoch": 5.348314606741573,
1712
+ "grad_norm": 0.9127669334411621,
1713
+ "learning_rate": 0.0002,
1714
+ "loss": 1.1876,
1715
+ "step": 2380
1716
+ },
1717
+ {
1718
+ "epoch": 5.370786516853933,
1719
+ "grad_norm": 1.08461594581604,
1720
+ "learning_rate": 0.0002,
1721
+ "loss": 1.221,
1722
+ "step": 2390
1723
+ },
1724
+ {
1725
+ "epoch": 5.393258426966292,
1726
+ "grad_norm": 0.9980637431144714,
1727
+ "learning_rate": 0.0002,
1728
+ "loss": 1.1774,
1729
+ "step": 2400
1730
+ },
1731
+ {
1732
+ "epoch": 5.415730337078652,
1733
+ "grad_norm": 0.8567450642585754,
1734
+ "learning_rate": 0.0002,
1735
+ "loss": 1.176,
1736
+ "step": 2410
1737
+ },
1738
+ {
1739
+ "epoch": 5.438202247191011,
1740
+ "grad_norm": 1.2249586582183838,
1741
+ "learning_rate": 0.0002,
1742
+ "loss": 1.2827,
1743
+ "step": 2420
1744
+ },
1745
+ {
1746
+ "epoch": 5.460674157303371,
1747
+ "grad_norm": 1.1892809867858887,
1748
+ "learning_rate": 0.0002,
1749
+ "loss": 1.1992,
1750
+ "step": 2430
1751
+ },
1752
+ {
1753
+ "epoch": 5.48314606741573,
1754
+ "grad_norm": 1.0345431566238403,
1755
+ "learning_rate": 0.0002,
1756
+ "loss": 1.2509,
1757
+ "step": 2440
1758
+ },
1759
+ {
1760
+ "epoch": 5.50561797752809,
1761
+ "grad_norm": 0.9980419874191284,
1762
+ "learning_rate": 0.0002,
1763
+ "loss": 1.1858,
1764
+ "step": 2450
1765
+ },
1766
+ {
1767
+ "epoch": 5.52808988764045,
1768
+ "grad_norm": 1.1752392053604126,
1769
+ "learning_rate": 0.0002,
1770
+ "loss": 1.2588,
1771
+ "step": 2460
1772
+ },
1773
+ {
1774
+ "epoch": 5.550561797752809,
1775
+ "grad_norm": 0.8859575390815735,
1776
+ "learning_rate": 0.0002,
1777
+ "loss": 1.2114,
1778
+ "step": 2470
1779
+ },
1780
+ {
1781
+ "epoch": 5.573033707865169,
1782
+ "grad_norm": 1.420501708984375,
1783
+ "learning_rate": 0.0002,
1784
+ "loss": 1.2752,
1785
+ "step": 2480
1786
+ },
1787
+ {
1788
+ "epoch": 5.595505617977528,
1789
+ "grad_norm": 0.9078432321548462,
1790
+ "learning_rate": 0.0002,
1791
+ "loss": 1.2315,
1792
+ "step": 2490
1793
+ },
1794
+ {
1795
+ "epoch": 5.617977528089888,
1796
+ "grad_norm": 0.9222809076309204,
1797
+ "learning_rate": 0.0002,
1798
+ "loss": 1.3212,
1799
+ "step": 2500
1800
+ },
1801
+ {
1802
+ "epoch": 5.640449438202247,
1803
+ "grad_norm": 1.204506278038025,
1804
+ "learning_rate": 0.0002,
1805
+ "loss": 1.2513,
1806
+ "step": 2510
1807
+ },
1808
+ {
1809
+ "epoch": 5.662921348314606,
1810
+ "grad_norm": 0.9066972732543945,
1811
+ "learning_rate": 0.0002,
1812
+ "loss": 1.2394,
1813
+ "step": 2520
1814
+ },
1815
+ {
1816
+ "epoch": 5.685393258426966,
1817
+ "grad_norm": 1.0702279806137085,
1818
+ "learning_rate": 0.0002,
1819
+ "loss": 1.2401,
1820
+ "step": 2530
1821
+ },
1822
+ {
1823
+ "epoch": 5.707865168539326,
1824
+ "grad_norm": 0.9495944380760193,
1825
+ "learning_rate": 0.0002,
1826
+ "loss": 1.2223,
1827
+ "step": 2540
1828
+ },
1829
+ {
1830
+ "epoch": 5.730337078651686,
1831
+ "grad_norm": 0.9618848562240601,
1832
+ "learning_rate": 0.0002,
1833
+ "loss": 1.2575,
1834
+ "step": 2550
1835
+ },
1836
+ {
1837
+ "epoch": 5.752808988764045,
1838
+ "grad_norm": 1.0767472982406616,
1839
+ "learning_rate": 0.0002,
1840
+ "loss": 1.2507,
1841
+ "step": 2560
1842
+ },
1843
+ {
1844
+ "epoch": 5.775280898876405,
1845
+ "grad_norm": 0.9433596730232239,
1846
+ "learning_rate": 0.0002,
1847
+ "loss": 1.2771,
1848
+ "step": 2570
1849
+ },
1850
+ {
1851
+ "epoch": 5.797752808988764,
1852
+ "grad_norm": 0.8665973544120789,
1853
+ "learning_rate": 0.0002,
1854
+ "loss": 1.2685,
1855
+ "step": 2580
1856
+ },
1857
+ {
1858
+ "epoch": 5.820224719101123,
1859
+ "grad_norm": 1.3818042278289795,
1860
+ "learning_rate": 0.0002,
1861
+ "loss": 1.2273,
1862
+ "step": 2590
1863
+ },
1864
+ {
1865
+ "epoch": 5.842696629213483,
1866
+ "grad_norm": 0.9777767658233643,
1867
+ "learning_rate": 0.0002,
1868
+ "loss": 1.2556,
1869
+ "step": 2600
1870
+ },
1871
+ {
1872
+ "epoch": 5.865168539325842,
1873
+ "grad_norm": 1.0218071937561035,
1874
+ "learning_rate": 0.0002,
1875
+ "loss": 1.2912,
1876
+ "step": 2610
1877
+ },
1878
+ {
1879
+ "epoch": 5.887640449438202,
1880
+ "grad_norm": 1.0352181196212769,
1881
+ "learning_rate": 0.0002,
1882
+ "loss": 1.2863,
1883
+ "step": 2620
1884
+ },
1885
+ {
1886
+ "epoch": 5.910112359550562,
1887
+ "grad_norm": 0.8958706855773926,
1888
+ "learning_rate": 0.0002,
1889
+ "loss": 1.3095,
1890
+ "step": 2630
1891
+ },
1892
+ {
1893
+ "epoch": 5.932584269662922,
1894
+ "grad_norm": 1.3900598287582397,
1895
+ "learning_rate": 0.0002,
1896
+ "loss": 1.2536,
1897
+ "step": 2640
1898
+ },
1899
+ {
1900
+ "epoch": 5.955056179775281,
1901
+ "grad_norm": 0.8726103901863098,
1902
+ "learning_rate": 0.0002,
1903
+ "loss": 1.1607,
1904
+ "step": 2650
1905
+ },
1906
+ {
1907
+ "epoch": 5.97752808988764,
1908
+ "grad_norm": 0.9785570502281189,
1909
+ "learning_rate": 0.0002,
1910
+ "loss": 1.2667,
1911
+ "step": 2660
1912
+ },
1913
+ {
1914
+ "epoch": 6.0,
1915
+ "grad_norm": 0.9082143306732178,
1916
+ "learning_rate": 0.0002,
1917
+ "loss": 1.2528,
1918
+ "step": 2670
1919
+ },
1920
+ {
1921
+ "epoch": 6.0,
1922
+ "eval_loss": 2.0624730587005615,
1923
+ "eval_runtime": 38.84,
1924
+ "eval_samples_per_second": 13.26,
1925
+ "eval_steps_per_second": 1.674,
1926
+ "step": 2670
1927
+ }
1928
+ ],
1929
+ "logging_steps": 10,
1930
+ "max_steps": 3560,
1931
+ "num_input_tokens_seen": 0,
1932
+ "num_train_epochs": 8,
1933
+ "save_steps": 200,
1934
+ "stateful_callbacks": {
1935
+ "TrainerControl": {
1936
+ "args": {
1937
+ "should_epoch_stop": false,
1938
+ "should_evaluate": false,
1939
+ "should_log": false,
1940
+ "should_save": true,
1941
+ "should_training_stop": false
1942
+ },
1943
+ "attributes": {}
1944
+ }
1945
+ },
1946
+ "total_flos": 1.2356162162786304e+17,
1947
+ "train_batch_size": 1,
1948
+ "trial_name": null,
1949
+ "trial_params": null
1950
+ }
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-2670/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70bb087d22fb0995345805c545302523633dddfce545390f986898a00d9c23d9
3
+ size 5560
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-3115/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.3-num-2108-sd-42/checkpoint-3115/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }