MilaWang commited on
Commit
dd82ec9
·
verified ·
1 Parent(s): 9bce8dc

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-0.4-num-2811-sd-0/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-0.4-num-2811-sd-0/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-0.4-num-2811-sd-0/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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/trainer_state.json +882 -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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/trainer_state.json +1310 -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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/trainer_state.json +1738 -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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/trainer_state.json +2166 -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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-3594/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-0.4-num-2811-sd-0/checkpoint-3594/adapter_config.json +29 -0
.gitattributes CHANGED
@@ -1183,3 +1183,12 @@ gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1
1183
  gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-150-sd-10000/checkpoint-48/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1184
  gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-150-sd-10000/checkpoint-6/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1185
  gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-150-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
1183
  gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-150-sd-10000/checkpoint-48/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1184
  gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-150-sd-10000/checkpoint-6/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1185
  gemma-2-9b-it_int4_flare-fiqasa_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.2-num-150-sd-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1186
+ 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-0.4-num-2811-sd-0/checkpoint-1198/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1187
+ 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-0.4-num-2811-sd-0/checkpoint-1797/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1188
+ 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-0.4-num-2811-sd-0/checkpoint-2396/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1189
+ 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-0.4-num-2811-sd-0/checkpoint-2995/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1190
+ 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-0.4-num-2811-sd-0/checkpoint-3594/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1191
+ 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-0.4-num-2811-sd-0/checkpoint-4193/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1192
+ 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-0.4-num-2811-sd-0/checkpoint-4792/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1193
+ 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-0.4-num-2811-sd-0/checkpoint-599/tokenizer.json filter=lfs diff=lfs merge=lfs -text
1194
+ 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-0.4-num-2811-sd-0/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-0.4-num-2811-sd-0/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-0.4-num-2811-sd-0/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-0.4-num-2811-sd-0/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc54ab35d13f4b28ffa8c99f20c0db3d91e7323f68e725af2c8a6e54d45f622
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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc54ab35d13f4b28ffa8c99f20c0db3d91e7323f68e725af2c8a6e54d45f622
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-0.4-num-2811-sd-0/checkpoint-1198/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e872836526651f9f209f12f325c7a7806cfe788a5f0cc0ac2df9e5a02696621
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-0.4-num-2811-sd-0/checkpoint-1198/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea4a8e7e67d80ee514e98886c8f16f52e932c57fa7264878754bbbd833b7a31
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-0.4-num-2811-sd-0/checkpoint-1198/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffc2bf64d8fde4d5db26327467b14671c96072921161522d09bb8570cdf724a3
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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/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-0.4-num-2811-sd-0/checkpoint-1198/trainer_state.json ADDED
@@ -0,0 +1,882 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8182536363601685,
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-0.4-num-2811-sd-0/checkpoint-1198",
4
+ "epoch": 2.0,
5
+ "eval_steps": 10,
6
+ "global_step": 1198,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01669449081803005,
13
+ "grad_norm": 0.4811326861381531,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.6298,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0333889816360601,
20
+ "grad_norm": 0.697903573513031,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.2673,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.05008347245409015,
27
+ "grad_norm": 0.5622886419296265,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.0746,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0667779632721202,
34
+ "grad_norm": 0.4684421122074127,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.9808,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.08347245409015025,
41
+ "grad_norm": 0.4790354371070862,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.9796,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.1001669449081803,
48
+ "grad_norm": 0.5846750140190125,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9269,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.11686143572621036,
55
+ "grad_norm": 0.4034216105937958,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.9773,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1335559265442404,
62
+ "grad_norm": 0.4602500796318054,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.8688,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.15025041736227046,
69
+ "grad_norm": 0.46994853019714355,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.9703,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.1669449081803005,
76
+ "grad_norm": 0.3892269730567932,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8443,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.18363939899833054,
83
+ "grad_norm": 0.40771016478538513,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.9192,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2003338898163606,
90
+ "grad_norm": 0.3820408880710602,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8292,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.21702838063439064,
97
+ "grad_norm": 0.3719843626022339,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.8313,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.2337228714524207,
104
+ "grad_norm": 0.4359976351261139,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.8189,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.25041736227045075,
111
+ "grad_norm": 0.3932259976863861,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.8125,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.2671118530884808,
118
+ "grad_norm": 0.7001785635948181,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.8681,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.2838063439065108,
125
+ "grad_norm": 0.7619664669036865,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.9328,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3005008347245409,
132
+ "grad_norm": 0.3715350329875946,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.7572,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.31719532554257096,
139
+ "grad_norm": 0.5008004903793335,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8551,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.333889816360601,
146
+ "grad_norm": 0.47509506344795227,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.8469,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.35058430717863104,
153
+ "grad_norm": 0.41775935888290405,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.9042,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.3672787979966611,
160
+ "grad_norm": 0.43939948081970215,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.7995,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.38397328881469117,
167
+ "grad_norm": 0.5101977586746216,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.8535,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.4006677796327212,
174
+ "grad_norm": 0.37367475032806396,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.8261,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.41736227045075125,
181
+ "grad_norm": 0.38865089416503906,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.8361,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.4340567612687813,
188
+ "grad_norm": 0.33937838673591614,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.8044,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.4507512520868113,
195
+ "grad_norm": 0.41416028141975403,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8288,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.4674457429048414,
202
+ "grad_norm": 0.4010271430015564,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.8542,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.48414023372287146,
209
+ "grad_norm": 0.3960907459259033,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8803,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.5008347245409015,
216
+ "grad_norm": 0.357433021068573,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.8875,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.5175292153589316,
223
+ "grad_norm": 0.38190674781799316,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.8478,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5342237061769616,
230
+ "grad_norm": 0.3336802124977112,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.8142,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5509181969949917,
237
+ "grad_norm": 0.35935860872268677,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.82,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.5676126878130217,
244
+ "grad_norm": 0.3950583040714264,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.854,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.5843071786310517,
251
+ "grad_norm": 0.31413400173187256,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.8089,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6010016694490818,
258
+ "grad_norm": 0.3342890441417694,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.8417,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6176961602671118,
265
+ "grad_norm": 0.36961331963539124,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.766,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6343906510851419,
272
+ "grad_norm": 0.350652813911438,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.8264,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.6510851419031719,
279
+ "grad_norm": 0.3588177263736725,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.7797,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.667779632721202,
286
+ "grad_norm": 0.3327147960662842,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.6967,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.6844741235392321,
293
+ "grad_norm": 0.3632844388484955,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.754,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.7011686143572621,
300
+ "grad_norm": 0.34581053256988525,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.8264,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.7178631051752922,
307
+ "grad_norm": 0.37237727642059326,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.8706,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.7345575959933222,
314
+ "grad_norm": 0.48366475105285645,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.711,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.7512520868113522,
321
+ "grad_norm": 0.3512793183326721,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.8658,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.7679465776293823,
328
+ "grad_norm": 0.30473145842552185,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.7687,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.7846410684474123,
335
+ "grad_norm": 0.3718157112598419,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.789,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.8013355592654424,
342
+ "grad_norm": 0.34506872296333313,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.8527,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.8180300500834724,
349
+ "grad_norm": 0.36895203590393066,
350
+ "learning_rate": 0.0002,
351
+ "loss": 1.8163,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.8347245409015025,
356
+ "grad_norm": 0.35659778118133545,
357
+ "learning_rate": 0.0002,
358
+ "loss": 1.8499,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.8514190317195326,
363
+ "grad_norm": 0.3631179928779602,
364
+ "learning_rate": 0.0002,
365
+ "loss": 1.8096,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.8681135225375626,
370
+ "grad_norm": 0.3252873420715332,
371
+ "learning_rate": 0.0002,
372
+ "loss": 1.8003,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.8848080133555927,
377
+ "grad_norm": 0.32796111702919006,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.7831,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.9015025041736227,
384
+ "grad_norm": 0.3556145131587982,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.7675,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.9181969949916527,
391
+ "grad_norm": 0.33029764890670776,
392
+ "learning_rate": 0.0002,
393
+ "loss": 1.7902,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.9348914858096828,
398
+ "grad_norm": 0.3531745970249176,
399
+ "learning_rate": 0.0002,
400
+ "loss": 1.7932,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.9515859766277128,
405
+ "grad_norm": 0.3486989140510559,
406
+ "learning_rate": 0.0002,
407
+ "loss": 1.7982,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.9682804674457429,
412
+ "grad_norm": 0.34676939249038696,
413
+ "learning_rate": 0.0002,
414
+ "loss": 1.8522,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.9849749582637729,
419
+ "grad_norm": 0.3389652669429779,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.7805,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 1.0,
426
+ "eval_loss": 1.8236571550369263,
427
+ "eval_runtime": 77.157,
428
+ "eval_samples_per_second": 6.675,
429
+ "eval_steps_per_second": 0.842,
430
+ "step": 599
431
+ },
432
+ {
433
+ "epoch": 1.001669449081803,
434
+ "grad_norm": 0.6550514698028564,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.7724,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.018363939899833,
441
+ "grad_norm": 0.36824166774749756,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.7601,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.0350584307178632,
448
+ "grad_norm": 0.34707099199295044,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.7684,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.0517529215358932,
455
+ "grad_norm": 0.38599663972854614,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.7552,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.0684474123539232,
462
+ "grad_norm": 0.34381693601608276,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.7396,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.0851419031719534,
469
+ "grad_norm": 0.3657481372356415,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.7621,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.1018363939899833,
476
+ "grad_norm": 0.3310803771018982,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.723,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.1185308848080133,
483
+ "grad_norm": 0.37122875452041626,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.7788,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.1352253756260433,
490
+ "grad_norm": 0.3976633548736572,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.6887,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.1519198664440735,
497
+ "grad_norm": 0.37567615509033203,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.7398,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.1686143572621035,
504
+ "grad_norm": 0.3683645725250244,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.7326,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.1853088480801335,
511
+ "grad_norm": 0.3862009644508362,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.8074,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.2020033388981637,
518
+ "grad_norm": 0.3478439450263977,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.7993,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.2186978297161937,
525
+ "grad_norm": 0.3694932162761688,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.7945,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.2353923205342237,
532
+ "grad_norm": 0.3661787211894989,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.7269,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.2520868113522536,
539
+ "grad_norm": 0.372951865196228,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.7561,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.2687813021702838,
546
+ "grad_norm": 0.38718998432159424,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.7507,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.2854757929883138,
553
+ "grad_norm": 0.37488260865211487,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.7331,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.302170283806344,
560
+ "grad_norm": 0.34794917702674866,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.7548,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.318864774624374,
567
+ "grad_norm": 0.3627476990222931,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.7592,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.335559265442404,
574
+ "grad_norm": 0.3773096799850464,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.6837,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.352253756260434,
581
+ "grad_norm": 0.36476725339889526,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7448,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.3689482470784642,
588
+ "grad_norm": 0.3767942190170288,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.7958,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.3856427378964942,
595
+ "grad_norm": 0.3502795398235321,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.7241,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.4023372287145242,
602
+ "grad_norm": 0.4008622169494629,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.736,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.4190317195325544,
609
+ "grad_norm": 0.4029707610607147,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.7211,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.4357262103505843,
616
+ "grad_norm": 0.41480565071105957,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.712,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.4524207011686143,
623
+ "grad_norm": 0.4351646900177002,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.7287,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.4691151919866443,
630
+ "grad_norm": 0.4053232967853546,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.8436,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.4858096828046745,
637
+ "grad_norm": 0.3515186607837677,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.7669,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.5025041736227045,
644
+ "grad_norm": 0.42895469069480896,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.698,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.5191986644407347,
651
+ "grad_norm": 0.40897831320762634,
652
+ "learning_rate": 0.0002,
653
+ "loss": 1.7064,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.5358931552587647,
658
+ "grad_norm": 0.3544739782810211,
659
+ "learning_rate": 0.0002,
660
+ "loss": 1.7539,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.5525876460767947,
665
+ "grad_norm": 0.3848305642604828,
666
+ "learning_rate": 0.0002,
667
+ "loss": 1.7596,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.5692821368948247,
672
+ "grad_norm": 0.36952173709869385,
673
+ "learning_rate": 0.0002,
674
+ "loss": 1.7344,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.5859766277128546,
679
+ "grad_norm": 0.36505743861198425,
680
+ "learning_rate": 0.0002,
681
+ "loss": 1.7329,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.6026711185308848,
686
+ "grad_norm": 0.3707764446735382,
687
+ "learning_rate": 0.0002,
688
+ "loss": 1.6828,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.6193656093489148,
693
+ "grad_norm": 0.35995468497276306,
694
+ "learning_rate": 0.0002,
695
+ "loss": 1.7465,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.636060100166945,
700
+ "grad_norm": 0.35458096861839294,
701
+ "learning_rate": 0.0002,
702
+ "loss": 1.7537,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.652754590984975,
707
+ "grad_norm": 0.3557756841182709,
708
+ "learning_rate": 0.0002,
709
+ "loss": 1.7075,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.669449081803005,
714
+ "grad_norm": 0.355899453163147,
715
+ "learning_rate": 0.0002,
716
+ "loss": 1.7307,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.686143572621035,
721
+ "grad_norm": 0.3709148168563843,
722
+ "learning_rate": 0.0002,
723
+ "loss": 1.7701,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.702838063439065,
728
+ "grad_norm": 0.3731614947319031,
729
+ "learning_rate": 0.0002,
730
+ "loss": 1.7637,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.7195325542570952,
735
+ "grad_norm": 0.3639261722564697,
736
+ "learning_rate": 0.0002,
737
+ "loss": 1.741,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.7362270450751254,
742
+ "grad_norm": 0.36371079087257385,
743
+ "learning_rate": 0.0002,
744
+ "loss": 1.727,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.7529215358931554,
749
+ "grad_norm": 0.38235539197921753,
750
+ "learning_rate": 0.0002,
751
+ "loss": 1.7275,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.7696160267111853,
756
+ "grad_norm": 0.4109364151954651,
757
+ "learning_rate": 0.0002,
758
+ "loss": 1.7304,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.7863105175292153,
763
+ "grad_norm": 0.3499647378921509,
764
+ "learning_rate": 0.0002,
765
+ "loss": 1.7244,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.8030050083472453,
770
+ "grad_norm": 0.3892260193824768,
771
+ "learning_rate": 0.0002,
772
+ "loss": 1.7117,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.8196994991652755,
777
+ "grad_norm": 0.3545094132423401,
778
+ "learning_rate": 0.0002,
779
+ "loss": 1.7764,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.8363939899833055,
784
+ "grad_norm": 0.40419837832450867,
785
+ "learning_rate": 0.0002,
786
+ "loss": 1.87,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.8530884808013357,
791
+ "grad_norm": 0.38423678278923035,
792
+ "learning_rate": 0.0002,
793
+ "loss": 1.6783,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.8697829716193657,
798
+ "grad_norm": 0.378408282995224,
799
+ "learning_rate": 0.0002,
800
+ "loss": 1.7714,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.8864774624373957,
805
+ "grad_norm": 0.4071941077709198,
806
+ "learning_rate": 0.0002,
807
+ "loss": 1.7461,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.9031719532554257,
812
+ "grad_norm": 0.42363739013671875,
813
+ "learning_rate": 0.0002,
814
+ "loss": 1.7281,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.9198664440734556,
819
+ "grad_norm": 0.37373560667037964,
820
+ "learning_rate": 0.0002,
821
+ "loss": 1.819,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.9365609348914858,
826
+ "grad_norm": 0.36408767104148865,
827
+ "learning_rate": 0.0002,
828
+ "loss": 1.7847,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.9532554257095158,
833
+ "grad_norm": 0.3795453906059265,
834
+ "learning_rate": 0.0002,
835
+ "loss": 1.6725,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.969949916527546,
840
+ "grad_norm": 0.34415504336357117,
841
+ "learning_rate": 0.0002,
842
+ "loss": 1.7726,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.986644407345576,
847
+ "grad_norm": 0.3491021394729614,
848
+ "learning_rate": 0.0002,
849
+ "loss": 1.6199,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 2.0,
854
+ "eval_loss": 1.8182536363601685,
855
+ "eval_runtime": 87.8767,
856
+ "eval_samples_per_second": 5.86,
857
+ "eval_steps_per_second": 0.74,
858
+ "step": 1198
859
+ }
860
+ ],
861
+ "logging_steps": 10,
862
+ "max_steps": 4792,
863
+ "num_input_tokens_seen": 0,
864
+ "num_train_epochs": 8,
865
+ "save_steps": 200,
866
+ "stateful_callbacks": {
867
+ "TrainerControl": {
868
+ "args": {
869
+ "should_epoch_stop": false,
870
+ "should_evaluate": false,
871
+ "should_log": false,
872
+ "should_save": true,
873
+ "should_training_stop": false
874
+ },
875
+ "attributes": {}
876
+ }
877
+ },
878
+ "total_flos": 5.544075756935578e+16,
879
+ "train_batch_size": 1,
880
+ "trial_name": null,
881
+ "trial_params": null
882
+ }
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-0.4-num-2811-sd-0/checkpoint-1198/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790482b172d64d1d94b484408c50783310f7b01be29f8cf82f809f2acd1ec121
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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cfafbe2e54dce755785501eea86255490b40ae13766e36fbbb2e98ff1300300
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-0.4-num-2811-sd-0/checkpoint-1797/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9023eb228d5ac172a597a3c52983c2e00ac0c37f24181f227fea577960b69c46
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-0.4-num-2811-sd-0/checkpoint-1797/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea6c6af453659b278bc8dda0303baa95ac327f14e19435dd17c914be5b0461a
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-0.4-num-2811-sd-0/checkpoint-1797/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57b84ab53b8b016556e5c471248db54a7b5fb2ab750167e4f885b03aff346794
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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/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-0.4-num-2811-sd-0/checkpoint-1797/trainer_state.json ADDED
@@ -0,0 +1,1310 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8182536363601685,
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-0.4-num-2811-sd-0/checkpoint-1198",
4
+ "epoch": 3.0,
5
+ "eval_steps": 10,
6
+ "global_step": 1797,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01669449081803005,
13
+ "grad_norm": 0.4811326861381531,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.6298,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0333889816360601,
20
+ "grad_norm": 0.697903573513031,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.2673,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.05008347245409015,
27
+ "grad_norm": 0.5622886419296265,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.0746,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0667779632721202,
34
+ "grad_norm": 0.4684421122074127,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.9808,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.08347245409015025,
41
+ "grad_norm": 0.4790354371070862,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.9796,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.1001669449081803,
48
+ "grad_norm": 0.5846750140190125,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9269,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.11686143572621036,
55
+ "grad_norm": 0.4034216105937958,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.9773,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1335559265442404,
62
+ "grad_norm": 0.4602500796318054,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.8688,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.15025041736227046,
69
+ "grad_norm": 0.46994853019714355,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.9703,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.1669449081803005,
76
+ "grad_norm": 0.3892269730567932,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8443,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.18363939899833054,
83
+ "grad_norm": 0.40771016478538513,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.9192,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2003338898163606,
90
+ "grad_norm": 0.3820408880710602,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8292,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.21702838063439064,
97
+ "grad_norm": 0.3719843626022339,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.8313,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.2337228714524207,
104
+ "grad_norm": 0.4359976351261139,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.8189,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.25041736227045075,
111
+ "grad_norm": 0.3932259976863861,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.8125,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.2671118530884808,
118
+ "grad_norm": 0.7001785635948181,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.8681,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.2838063439065108,
125
+ "grad_norm": 0.7619664669036865,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.9328,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3005008347245409,
132
+ "grad_norm": 0.3715350329875946,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.7572,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.31719532554257096,
139
+ "grad_norm": 0.5008004903793335,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8551,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.333889816360601,
146
+ "grad_norm": 0.47509506344795227,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.8469,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.35058430717863104,
153
+ "grad_norm": 0.41775935888290405,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.9042,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.3672787979966611,
160
+ "grad_norm": 0.43939948081970215,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.7995,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.38397328881469117,
167
+ "grad_norm": 0.5101977586746216,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.8535,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.4006677796327212,
174
+ "grad_norm": 0.37367475032806396,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.8261,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.41736227045075125,
181
+ "grad_norm": 0.38865089416503906,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.8361,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.4340567612687813,
188
+ "grad_norm": 0.33937838673591614,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.8044,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.4507512520868113,
195
+ "grad_norm": 0.41416028141975403,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8288,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.4674457429048414,
202
+ "grad_norm": 0.4010271430015564,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.8542,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.48414023372287146,
209
+ "grad_norm": 0.3960907459259033,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8803,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.5008347245409015,
216
+ "grad_norm": 0.357433021068573,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.8875,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.5175292153589316,
223
+ "grad_norm": 0.38190674781799316,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.8478,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5342237061769616,
230
+ "grad_norm": 0.3336802124977112,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.8142,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5509181969949917,
237
+ "grad_norm": 0.35935860872268677,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.82,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.5676126878130217,
244
+ "grad_norm": 0.3950583040714264,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.854,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.5843071786310517,
251
+ "grad_norm": 0.31413400173187256,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.8089,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6010016694490818,
258
+ "grad_norm": 0.3342890441417694,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.8417,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6176961602671118,
265
+ "grad_norm": 0.36961331963539124,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.766,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6343906510851419,
272
+ "grad_norm": 0.350652813911438,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.8264,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.6510851419031719,
279
+ "grad_norm": 0.3588177263736725,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.7797,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.667779632721202,
286
+ "grad_norm": 0.3327147960662842,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.6967,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.6844741235392321,
293
+ "grad_norm": 0.3632844388484955,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.754,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.7011686143572621,
300
+ "grad_norm": 0.34581053256988525,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.8264,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.7178631051752922,
307
+ "grad_norm": 0.37237727642059326,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.8706,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.7345575959933222,
314
+ "grad_norm": 0.48366475105285645,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.711,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.7512520868113522,
321
+ "grad_norm": 0.3512793183326721,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.8658,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.7679465776293823,
328
+ "grad_norm": 0.30473145842552185,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.7687,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.7846410684474123,
335
+ "grad_norm": 0.3718157112598419,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.789,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.8013355592654424,
342
+ "grad_norm": 0.34506872296333313,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.8527,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.8180300500834724,
349
+ "grad_norm": 0.36895203590393066,
350
+ "learning_rate": 0.0002,
351
+ "loss": 1.8163,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.8347245409015025,
356
+ "grad_norm": 0.35659778118133545,
357
+ "learning_rate": 0.0002,
358
+ "loss": 1.8499,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.8514190317195326,
363
+ "grad_norm": 0.3631179928779602,
364
+ "learning_rate": 0.0002,
365
+ "loss": 1.8096,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.8681135225375626,
370
+ "grad_norm": 0.3252873420715332,
371
+ "learning_rate": 0.0002,
372
+ "loss": 1.8003,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.8848080133555927,
377
+ "grad_norm": 0.32796111702919006,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.7831,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.9015025041736227,
384
+ "grad_norm": 0.3556145131587982,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.7675,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.9181969949916527,
391
+ "grad_norm": 0.33029764890670776,
392
+ "learning_rate": 0.0002,
393
+ "loss": 1.7902,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.9348914858096828,
398
+ "grad_norm": 0.3531745970249176,
399
+ "learning_rate": 0.0002,
400
+ "loss": 1.7932,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.9515859766277128,
405
+ "grad_norm": 0.3486989140510559,
406
+ "learning_rate": 0.0002,
407
+ "loss": 1.7982,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.9682804674457429,
412
+ "grad_norm": 0.34676939249038696,
413
+ "learning_rate": 0.0002,
414
+ "loss": 1.8522,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.9849749582637729,
419
+ "grad_norm": 0.3389652669429779,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.7805,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 1.0,
426
+ "eval_loss": 1.8236571550369263,
427
+ "eval_runtime": 77.157,
428
+ "eval_samples_per_second": 6.675,
429
+ "eval_steps_per_second": 0.842,
430
+ "step": 599
431
+ },
432
+ {
433
+ "epoch": 1.001669449081803,
434
+ "grad_norm": 0.6550514698028564,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.7724,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.018363939899833,
441
+ "grad_norm": 0.36824166774749756,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.7601,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.0350584307178632,
448
+ "grad_norm": 0.34707099199295044,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.7684,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.0517529215358932,
455
+ "grad_norm": 0.38599663972854614,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.7552,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.0684474123539232,
462
+ "grad_norm": 0.34381693601608276,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.7396,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.0851419031719534,
469
+ "grad_norm": 0.3657481372356415,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.7621,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.1018363939899833,
476
+ "grad_norm": 0.3310803771018982,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.723,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.1185308848080133,
483
+ "grad_norm": 0.37122875452041626,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.7788,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.1352253756260433,
490
+ "grad_norm": 0.3976633548736572,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.6887,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.1519198664440735,
497
+ "grad_norm": 0.37567615509033203,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.7398,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.1686143572621035,
504
+ "grad_norm": 0.3683645725250244,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.7326,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.1853088480801335,
511
+ "grad_norm": 0.3862009644508362,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.8074,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.2020033388981637,
518
+ "grad_norm": 0.3478439450263977,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.7993,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.2186978297161937,
525
+ "grad_norm": 0.3694932162761688,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.7945,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.2353923205342237,
532
+ "grad_norm": 0.3661787211894989,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.7269,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.2520868113522536,
539
+ "grad_norm": 0.372951865196228,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.7561,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.2687813021702838,
546
+ "grad_norm": 0.38718998432159424,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.7507,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.2854757929883138,
553
+ "grad_norm": 0.37488260865211487,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.7331,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.302170283806344,
560
+ "grad_norm": 0.34794917702674866,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.7548,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.318864774624374,
567
+ "grad_norm": 0.3627476990222931,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.7592,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.335559265442404,
574
+ "grad_norm": 0.3773096799850464,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.6837,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.352253756260434,
581
+ "grad_norm": 0.36476725339889526,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7448,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.3689482470784642,
588
+ "grad_norm": 0.3767942190170288,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.7958,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.3856427378964942,
595
+ "grad_norm": 0.3502795398235321,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.7241,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.4023372287145242,
602
+ "grad_norm": 0.4008622169494629,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.736,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.4190317195325544,
609
+ "grad_norm": 0.4029707610607147,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.7211,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.4357262103505843,
616
+ "grad_norm": 0.41480565071105957,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.712,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.4524207011686143,
623
+ "grad_norm": 0.4351646900177002,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.7287,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.4691151919866443,
630
+ "grad_norm": 0.4053232967853546,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.8436,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.4858096828046745,
637
+ "grad_norm": 0.3515186607837677,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.7669,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.5025041736227045,
644
+ "grad_norm": 0.42895469069480896,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.698,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.5191986644407347,
651
+ "grad_norm": 0.40897831320762634,
652
+ "learning_rate": 0.0002,
653
+ "loss": 1.7064,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.5358931552587647,
658
+ "grad_norm": 0.3544739782810211,
659
+ "learning_rate": 0.0002,
660
+ "loss": 1.7539,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.5525876460767947,
665
+ "grad_norm": 0.3848305642604828,
666
+ "learning_rate": 0.0002,
667
+ "loss": 1.7596,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.5692821368948247,
672
+ "grad_norm": 0.36952173709869385,
673
+ "learning_rate": 0.0002,
674
+ "loss": 1.7344,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.5859766277128546,
679
+ "grad_norm": 0.36505743861198425,
680
+ "learning_rate": 0.0002,
681
+ "loss": 1.7329,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.6026711185308848,
686
+ "grad_norm": 0.3707764446735382,
687
+ "learning_rate": 0.0002,
688
+ "loss": 1.6828,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.6193656093489148,
693
+ "grad_norm": 0.35995468497276306,
694
+ "learning_rate": 0.0002,
695
+ "loss": 1.7465,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.636060100166945,
700
+ "grad_norm": 0.35458096861839294,
701
+ "learning_rate": 0.0002,
702
+ "loss": 1.7537,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.652754590984975,
707
+ "grad_norm": 0.3557756841182709,
708
+ "learning_rate": 0.0002,
709
+ "loss": 1.7075,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.669449081803005,
714
+ "grad_norm": 0.355899453163147,
715
+ "learning_rate": 0.0002,
716
+ "loss": 1.7307,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.686143572621035,
721
+ "grad_norm": 0.3709148168563843,
722
+ "learning_rate": 0.0002,
723
+ "loss": 1.7701,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.702838063439065,
728
+ "grad_norm": 0.3731614947319031,
729
+ "learning_rate": 0.0002,
730
+ "loss": 1.7637,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.7195325542570952,
735
+ "grad_norm": 0.3639261722564697,
736
+ "learning_rate": 0.0002,
737
+ "loss": 1.741,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.7362270450751254,
742
+ "grad_norm": 0.36371079087257385,
743
+ "learning_rate": 0.0002,
744
+ "loss": 1.727,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.7529215358931554,
749
+ "grad_norm": 0.38235539197921753,
750
+ "learning_rate": 0.0002,
751
+ "loss": 1.7275,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.7696160267111853,
756
+ "grad_norm": 0.4109364151954651,
757
+ "learning_rate": 0.0002,
758
+ "loss": 1.7304,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.7863105175292153,
763
+ "grad_norm": 0.3499647378921509,
764
+ "learning_rate": 0.0002,
765
+ "loss": 1.7244,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.8030050083472453,
770
+ "grad_norm": 0.3892260193824768,
771
+ "learning_rate": 0.0002,
772
+ "loss": 1.7117,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.8196994991652755,
777
+ "grad_norm": 0.3545094132423401,
778
+ "learning_rate": 0.0002,
779
+ "loss": 1.7764,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.8363939899833055,
784
+ "grad_norm": 0.40419837832450867,
785
+ "learning_rate": 0.0002,
786
+ "loss": 1.87,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.8530884808013357,
791
+ "grad_norm": 0.38423678278923035,
792
+ "learning_rate": 0.0002,
793
+ "loss": 1.6783,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.8697829716193657,
798
+ "grad_norm": 0.378408282995224,
799
+ "learning_rate": 0.0002,
800
+ "loss": 1.7714,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.8864774624373957,
805
+ "grad_norm": 0.4071941077709198,
806
+ "learning_rate": 0.0002,
807
+ "loss": 1.7461,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.9031719532554257,
812
+ "grad_norm": 0.42363739013671875,
813
+ "learning_rate": 0.0002,
814
+ "loss": 1.7281,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.9198664440734556,
819
+ "grad_norm": 0.37373560667037964,
820
+ "learning_rate": 0.0002,
821
+ "loss": 1.819,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.9365609348914858,
826
+ "grad_norm": 0.36408767104148865,
827
+ "learning_rate": 0.0002,
828
+ "loss": 1.7847,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.9532554257095158,
833
+ "grad_norm": 0.3795453906059265,
834
+ "learning_rate": 0.0002,
835
+ "loss": 1.6725,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.969949916527546,
840
+ "grad_norm": 0.34415504336357117,
841
+ "learning_rate": 0.0002,
842
+ "loss": 1.7726,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.986644407345576,
847
+ "grad_norm": 0.3491021394729614,
848
+ "learning_rate": 0.0002,
849
+ "loss": 1.6199,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 2.0,
854
+ "eval_loss": 1.8182536363601685,
855
+ "eval_runtime": 87.8767,
856
+ "eval_samples_per_second": 5.86,
857
+ "eval_steps_per_second": 0.74,
858
+ "step": 1198
859
+ },
860
+ {
861
+ "epoch": 2.003338898163606,
862
+ "grad_norm": 0.36758512258529663,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.5857,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.020033388981636,
869
+ "grad_norm": 0.36278557777404785,
870
+ "learning_rate": 0.0002,
871
+ "loss": 1.61,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.036727879799666,
876
+ "grad_norm": 0.4186977744102478,
877
+ "learning_rate": 0.0002,
878
+ "loss": 1.6733,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.053422370617696,
883
+ "grad_norm": 0.3958706855773926,
884
+ "learning_rate": 0.0002,
885
+ "loss": 1.6977,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.0701168614357264,
890
+ "grad_norm": 0.43305638432502747,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.7054,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.0868113522537564,
897
+ "grad_norm": 0.4509678781032562,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.6275,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.1035058430717863,
904
+ "grad_norm": 0.4297264516353607,
905
+ "learning_rate": 0.0002,
906
+ "loss": 1.6814,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.1202003338898163,
911
+ "grad_norm": 0.4579504132270813,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.6121,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.1368948247078463,
918
+ "grad_norm": 0.4223267138004303,
919
+ "learning_rate": 0.0002,
920
+ "loss": 1.6207,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.1535893155258763,
925
+ "grad_norm": 0.41538703441619873,
926
+ "learning_rate": 0.0002,
927
+ "loss": 1.6472,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.1702838063439067,
932
+ "grad_norm": 0.4987374544143677,
933
+ "learning_rate": 0.0002,
934
+ "loss": 1.6274,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.1869782971619367,
939
+ "grad_norm": 0.45300114154815674,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.6555,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.2036727879799667,
946
+ "grad_norm": 0.4577588737010956,
947
+ "learning_rate": 0.0002,
948
+ "loss": 1.6486,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.2203672787979967,
953
+ "grad_norm": 0.4110747277736664,
954
+ "learning_rate": 0.0002,
955
+ "loss": 1.644,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.2370617696160267,
960
+ "grad_norm": 0.5107163190841675,
961
+ "learning_rate": 0.0002,
962
+ "loss": 1.5875,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.2537562604340566,
967
+ "grad_norm": 0.41190820932388306,
968
+ "learning_rate": 0.0002,
969
+ "loss": 1.691,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.2704507512520866,
974
+ "grad_norm": 0.47458386421203613,
975
+ "learning_rate": 0.0002,
976
+ "loss": 1.5745,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.287145242070117,
981
+ "grad_norm": 0.42136940360069275,
982
+ "learning_rate": 0.0002,
983
+ "loss": 1.6964,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.303839732888147,
988
+ "grad_norm": 0.48292383551597595,
989
+ "learning_rate": 0.0002,
990
+ "loss": 1.657,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.320534223706177,
995
+ "grad_norm": 0.4519229531288147,
996
+ "learning_rate": 0.0002,
997
+ "loss": 1.6816,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.337228714524207,
1002
+ "grad_norm": 0.5860922336578369,
1003
+ "learning_rate": 0.0002,
1004
+ "loss": 1.6408,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.353923205342237,
1009
+ "grad_norm": 0.4362313747406006,
1010
+ "learning_rate": 0.0002,
1011
+ "loss": 1.5551,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.370617696160267,
1016
+ "grad_norm": 0.46916621923446655,
1017
+ "learning_rate": 0.0002,
1018
+ "loss": 1.6763,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.3873121869782974,
1023
+ "grad_norm": 0.5249663591384888,
1024
+ "learning_rate": 0.0002,
1025
+ "loss": 1.6082,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.4040066777963274,
1030
+ "grad_norm": 0.4764375388622284,
1031
+ "learning_rate": 0.0002,
1032
+ "loss": 1.6793,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.4207011686143574,
1037
+ "grad_norm": 0.46573784947395325,
1038
+ "learning_rate": 0.0002,
1039
+ "loss": 1.6395,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.4373956594323873,
1044
+ "grad_norm": 0.44539371132850647,
1045
+ "learning_rate": 0.0002,
1046
+ "loss": 1.6629,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.4540901502504173,
1051
+ "grad_norm": 0.40925896167755127,
1052
+ "learning_rate": 0.0002,
1053
+ "loss": 1.6149,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.4707846410684473,
1058
+ "grad_norm": 0.4431462287902832,
1059
+ "learning_rate": 0.0002,
1060
+ "loss": 1.6213,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.4874791318864773,
1065
+ "grad_norm": 0.5476022362709045,
1066
+ "learning_rate": 0.0002,
1067
+ "loss": 1.692,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 2.5041736227045073,
1072
+ "grad_norm": 0.44762539863586426,
1073
+ "learning_rate": 0.0002,
1074
+ "loss": 1.5875,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 2.5208681135225377,
1079
+ "grad_norm": 0.5470041632652283,
1080
+ "learning_rate": 0.0002,
1081
+ "loss": 1.6811,
1082
+ "step": 1510
1083
+ },
1084
+ {
1085
+ "epoch": 2.5375626043405677,
1086
+ "grad_norm": 0.4739997088909149,
1087
+ "learning_rate": 0.0002,
1088
+ "loss": 1.7411,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.5542570951585977,
1093
+ "grad_norm": 0.47115322947502136,
1094
+ "learning_rate": 0.0002,
1095
+ "loss": 1.5975,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.5709515859766277,
1100
+ "grad_norm": 0.49705708026885986,
1101
+ "learning_rate": 0.0002,
1102
+ "loss": 1.6828,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.5876460767946576,
1107
+ "grad_norm": 0.5537301301956177,
1108
+ "learning_rate": 0.0002,
1109
+ "loss": 1.7135,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.604340567612688,
1114
+ "grad_norm": 0.46930626034736633,
1115
+ "learning_rate": 0.0002,
1116
+ "loss": 1.5753,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.621035058430718,
1121
+ "grad_norm": 0.42371469736099243,
1122
+ "learning_rate": 0.0002,
1123
+ "loss": 1.6706,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.637729549248748,
1128
+ "grad_norm": 0.49005603790283203,
1129
+ "learning_rate": 0.0002,
1130
+ "loss": 1.6193,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.654424040066778,
1135
+ "grad_norm": 0.4646829068660736,
1136
+ "learning_rate": 0.0002,
1137
+ "loss": 1.7138,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.671118530884808,
1142
+ "grad_norm": 0.5091238617897034,
1143
+ "learning_rate": 0.0002,
1144
+ "loss": 1.6806,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.687813021702838,
1149
+ "grad_norm": 0.4889985918998718,
1150
+ "learning_rate": 0.0002,
1151
+ "loss": 1.65,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.704507512520868,
1156
+ "grad_norm": 0.5128234624862671,
1157
+ "learning_rate": 0.0002,
1158
+ "loss": 1.6573,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.721202003338898,
1163
+ "grad_norm": 0.46999186277389526,
1164
+ "learning_rate": 0.0002,
1165
+ "loss": 1.6739,
1166
+ "step": 1630
1167
+ },
1168
+ {
1169
+ "epoch": 2.7378964941569284,
1170
+ "grad_norm": 0.4949921667575836,
1171
+ "learning_rate": 0.0002,
1172
+ "loss": 1.6277,
1173
+ "step": 1640
1174
+ },
1175
+ {
1176
+ "epoch": 2.7545909849749584,
1177
+ "grad_norm": 0.4484370946884155,
1178
+ "learning_rate": 0.0002,
1179
+ "loss": 1.5958,
1180
+ "step": 1650
1181
+ },
1182
+ {
1183
+ "epoch": 2.7712854757929883,
1184
+ "grad_norm": 0.45599570870399475,
1185
+ "learning_rate": 0.0002,
1186
+ "loss": 1.6156,
1187
+ "step": 1660
1188
+ },
1189
+ {
1190
+ "epoch": 2.7879799666110183,
1191
+ "grad_norm": 0.5093285441398621,
1192
+ "learning_rate": 0.0002,
1193
+ "loss": 1.6037,
1194
+ "step": 1670
1195
+ },
1196
+ {
1197
+ "epoch": 2.8046744574290483,
1198
+ "grad_norm": 0.44737935066223145,
1199
+ "learning_rate": 0.0002,
1200
+ "loss": 1.6675,
1201
+ "step": 1680
1202
+ },
1203
+ {
1204
+ "epoch": 2.8213689482470787,
1205
+ "grad_norm": 0.4374251365661621,
1206
+ "learning_rate": 0.0002,
1207
+ "loss": 1.6429,
1208
+ "step": 1690
1209
+ },
1210
+ {
1211
+ "epoch": 2.8380634390651087,
1212
+ "grad_norm": 0.44765740633010864,
1213
+ "learning_rate": 0.0002,
1214
+ "loss": 1.5941,
1215
+ "step": 1700
1216
+ },
1217
+ {
1218
+ "epoch": 2.8547579298831387,
1219
+ "grad_norm": 0.44685253500938416,
1220
+ "learning_rate": 0.0002,
1221
+ "loss": 1.6841,
1222
+ "step": 1710
1223
+ },
1224
+ {
1225
+ "epoch": 2.8714524207011687,
1226
+ "grad_norm": 0.44777143001556396,
1227
+ "learning_rate": 0.0002,
1228
+ "loss": 1.6301,
1229
+ "step": 1720
1230
+ },
1231
+ {
1232
+ "epoch": 2.8881469115191987,
1233
+ "grad_norm": 0.4178132712841034,
1234
+ "learning_rate": 0.0002,
1235
+ "loss": 1.6473,
1236
+ "step": 1730
1237
+ },
1238
+ {
1239
+ "epoch": 2.9048414023372287,
1240
+ "grad_norm": 0.4487852156162262,
1241
+ "learning_rate": 0.0002,
1242
+ "loss": 1.6491,
1243
+ "step": 1740
1244
+ },
1245
+ {
1246
+ "epoch": 2.9215358931552586,
1247
+ "grad_norm": 0.47137337923049927,
1248
+ "learning_rate": 0.0002,
1249
+ "loss": 1.6616,
1250
+ "step": 1750
1251
+ },
1252
+ {
1253
+ "epoch": 2.9382303839732886,
1254
+ "grad_norm": 0.48543235659599304,
1255
+ "learning_rate": 0.0002,
1256
+ "loss": 1.6767,
1257
+ "step": 1760
1258
+ },
1259
+ {
1260
+ "epoch": 2.9549248747913186,
1261
+ "grad_norm": 0.4174182116985321,
1262
+ "learning_rate": 0.0002,
1263
+ "loss": 1.7055,
1264
+ "step": 1770
1265
+ },
1266
+ {
1267
+ "epoch": 2.971619365609349,
1268
+ "grad_norm": 0.43385711312294006,
1269
+ "learning_rate": 0.0002,
1270
+ "loss": 1.5767,
1271
+ "step": 1780
1272
+ },
1273
+ {
1274
+ "epoch": 2.988313856427379,
1275
+ "grad_norm": 0.474332332611084,
1276
+ "learning_rate": 0.0002,
1277
+ "loss": 1.6215,
1278
+ "step": 1790
1279
+ },
1280
+ {
1281
+ "epoch": 3.0,
1282
+ "eval_loss": 1.8456445932388306,
1283
+ "eval_runtime": 87.6261,
1284
+ "eval_samples_per_second": 5.877,
1285
+ "eval_steps_per_second": 0.742,
1286
+ "step": 1797
1287
+ }
1288
+ ],
1289
+ "logging_steps": 10,
1290
+ "max_steps": 4792,
1291
+ "num_input_tokens_seen": 0,
1292
+ "num_train_epochs": 8,
1293
+ "save_steps": 200,
1294
+ "stateful_callbacks": {
1295
+ "TrainerControl": {
1296
+ "args": {
1297
+ "should_epoch_stop": false,
1298
+ "should_evaluate": false,
1299
+ "should_log": false,
1300
+ "should_save": true,
1301
+ "should_training_stop": false
1302
+ },
1303
+ "attributes": {}
1304
+ }
1305
+ },
1306
+ "total_flos": 8.316113635403366e+16,
1307
+ "train_batch_size": 1,
1308
+ "trial_name": null,
1309
+ "trial_params": null
1310
+ }
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-0.4-num-2811-sd-0/checkpoint-1797/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790482b172d64d1d94b484408c50783310f7b01be29f8cf82f809f2acd1ec121
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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f7cc9fca2733a1aa9e8a24d12bfafeb33816e532d46f26d6a124e48cee37073
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-0.4-num-2811-sd-0/checkpoint-2396/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e025bff57ae0383efa78511d542bdfad18c92611e898a75604fc1f02a0870d
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-0.4-num-2811-sd-0/checkpoint-2396/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2caf9686e72f2d99753b3f12a0c4895855368b371595b7dd4d0d3e0672998126
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-0.4-num-2811-sd-0/checkpoint-2396/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98fe9c6c555dae3a3bdf3813f204237057dfa5e96c9d907e021dcc9d788270e
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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/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-0.4-num-2811-sd-0/checkpoint-2396/trainer_state.json ADDED
@@ -0,0 +1,1738 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8182536363601685,
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-0.4-num-2811-sd-0/checkpoint-1198",
4
+ "epoch": 4.0,
5
+ "eval_steps": 10,
6
+ "global_step": 2396,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01669449081803005,
13
+ "grad_norm": 0.4811326861381531,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.6298,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0333889816360601,
20
+ "grad_norm": 0.697903573513031,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.2673,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.05008347245409015,
27
+ "grad_norm": 0.5622886419296265,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.0746,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0667779632721202,
34
+ "grad_norm": 0.4684421122074127,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.9808,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.08347245409015025,
41
+ "grad_norm": 0.4790354371070862,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.9796,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.1001669449081803,
48
+ "grad_norm": 0.5846750140190125,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9269,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.11686143572621036,
55
+ "grad_norm": 0.4034216105937958,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.9773,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1335559265442404,
62
+ "grad_norm": 0.4602500796318054,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.8688,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.15025041736227046,
69
+ "grad_norm": 0.46994853019714355,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.9703,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.1669449081803005,
76
+ "grad_norm": 0.3892269730567932,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8443,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.18363939899833054,
83
+ "grad_norm": 0.40771016478538513,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.9192,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2003338898163606,
90
+ "grad_norm": 0.3820408880710602,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8292,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.21702838063439064,
97
+ "grad_norm": 0.3719843626022339,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.8313,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.2337228714524207,
104
+ "grad_norm": 0.4359976351261139,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.8189,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.25041736227045075,
111
+ "grad_norm": 0.3932259976863861,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.8125,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.2671118530884808,
118
+ "grad_norm": 0.7001785635948181,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.8681,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.2838063439065108,
125
+ "grad_norm": 0.7619664669036865,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.9328,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3005008347245409,
132
+ "grad_norm": 0.3715350329875946,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.7572,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.31719532554257096,
139
+ "grad_norm": 0.5008004903793335,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8551,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.333889816360601,
146
+ "grad_norm": 0.47509506344795227,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.8469,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.35058430717863104,
153
+ "grad_norm": 0.41775935888290405,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.9042,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.3672787979966611,
160
+ "grad_norm": 0.43939948081970215,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.7995,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.38397328881469117,
167
+ "grad_norm": 0.5101977586746216,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.8535,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.4006677796327212,
174
+ "grad_norm": 0.37367475032806396,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.8261,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.41736227045075125,
181
+ "grad_norm": 0.38865089416503906,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.8361,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.4340567612687813,
188
+ "grad_norm": 0.33937838673591614,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.8044,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.4507512520868113,
195
+ "grad_norm": 0.41416028141975403,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8288,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.4674457429048414,
202
+ "grad_norm": 0.4010271430015564,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.8542,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.48414023372287146,
209
+ "grad_norm": 0.3960907459259033,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8803,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.5008347245409015,
216
+ "grad_norm": 0.357433021068573,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.8875,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.5175292153589316,
223
+ "grad_norm": 0.38190674781799316,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.8478,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5342237061769616,
230
+ "grad_norm": 0.3336802124977112,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.8142,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5509181969949917,
237
+ "grad_norm": 0.35935860872268677,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.82,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.5676126878130217,
244
+ "grad_norm": 0.3950583040714264,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.854,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.5843071786310517,
251
+ "grad_norm": 0.31413400173187256,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.8089,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6010016694490818,
258
+ "grad_norm": 0.3342890441417694,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.8417,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6176961602671118,
265
+ "grad_norm": 0.36961331963539124,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.766,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6343906510851419,
272
+ "grad_norm": 0.350652813911438,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.8264,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.6510851419031719,
279
+ "grad_norm": 0.3588177263736725,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.7797,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.667779632721202,
286
+ "grad_norm": 0.3327147960662842,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.6967,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.6844741235392321,
293
+ "grad_norm": 0.3632844388484955,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.754,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.7011686143572621,
300
+ "grad_norm": 0.34581053256988525,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.8264,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.7178631051752922,
307
+ "grad_norm": 0.37237727642059326,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.8706,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.7345575959933222,
314
+ "grad_norm": 0.48366475105285645,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.711,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.7512520868113522,
321
+ "grad_norm": 0.3512793183326721,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.8658,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.7679465776293823,
328
+ "grad_norm": 0.30473145842552185,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.7687,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.7846410684474123,
335
+ "grad_norm": 0.3718157112598419,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.789,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.8013355592654424,
342
+ "grad_norm": 0.34506872296333313,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.8527,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.8180300500834724,
349
+ "grad_norm": 0.36895203590393066,
350
+ "learning_rate": 0.0002,
351
+ "loss": 1.8163,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.8347245409015025,
356
+ "grad_norm": 0.35659778118133545,
357
+ "learning_rate": 0.0002,
358
+ "loss": 1.8499,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.8514190317195326,
363
+ "grad_norm": 0.3631179928779602,
364
+ "learning_rate": 0.0002,
365
+ "loss": 1.8096,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.8681135225375626,
370
+ "grad_norm": 0.3252873420715332,
371
+ "learning_rate": 0.0002,
372
+ "loss": 1.8003,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.8848080133555927,
377
+ "grad_norm": 0.32796111702919006,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.7831,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.9015025041736227,
384
+ "grad_norm": 0.3556145131587982,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.7675,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.9181969949916527,
391
+ "grad_norm": 0.33029764890670776,
392
+ "learning_rate": 0.0002,
393
+ "loss": 1.7902,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.9348914858096828,
398
+ "grad_norm": 0.3531745970249176,
399
+ "learning_rate": 0.0002,
400
+ "loss": 1.7932,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.9515859766277128,
405
+ "grad_norm": 0.3486989140510559,
406
+ "learning_rate": 0.0002,
407
+ "loss": 1.7982,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.9682804674457429,
412
+ "grad_norm": 0.34676939249038696,
413
+ "learning_rate": 0.0002,
414
+ "loss": 1.8522,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.9849749582637729,
419
+ "grad_norm": 0.3389652669429779,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.7805,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 1.0,
426
+ "eval_loss": 1.8236571550369263,
427
+ "eval_runtime": 77.157,
428
+ "eval_samples_per_second": 6.675,
429
+ "eval_steps_per_second": 0.842,
430
+ "step": 599
431
+ },
432
+ {
433
+ "epoch": 1.001669449081803,
434
+ "grad_norm": 0.6550514698028564,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.7724,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.018363939899833,
441
+ "grad_norm": 0.36824166774749756,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.7601,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.0350584307178632,
448
+ "grad_norm": 0.34707099199295044,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.7684,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.0517529215358932,
455
+ "grad_norm": 0.38599663972854614,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.7552,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.0684474123539232,
462
+ "grad_norm": 0.34381693601608276,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.7396,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.0851419031719534,
469
+ "grad_norm": 0.3657481372356415,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.7621,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.1018363939899833,
476
+ "grad_norm": 0.3310803771018982,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.723,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.1185308848080133,
483
+ "grad_norm": 0.37122875452041626,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.7788,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.1352253756260433,
490
+ "grad_norm": 0.3976633548736572,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.6887,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.1519198664440735,
497
+ "grad_norm": 0.37567615509033203,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.7398,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.1686143572621035,
504
+ "grad_norm": 0.3683645725250244,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.7326,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.1853088480801335,
511
+ "grad_norm": 0.3862009644508362,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.8074,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.2020033388981637,
518
+ "grad_norm": 0.3478439450263977,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.7993,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.2186978297161937,
525
+ "grad_norm": 0.3694932162761688,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.7945,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.2353923205342237,
532
+ "grad_norm": 0.3661787211894989,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.7269,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.2520868113522536,
539
+ "grad_norm": 0.372951865196228,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.7561,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.2687813021702838,
546
+ "grad_norm": 0.38718998432159424,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.7507,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.2854757929883138,
553
+ "grad_norm": 0.37488260865211487,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.7331,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.302170283806344,
560
+ "grad_norm": 0.34794917702674866,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.7548,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.318864774624374,
567
+ "grad_norm": 0.3627476990222931,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.7592,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.335559265442404,
574
+ "grad_norm": 0.3773096799850464,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.6837,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.352253756260434,
581
+ "grad_norm": 0.36476725339889526,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7448,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.3689482470784642,
588
+ "grad_norm": 0.3767942190170288,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.7958,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.3856427378964942,
595
+ "grad_norm": 0.3502795398235321,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.7241,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.4023372287145242,
602
+ "grad_norm": 0.4008622169494629,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.736,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.4190317195325544,
609
+ "grad_norm": 0.4029707610607147,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.7211,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.4357262103505843,
616
+ "grad_norm": 0.41480565071105957,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.712,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.4524207011686143,
623
+ "grad_norm": 0.4351646900177002,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.7287,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.4691151919866443,
630
+ "grad_norm": 0.4053232967853546,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.8436,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.4858096828046745,
637
+ "grad_norm": 0.3515186607837677,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.7669,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.5025041736227045,
644
+ "grad_norm": 0.42895469069480896,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.698,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.5191986644407347,
651
+ "grad_norm": 0.40897831320762634,
652
+ "learning_rate": 0.0002,
653
+ "loss": 1.7064,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.5358931552587647,
658
+ "grad_norm": 0.3544739782810211,
659
+ "learning_rate": 0.0002,
660
+ "loss": 1.7539,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.5525876460767947,
665
+ "grad_norm": 0.3848305642604828,
666
+ "learning_rate": 0.0002,
667
+ "loss": 1.7596,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.5692821368948247,
672
+ "grad_norm": 0.36952173709869385,
673
+ "learning_rate": 0.0002,
674
+ "loss": 1.7344,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.5859766277128546,
679
+ "grad_norm": 0.36505743861198425,
680
+ "learning_rate": 0.0002,
681
+ "loss": 1.7329,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.6026711185308848,
686
+ "grad_norm": 0.3707764446735382,
687
+ "learning_rate": 0.0002,
688
+ "loss": 1.6828,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.6193656093489148,
693
+ "grad_norm": 0.35995468497276306,
694
+ "learning_rate": 0.0002,
695
+ "loss": 1.7465,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.636060100166945,
700
+ "grad_norm": 0.35458096861839294,
701
+ "learning_rate": 0.0002,
702
+ "loss": 1.7537,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.652754590984975,
707
+ "grad_norm": 0.3557756841182709,
708
+ "learning_rate": 0.0002,
709
+ "loss": 1.7075,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.669449081803005,
714
+ "grad_norm": 0.355899453163147,
715
+ "learning_rate": 0.0002,
716
+ "loss": 1.7307,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.686143572621035,
721
+ "grad_norm": 0.3709148168563843,
722
+ "learning_rate": 0.0002,
723
+ "loss": 1.7701,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.702838063439065,
728
+ "grad_norm": 0.3731614947319031,
729
+ "learning_rate": 0.0002,
730
+ "loss": 1.7637,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.7195325542570952,
735
+ "grad_norm": 0.3639261722564697,
736
+ "learning_rate": 0.0002,
737
+ "loss": 1.741,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.7362270450751254,
742
+ "grad_norm": 0.36371079087257385,
743
+ "learning_rate": 0.0002,
744
+ "loss": 1.727,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.7529215358931554,
749
+ "grad_norm": 0.38235539197921753,
750
+ "learning_rate": 0.0002,
751
+ "loss": 1.7275,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.7696160267111853,
756
+ "grad_norm": 0.4109364151954651,
757
+ "learning_rate": 0.0002,
758
+ "loss": 1.7304,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.7863105175292153,
763
+ "grad_norm": 0.3499647378921509,
764
+ "learning_rate": 0.0002,
765
+ "loss": 1.7244,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.8030050083472453,
770
+ "grad_norm": 0.3892260193824768,
771
+ "learning_rate": 0.0002,
772
+ "loss": 1.7117,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.8196994991652755,
777
+ "grad_norm": 0.3545094132423401,
778
+ "learning_rate": 0.0002,
779
+ "loss": 1.7764,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.8363939899833055,
784
+ "grad_norm": 0.40419837832450867,
785
+ "learning_rate": 0.0002,
786
+ "loss": 1.87,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.8530884808013357,
791
+ "grad_norm": 0.38423678278923035,
792
+ "learning_rate": 0.0002,
793
+ "loss": 1.6783,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.8697829716193657,
798
+ "grad_norm": 0.378408282995224,
799
+ "learning_rate": 0.0002,
800
+ "loss": 1.7714,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.8864774624373957,
805
+ "grad_norm": 0.4071941077709198,
806
+ "learning_rate": 0.0002,
807
+ "loss": 1.7461,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.9031719532554257,
812
+ "grad_norm": 0.42363739013671875,
813
+ "learning_rate": 0.0002,
814
+ "loss": 1.7281,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.9198664440734556,
819
+ "grad_norm": 0.37373560667037964,
820
+ "learning_rate": 0.0002,
821
+ "loss": 1.819,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.9365609348914858,
826
+ "grad_norm": 0.36408767104148865,
827
+ "learning_rate": 0.0002,
828
+ "loss": 1.7847,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.9532554257095158,
833
+ "grad_norm": 0.3795453906059265,
834
+ "learning_rate": 0.0002,
835
+ "loss": 1.6725,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.969949916527546,
840
+ "grad_norm": 0.34415504336357117,
841
+ "learning_rate": 0.0002,
842
+ "loss": 1.7726,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.986644407345576,
847
+ "grad_norm": 0.3491021394729614,
848
+ "learning_rate": 0.0002,
849
+ "loss": 1.6199,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 2.0,
854
+ "eval_loss": 1.8182536363601685,
855
+ "eval_runtime": 87.8767,
856
+ "eval_samples_per_second": 5.86,
857
+ "eval_steps_per_second": 0.74,
858
+ "step": 1198
859
+ },
860
+ {
861
+ "epoch": 2.003338898163606,
862
+ "grad_norm": 0.36758512258529663,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.5857,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.020033388981636,
869
+ "grad_norm": 0.36278557777404785,
870
+ "learning_rate": 0.0002,
871
+ "loss": 1.61,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.036727879799666,
876
+ "grad_norm": 0.4186977744102478,
877
+ "learning_rate": 0.0002,
878
+ "loss": 1.6733,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.053422370617696,
883
+ "grad_norm": 0.3958706855773926,
884
+ "learning_rate": 0.0002,
885
+ "loss": 1.6977,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.0701168614357264,
890
+ "grad_norm": 0.43305638432502747,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.7054,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.0868113522537564,
897
+ "grad_norm": 0.4509678781032562,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.6275,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.1035058430717863,
904
+ "grad_norm": 0.4297264516353607,
905
+ "learning_rate": 0.0002,
906
+ "loss": 1.6814,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.1202003338898163,
911
+ "grad_norm": 0.4579504132270813,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.6121,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.1368948247078463,
918
+ "grad_norm": 0.4223267138004303,
919
+ "learning_rate": 0.0002,
920
+ "loss": 1.6207,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.1535893155258763,
925
+ "grad_norm": 0.41538703441619873,
926
+ "learning_rate": 0.0002,
927
+ "loss": 1.6472,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.1702838063439067,
932
+ "grad_norm": 0.4987374544143677,
933
+ "learning_rate": 0.0002,
934
+ "loss": 1.6274,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.1869782971619367,
939
+ "grad_norm": 0.45300114154815674,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.6555,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.2036727879799667,
946
+ "grad_norm": 0.4577588737010956,
947
+ "learning_rate": 0.0002,
948
+ "loss": 1.6486,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.2203672787979967,
953
+ "grad_norm": 0.4110747277736664,
954
+ "learning_rate": 0.0002,
955
+ "loss": 1.644,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.2370617696160267,
960
+ "grad_norm": 0.5107163190841675,
961
+ "learning_rate": 0.0002,
962
+ "loss": 1.5875,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.2537562604340566,
967
+ "grad_norm": 0.41190820932388306,
968
+ "learning_rate": 0.0002,
969
+ "loss": 1.691,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.2704507512520866,
974
+ "grad_norm": 0.47458386421203613,
975
+ "learning_rate": 0.0002,
976
+ "loss": 1.5745,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.287145242070117,
981
+ "grad_norm": 0.42136940360069275,
982
+ "learning_rate": 0.0002,
983
+ "loss": 1.6964,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.303839732888147,
988
+ "grad_norm": 0.48292383551597595,
989
+ "learning_rate": 0.0002,
990
+ "loss": 1.657,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.320534223706177,
995
+ "grad_norm": 0.4519229531288147,
996
+ "learning_rate": 0.0002,
997
+ "loss": 1.6816,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.337228714524207,
1002
+ "grad_norm": 0.5860922336578369,
1003
+ "learning_rate": 0.0002,
1004
+ "loss": 1.6408,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.353923205342237,
1009
+ "grad_norm": 0.4362313747406006,
1010
+ "learning_rate": 0.0002,
1011
+ "loss": 1.5551,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.370617696160267,
1016
+ "grad_norm": 0.46916621923446655,
1017
+ "learning_rate": 0.0002,
1018
+ "loss": 1.6763,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.3873121869782974,
1023
+ "grad_norm": 0.5249663591384888,
1024
+ "learning_rate": 0.0002,
1025
+ "loss": 1.6082,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.4040066777963274,
1030
+ "grad_norm": 0.4764375388622284,
1031
+ "learning_rate": 0.0002,
1032
+ "loss": 1.6793,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.4207011686143574,
1037
+ "grad_norm": 0.46573784947395325,
1038
+ "learning_rate": 0.0002,
1039
+ "loss": 1.6395,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.4373956594323873,
1044
+ "grad_norm": 0.44539371132850647,
1045
+ "learning_rate": 0.0002,
1046
+ "loss": 1.6629,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.4540901502504173,
1051
+ "grad_norm": 0.40925896167755127,
1052
+ "learning_rate": 0.0002,
1053
+ "loss": 1.6149,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.4707846410684473,
1058
+ "grad_norm": 0.4431462287902832,
1059
+ "learning_rate": 0.0002,
1060
+ "loss": 1.6213,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.4874791318864773,
1065
+ "grad_norm": 0.5476022362709045,
1066
+ "learning_rate": 0.0002,
1067
+ "loss": 1.692,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 2.5041736227045073,
1072
+ "grad_norm": 0.44762539863586426,
1073
+ "learning_rate": 0.0002,
1074
+ "loss": 1.5875,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 2.5208681135225377,
1079
+ "grad_norm": 0.5470041632652283,
1080
+ "learning_rate": 0.0002,
1081
+ "loss": 1.6811,
1082
+ "step": 1510
1083
+ },
1084
+ {
1085
+ "epoch": 2.5375626043405677,
1086
+ "grad_norm": 0.4739997088909149,
1087
+ "learning_rate": 0.0002,
1088
+ "loss": 1.7411,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.5542570951585977,
1093
+ "grad_norm": 0.47115322947502136,
1094
+ "learning_rate": 0.0002,
1095
+ "loss": 1.5975,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.5709515859766277,
1100
+ "grad_norm": 0.49705708026885986,
1101
+ "learning_rate": 0.0002,
1102
+ "loss": 1.6828,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.5876460767946576,
1107
+ "grad_norm": 0.5537301301956177,
1108
+ "learning_rate": 0.0002,
1109
+ "loss": 1.7135,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.604340567612688,
1114
+ "grad_norm": 0.46930626034736633,
1115
+ "learning_rate": 0.0002,
1116
+ "loss": 1.5753,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.621035058430718,
1121
+ "grad_norm": 0.42371469736099243,
1122
+ "learning_rate": 0.0002,
1123
+ "loss": 1.6706,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.637729549248748,
1128
+ "grad_norm": 0.49005603790283203,
1129
+ "learning_rate": 0.0002,
1130
+ "loss": 1.6193,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.654424040066778,
1135
+ "grad_norm": 0.4646829068660736,
1136
+ "learning_rate": 0.0002,
1137
+ "loss": 1.7138,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.671118530884808,
1142
+ "grad_norm": 0.5091238617897034,
1143
+ "learning_rate": 0.0002,
1144
+ "loss": 1.6806,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.687813021702838,
1149
+ "grad_norm": 0.4889985918998718,
1150
+ "learning_rate": 0.0002,
1151
+ "loss": 1.65,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.704507512520868,
1156
+ "grad_norm": 0.5128234624862671,
1157
+ "learning_rate": 0.0002,
1158
+ "loss": 1.6573,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.721202003338898,
1163
+ "grad_norm": 0.46999186277389526,
1164
+ "learning_rate": 0.0002,
1165
+ "loss": 1.6739,
1166
+ "step": 1630
1167
+ },
1168
+ {
1169
+ "epoch": 2.7378964941569284,
1170
+ "grad_norm": 0.4949921667575836,
1171
+ "learning_rate": 0.0002,
1172
+ "loss": 1.6277,
1173
+ "step": 1640
1174
+ },
1175
+ {
1176
+ "epoch": 2.7545909849749584,
1177
+ "grad_norm": 0.4484370946884155,
1178
+ "learning_rate": 0.0002,
1179
+ "loss": 1.5958,
1180
+ "step": 1650
1181
+ },
1182
+ {
1183
+ "epoch": 2.7712854757929883,
1184
+ "grad_norm": 0.45599570870399475,
1185
+ "learning_rate": 0.0002,
1186
+ "loss": 1.6156,
1187
+ "step": 1660
1188
+ },
1189
+ {
1190
+ "epoch": 2.7879799666110183,
1191
+ "grad_norm": 0.5093285441398621,
1192
+ "learning_rate": 0.0002,
1193
+ "loss": 1.6037,
1194
+ "step": 1670
1195
+ },
1196
+ {
1197
+ "epoch": 2.8046744574290483,
1198
+ "grad_norm": 0.44737935066223145,
1199
+ "learning_rate": 0.0002,
1200
+ "loss": 1.6675,
1201
+ "step": 1680
1202
+ },
1203
+ {
1204
+ "epoch": 2.8213689482470787,
1205
+ "grad_norm": 0.4374251365661621,
1206
+ "learning_rate": 0.0002,
1207
+ "loss": 1.6429,
1208
+ "step": 1690
1209
+ },
1210
+ {
1211
+ "epoch": 2.8380634390651087,
1212
+ "grad_norm": 0.44765740633010864,
1213
+ "learning_rate": 0.0002,
1214
+ "loss": 1.5941,
1215
+ "step": 1700
1216
+ },
1217
+ {
1218
+ "epoch": 2.8547579298831387,
1219
+ "grad_norm": 0.44685253500938416,
1220
+ "learning_rate": 0.0002,
1221
+ "loss": 1.6841,
1222
+ "step": 1710
1223
+ },
1224
+ {
1225
+ "epoch": 2.8714524207011687,
1226
+ "grad_norm": 0.44777143001556396,
1227
+ "learning_rate": 0.0002,
1228
+ "loss": 1.6301,
1229
+ "step": 1720
1230
+ },
1231
+ {
1232
+ "epoch": 2.8881469115191987,
1233
+ "grad_norm": 0.4178132712841034,
1234
+ "learning_rate": 0.0002,
1235
+ "loss": 1.6473,
1236
+ "step": 1730
1237
+ },
1238
+ {
1239
+ "epoch": 2.9048414023372287,
1240
+ "grad_norm": 0.4487852156162262,
1241
+ "learning_rate": 0.0002,
1242
+ "loss": 1.6491,
1243
+ "step": 1740
1244
+ },
1245
+ {
1246
+ "epoch": 2.9215358931552586,
1247
+ "grad_norm": 0.47137337923049927,
1248
+ "learning_rate": 0.0002,
1249
+ "loss": 1.6616,
1250
+ "step": 1750
1251
+ },
1252
+ {
1253
+ "epoch": 2.9382303839732886,
1254
+ "grad_norm": 0.48543235659599304,
1255
+ "learning_rate": 0.0002,
1256
+ "loss": 1.6767,
1257
+ "step": 1760
1258
+ },
1259
+ {
1260
+ "epoch": 2.9549248747913186,
1261
+ "grad_norm": 0.4174182116985321,
1262
+ "learning_rate": 0.0002,
1263
+ "loss": 1.7055,
1264
+ "step": 1770
1265
+ },
1266
+ {
1267
+ "epoch": 2.971619365609349,
1268
+ "grad_norm": 0.43385711312294006,
1269
+ "learning_rate": 0.0002,
1270
+ "loss": 1.5767,
1271
+ "step": 1780
1272
+ },
1273
+ {
1274
+ "epoch": 2.988313856427379,
1275
+ "grad_norm": 0.474332332611084,
1276
+ "learning_rate": 0.0002,
1277
+ "loss": 1.6215,
1278
+ "step": 1790
1279
+ },
1280
+ {
1281
+ "epoch": 3.0,
1282
+ "eval_loss": 1.8456445932388306,
1283
+ "eval_runtime": 87.6261,
1284
+ "eval_samples_per_second": 5.877,
1285
+ "eval_steps_per_second": 0.742,
1286
+ "step": 1797
1287
+ },
1288
+ {
1289
+ "epoch": 3.005008347245409,
1290
+ "grad_norm": 0.40323764085769653,
1291
+ "learning_rate": 0.0002,
1292
+ "loss": 1.6224,
1293
+ "step": 1800
1294
+ },
1295
+ {
1296
+ "epoch": 3.021702838063439,
1297
+ "grad_norm": 0.45069044828414917,
1298
+ "learning_rate": 0.0002,
1299
+ "loss": 1.5367,
1300
+ "step": 1810
1301
+ },
1302
+ {
1303
+ "epoch": 3.038397328881469,
1304
+ "grad_norm": 0.6204925775527954,
1305
+ "learning_rate": 0.0002,
1306
+ "loss": 1.5271,
1307
+ "step": 1820
1308
+ },
1309
+ {
1310
+ "epoch": 3.0550918196994994,
1311
+ "grad_norm": 0.5857783555984497,
1312
+ "learning_rate": 0.0002,
1313
+ "loss": 1.5056,
1314
+ "step": 1830
1315
+ },
1316
+ {
1317
+ "epoch": 3.0717863105175294,
1318
+ "grad_norm": 0.6776524782180786,
1319
+ "learning_rate": 0.0002,
1320
+ "loss": 1.5137,
1321
+ "step": 1840
1322
+ },
1323
+ {
1324
+ "epoch": 3.0884808013355594,
1325
+ "grad_norm": 0.5486199855804443,
1326
+ "learning_rate": 0.0002,
1327
+ "loss": 1.5106,
1328
+ "step": 1850
1329
+ },
1330
+ {
1331
+ "epoch": 3.1051752921535893,
1332
+ "grad_norm": 0.5496503710746765,
1333
+ "learning_rate": 0.0002,
1334
+ "loss": 1.414,
1335
+ "step": 1860
1336
+ },
1337
+ {
1338
+ "epoch": 3.1218697829716193,
1339
+ "grad_norm": 0.5602648258209229,
1340
+ "learning_rate": 0.0002,
1341
+ "loss": 1.5181,
1342
+ "step": 1870
1343
+ },
1344
+ {
1345
+ "epoch": 3.1385642737896493,
1346
+ "grad_norm": 1.0697380304336548,
1347
+ "learning_rate": 0.0002,
1348
+ "loss": 1.5406,
1349
+ "step": 1880
1350
+ },
1351
+ {
1352
+ "epoch": 3.1552587646076793,
1353
+ "grad_norm": 0.6087332367897034,
1354
+ "learning_rate": 0.0002,
1355
+ "loss": 1.4889,
1356
+ "step": 1890
1357
+ },
1358
+ {
1359
+ "epoch": 3.1719532554257097,
1360
+ "grad_norm": 0.5112161040306091,
1361
+ "learning_rate": 0.0002,
1362
+ "loss": 1.5219,
1363
+ "step": 1900
1364
+ },
1365
+ {
1366
+ "epoch": 3.1886477462437397,
1367
+ "grad_norm": 0.6393680572509766,
1368
+ "learning_rate": 0.0002,
1369
+ "loss": 1.5139,
1370
+ "step": 1910
1371
+ },
1372
+ {
1373
+ "epoch": 3.2053422370617697,
1374
+ "grad_norm": 0.7201815247535706,
1375
+ "learning_rate": 0.0002,
1376
+ "loss": 1.5337,
1377
+ "step": 1920
1378
+ },
1379
+ {
1380
+ "epoch": 3.2220367278797997,
1381
+ "grad_norm": 0.5856018662452698,
1382
+ "learning_rate": 0.0002,
1383
+ "loss": 1.6055,
1384
+ "step": 1930
1385
+ },
1386
+ {
1387
+ "epoch": 3.2387312186978297,
1388
+ "grad_norm": 0.581247866153717,
1389
+ "learning_rate": 0.0002,
1390
+ "loss": 1.4791,
1391
+ "step": 1940
1392
+ },
1393
+ {
1394
+ "epoch": 3.2554257095158596,
1395
+ "grad_norm": 0.6055102944374084,
1396
+ "learning_rate": 0.0002,
1397
+ "loss": 1.5395,
1398
+ "step": 1950
1399
+ },
1400
+ {
1401
+ "epoch": 3.27212020033389,
1402
+ "grad_norm": 0.546894371509552,
1403
+ "learning_rate": 0.0002,
1404
+ "loss": 1.5086,
1405
+ "step": 1960
1406
+ },
1407
+ {
1408
+ "epoch": 3.28881469115192,
1409
+ "grad_norm": 0.565558910369873,
1410
+ "learning_rate": 0.0002,
1411
+ "loss": 1.5712,
1412
+ "step": 1970
1413
+ },
1414
+ {
1415
+ "epoch": 3.30550918196995,
1416
+ "grad_norm": 1.2238883972167969,
1417
+ "learning_rate": 0.0002,
1418
+ "loss": 1.47,
1419
+ "step": 1980
1420
+ },
1421
+ {
1422
+ "epoch": 3.32220367278798,
1423
+ "grad_norm": 0.6362585425376892,
1424
+ "learning_rate": 0.0002,
1425
+ "loss": 1.4655,
1426
+ "step": 1990
1427
+ },
1428
+ {
1429
+ "epoch": 3.33889816360601,
1430
+ "grad_norm": 0.6131124496459961,
1431
+ "learning_rate": 0.0002,
1432
+ "loss": 1.5157,
1433
+ "step": 2000
1434
+ },
1435
+ {
1436
+ "epoch": 3.35559265442404,
1437
+ "grad_norm": 0.5181341767311096,
1438
+ "learning_rate": 0.0002,
1439
+ "loss": 1.5322,
1440
+ "step": 2010
1441
+ },
1442
+ {
1443
+ "epoch": 3.37228714524207,
1444
+ "grad_norm": 0.6667609810829163,
1445
+ "learning_rate": 0.0002,
1446
+ "loss": 1.5039,
1447
+ "step": 2020
1448
+ },
1449
+ {
1450
+ "epoch": 3.3889816360601,
1451
+ "grad_norm": 0.6488749980926514,
1452
+ "learning_rate": 0.0002,
1453
+ "loss": 1.5814,
1454
+ "step": 2030
1455
+ },
1456
+ {
1457
+ "epoch": 3.4056761268781304,
1458
+ "grad_norm": 0.5693286061286926,
1459
+ "learning_rate": 0.0002,
1460
+ "loss": 1.5226,
1461
+ "step": 2040
1462
+ },
1463
+ {
1464
+ "epoch": 3.4223706176961604,
1465
+ "grad_norm": 0.6154143810272217,
1466
+ "learning_rate": 0.0002,
1467
+ "loss": 1.5121,
1468
+ "step": 2050
1469
+ },
1470
+ {
1471
+ "epoch": 3.4390651085141903,
1472
+ "grad_norm": 0.6747981309890747,
1473
+ "learning_rate": 0.0002,
1474
+ "loss": 1.6033,
1475
+ "step": 2060
1476
+ },
1477
+ {
1478
+ "epoch": 3.4557595993322203,
1479
+ "grad_norm": 0.5494789481163025,
1480
+ "learning_rate": 0.0002,
1481
+ "loss": 1.5857,
1482
+ "step": 2070
1483
+ },
1484
+ {
1485
+ "epoch": 3.4724540901502503,
1486
+ "grad_norm": 2.481968402862549,
1487
+ "learning_rate": 0.0002,
1488
+ "loss": 1.5223,
1489
+ "step": 2080
1490
+ },
1491
+ {
1492
+ "epoch": 3.4891485809682803,
1493
+ "grad_norm": 0.589784562587738,
1494
+ "learning_rate": 0.0002,
1495
+ "loss": 1.4989,
1496
+ "step": 2090
1497
+ },
1498
+ {
1499
+ "epoch": 3.5058430717863107,
1500
+ "grad_norm": 0.6449820399284363,
1501
+ "learning_rate": 0.0002,
1502
+ "loss": 1.6227,
1503
+ "step": 2100
1504
+ },
1505
+ {
1506
+ "epoch": 3.5225375626043407,
1507
+ "grad_norm": 0.6467038989067078,
1508
+ "learning_rate": 0.0002,
1509
+ "loss": 1.588,
1510
+ "step": 2110
1511
+ },
1512
+ {
1513
+ "epoch": 3.5392320534223707,
1514
+ "grad_norm": 0.6533533334732056,
1515
+ "learning_rate": 0.0002,
1516
+ "loss": 1.5655,
1517
+ "step": 2120
1518
+ },
1519
+ {
1520
+ "epoch": 3.5559265442404007,
1521
+ "grad_norm": 0.6804035902023315,
1522
+ "learning_rate": 0.0002,
1523
+ "loss": 1.6052,
1524
+ "step": 2130
1525
+ },
1526
+ {
1527
+ "epoch": 3.5726210350584306,
1528
+ "grad_norm": 0.628773033618927,
1529
+ "learning_rate": 0.0002,
1530
+ "loss": 1.5408,
1531
+ "step": 2140
1532
+ },
1533
+ {
1534
+ "epoch": 3.5893155258764606,
1535
+ "grad_norm": 0.6055739521980286,
1536
+ "learning_rate": 0.0002,
1537
+ "loss": 1.5487,
1538
+ "step": 2150
1539
+ },
1540
+ {
1541
+ "epoch": 3.6060100166944906,
1542
+ "grad_norm": 0.6000894904136658,
1543
+ "learning_rate": 0.0002,
1544
+ "loss": 1.5305,
1545
+ "step": 2160
1546
+ },
1547
+ {
1548
+ "epoch": 3.6227045075125206,
1549
+ "grad_norm": 0.5862473249435425,
1550
+ "learning_rate": 0.0002,
1551
+ "loss": 1.4742,
1552
+ "step": 2170
1553
+ },
1554
+ {
1555
+ "epoch": 3.639398998330551,
1556
+ "grad_norm": 0.6547419428825378,
1557
+ "learning_rate": 0.0002,
1558
+ "loss": 1.503,
1559
+ "step": 2180
1560
+ },
1561
+ {
1562
+ "epoch": 3.656093489148581,
1563
+ "grad_norm": 0.5610318779945374,
1564
+ "learning_rate": 0.0002,
1565
+ "loss": 1.4704,
1566
+ "step": 2190
1567
+ },
1568
+ {
1569
+ "epoch": 3.672787979966611,
1570
+ "grad_norm": 0.6387564539909363,
1571
+ "learning_rate": 0.0002,
1572
+ "loss": 1.4814,
1573
+ "step": 2200
1574
+ },
1575
+ {
1576
+ "epoch": 3.689482470784641,
1577
+ "grad_norm": 0.6065090894699097,
1578
+ "learning_rate": 0.0002,
1579
+ "loss": 1.5356,
1580
+ "step": 2210
1581
+ },
1582
+ {
1583
+ "epoch": 3.706176961602671,
1584
+ "grad_norm": 0.6266646981239319,
1585
+ "learning_rate": 0.0002,
1586
+ "loss": 1.5074,
1587
+ "step": 2220
1588
+ },
1589
+ {
1590
+ "epoch": 3.7228714524207014,
1591
+ "grad_norm": 0.626944363117218,
1592
+ "learning_rate": 0.0002,
1593
+ "loss": 1.5146,
1594
+ "step": 2230
1595
+ },
1596
+ {
1597
+ "epoch": 3.7395659432387314,
1598
+ "grad_norm": 0.6043975949287415,
1599
+ "learning_rate": 0.0002,
1600
+ "loss": 1.5131,
1601
+ "step": 2240
1602
+ },
1603
+ {
1604
+ "epoch": 3.7562604340567614,
1605
+ "grad_norm": 0.599732518196106,
1606
+ "learning_rate": 0.0002,
1607
+ "loss": 1.5929,
1608
+ "step": 2250
1609
+ },
1610
+ {
1611
+ "epoch": 3.7729549248747913,
1612
+ "grad_norm": 0.6738389134407043,
1613
+ "learning_rate": 0.0002,
1614
+ "loss": 1.5236,
1615
+ "step": 2260
1616
+ },
1617
+ {
1618
+ "epoch": 3.7896494156928213,
1619
+ "grad_norm": 0.5561335682868958,
1620
+ "learning_rate": 0.0002,
1621
+ "loss": 1.5003,
1622
+ "step": 2270
1623
+ },
1624
+ {
1625
+ "epoch": 3.8063439065108513,
1626
+ "grad_norm": 0.6185726523399353,
1627
+ "learning_rate": 0.0002,
1628
+ "loss": 1.5013,
1629
+ "step": 2280
1630
+ },
1631
+ {
1632
+ "epoch": 3.8230383973288813,
1633
+ "grad_norm": 0.6151532530784607,
1634
+ "learning_rate": 0.0002,
1635
+ "loss": 1.4996,
1636
+ "step": 2290
1637
+ },
1638
+ {
1639
+ "epoch": 3.8397328881469113,
1640
+ "grad_norm": 0.5808233022689819,
1641
+ "learning_rate": 0.0002,
1642
+ "loss": 1.5453,
1643
+ "step": 2300
1644
+ },
1645
+ {
1646
+ "epoch": 3.8564273789649417,
1647
+ "grad_norm": 0.6615163683891296,
1648
+ "learning_rate": 0.0002,
1649
+ "loss": 1.5223,
1650
+ "step": 2310
1651
+ },
1652
+ {
1653
+ "epoch": 3.8731218697829717,
1654
+ "grad_norm": 0.5832979679107666,
1655
+ "learning_rate": 0.0002,
1656
+ "loss": 1.4365,
1657
+ "step": 2320
1658
+ },
1659
+ {
1660
+ "epoch": 3.8898163606010017,
1661
+ "grad_norm": 0.6119300127029419,
1662
+ "learning_rate": 0.0002,
1663
+ "loss": 1.6036,
1664
+ "step": 2330
1665
+ },
1666
+ {
1667
+ "epoch": 3.9065108514190316,
1668
+ "grad_norm": 0.6489697694778442,
1669
+ "learning_rate": 0.0002,
1670
+ "loss": 1.5581,
1671
+ "step": 2340
1672
+ },
1673
+ {
1674
+ "epoch": 3.9232053422370616,
1675
+ "grad_norm": 0.5539063215255737,
1676
+ "learning_rate": 0.0002,
1677
+ "loss": 1.5601,
1678
+ "step": 2350
1679
+ },
1680
+ {
1681
+ "epoch": 3.939899833055092,
1682
+ "grad_norm": 0.6062877178192139,
1683
+ "learning_rate": 0.0002,
1684
+ "loss": 1.5174,
1685
+ "step": 2360
1686
+ },
1687
+ {
1688
+ "epoch": 3.956594323873122,
1689
+ "grad_norm": 0.680609941482544,
1690
+ "learning_rate": 0.0002,
1691
+ "loss": 1.5168,
1692
+ "step": 2370
1693
+ },
1694
+ {
1695
+ "epoch": 3.973288814691152,
1696
+ "grad_norm": 0.6176834106445312,
1697
+ "learning_rate": 0.0002,
1698
+ "loss": 1.4875,
1699
+ "step": 2380
1700
+ },
1701
+ {
1702
+ "epoch": 3.989983305509182,
1703
+ "grad_norm": 0.6538102030754089,
1704
+ "learning_rate": 0.0002,
1705
+ "loss": 1.4984,
1706
+ "step": 2390
1707
+ },
1708
+ {
1709
+ "epoch": 4.0,
1710
+ "eval_loss": 1.8920671939849854,
1711
+ "eval_runtime": 76.5227,
1712
+ "eval_samples_per_second": 6.73,
1713
+ "eval_steps_per_second": 0.849,
1714
+ "step": 2396
1715
+ }
1716
+ ],
1717
+ "logging_steps": 10,
1718
+ "max_steps": 4792,
1719
+ "num_input_tokens_seen": 0,
1720
+ "num_train_epochs": 8,
1721
+ "save_steps": 200,
1722
+ "stateful_callbacks": {
1723
+ "TrainerControl": {
1724
+ "args": {
1725
+ "should_epoch_stop": false,
1726
+ "should_evaluate": false,
1727
+ "should_log": false,
1728
+ "should_save": true,
1729
+ "should_training_stop": false
1730
+ },
1731
+ "attributes": {}
1732
+ }
1733
+ },
1734
+ "total_flos": 1.1088151513871155e+17,
1735
+ "train_batch_size": 1,
1736
+ "trial_name": null,
1737
+ "trial_params": null
1738
+ }
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-0.4-num-2811-sd-0/checkpoint-2396/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790482b172d64d1d94b484408c50783310f7b01be29f8cf82f809f2acd1ec121
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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d8a094f89ef511bd01eac5f5a44a62ee185fa345dabc566691af268a3ac990
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-0.4-num-2811-sd-0/checkpoint-2995/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6ec7bfa01f491d5e1b42a017607bc7cf2c7f4db35ebca1f5f45b7ca8b97f85
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-0.4-num-2811-sd-0/checkpoint-2995/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14624519710bb8cc1311e6cc781b5a33ed02202d402078e40f4aa5315b0e7fcc
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-0.4-num-2811-sd-0/checkpoint-2995/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d52afad77475f7419648c9086512c38d0f7c88c906ef4783e76885c190568b1
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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/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-0.4-num-2811-sd-0/checkpoint-2995/trainer_state.json ADDED
@@ -0,0 +1,2166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8182536363601685,
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-0.4-num-2811-sd-0/checkpoint-1198",
4
+ "epoch": 5.0,
5
+ "eval_steps": 10,
6
+ "global_step": 2995,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01669449081803005,
13
+ "grad_norm": 0.4811326861381531,
14
+ "learning_rate": 0.0002,
15
+ "loss": 2.6298,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0333889816360601,
20
+ "grad_norm": 0.697903573513031,
21
+ "learning_rate": 0.0002,
22
+ "loss": 2.2673,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.05008347245409015,
27
+ "grad_norm": 0.5622886419296265,
28
+ "learning_rate": 0.0002,
29
+ "loss": 2.0746,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0667779632721202,
34
+ "grad_norm": 0.4684421122074127,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.9808,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.08347245409015025,
41
+ "grad_norm": 0.4790354371070862,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.9796,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.1001669449081803,
48
+ "grad_norm": 0.5846750140190125,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.9269,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.11686143572621036,
55
+ "grad_norm": 0.4034216105937958,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.9773,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.1335559265442404,
62
+ "grad_norm": 0.4602500796318054,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.8688,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.15025041736227046,
69
+ "grad_norm": 0.46994853019714355,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.9703,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.1669449081803005,
76
+ "grad_norm": 0.3892269730567932,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.8443,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.18363939899833054,
83
+ "grad_norm": 0.40771016478538513,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.9192,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2003338898163606,
90
+ "grad_norm": 0.3820408880710602,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8292,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.21702838063439064,
97
+ "grad_norm": 0.3719843626022339,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.8313,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.2337228714524207,
104
+ "grad_norm": 0.4359976351261139,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.8189,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.25041736227045075,
111
+ "grad_norm": 0.3932259976863861,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.8125,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.2671118530884808,
118
+ "grad_norm": 0.7001785635948181,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.8681,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.2838063439065108,
125
+ "grad_norm": 0.7619664669036865,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.9328,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3005008347245409,
132
+ "grad_norm": 0.3715350329875946,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.7572,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.31719532554257096,
139
+ "grad_norm": 0.5008004903793335,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.8551,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.333889816360601,
146
+ "grad_norm": 0.47509506344795227,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.8469,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.35058430717863104,
153
+ "grad_norm": 0.41775935888290405,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.9042,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.3672787979966611,
160
+ "grad_norm": 0.43939948081970215,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.7995,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.38397328881469117,
167
+ "grad_norm": 0.5101977586746216,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.8535,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.4006677796327212,
174
+ "grad_norm": 0.37367475032806396,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.8261,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.41736227045075125,
181
+ "grad_norm": 0.38865089416503906,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.8361,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.4340567612687813,
188
+ "grad_norm": 0.33937838673591614,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.8044,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.4507512520868113,
195
+ "grad_norm": 0.41416028141975403,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.8288,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.4674457429048414,
202
+ "grad_norm": 0.4010271430015564,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.8542,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.48414023372287146,
209
+ "grad_norm": 0.3960907459259033,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.8803,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.5008347245409015,
216
+ "grad_norm": 0.357433021068573,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.8875,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.5175292153589316,
223
+ "grad_norm": 0.38190674781799316,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.8478,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5342237061769616,
230
+ "grad_norm": 0.3336802124977112,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.8142,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5509181969949917,
237
+ "grad_norm": 0.35935860872268677,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.82,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.5676126878130217,
244
+ "grad_norm": 0.3950583040714264,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.854,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.5843071786310517,
251
+ "grad_norm": 0.31413400173187256,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.8089,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6010016694490818,
258
+ "grad_norm": 0.3342890441417694,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.8417,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6176961602671118,
265
+ "grad_norm": 0.36961331963539124,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.766,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6343906510851419,
272
+ "grad_norm": 0.350652813911438,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.8264,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.6510851419031719,
279
+ "grad_norm": 0.3588177263736725,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.7797,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.667779632721202,
286
+ "grad_norm": 0.3327147960662842,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.6967,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.6844741235392321,
293
+ "grad_norm": 0.3632844388484955,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.754,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.7011686143572621,
300
+ "grad_norm": 0.34581053256988525,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.8264,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.7178631051752922,
307
+ "grad_norm": 0.37237727642059326,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.8706,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.7345575959933222,
314
+ "grad_norm": 0.48366475105285645,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.711,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.7512520868113522,
321
+ "grad_norm": 0.3512793183326721,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.8658,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.7679465776293823,
328
+ "grad_norm": 0.30473145842552185,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.7687,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.7846410684474123,
335
+ "grad_norm": 0.3718157112598419,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.789,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.8013355592654424,
342
+ "grad_norm": 0.34506872296333313,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.8527,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.8180300500834724,
349
+ "grad_norm": 0.36895203590393066,
350
+ "learning_rate": 0.0002,
351
+ "loss": 1.8163,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.8347245409015025,
356
+ "grad_norm": 0.35659778118133545,
357
+ "learning_rate": 0.0002,
358
+ "loss": 1.8499,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.8514190317195326,
363
+ "grad_norm": 0.3631179928779602,
364
+ "learning_rate": 0.0002,
365
+ "loss": 1.8096,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.8681135225375626,
370
+ "grad_norm": 0.3252873420715332,
371
+ "learning_rate": 0.0002,
372
+ "loss": 1.8003,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.8848080133555927,
377
+ "grad_norm": 0.32796111702919006,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.7831,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.9015025041736227,
384
+ "grad_norm": 0.3556145131587982,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.7675,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.9181969949916527,
391
+ "grad_norm": 0.33029764890670776,
392
+ "learning_rate": 0.0002,
393
+ "loss": 1.7902,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.9348914858096828,
398
+ "grad_norm": 0.3531745970249176,
399
+ "learning_rate": 0.0002,
400
+ "loss": 1.7932,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.9515859766277128,
405
+ "grad_norm": 0.3486989140510559,
406
+ "learning_rate": 0.0002,
407
+ "loss": 1.7982,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.9682804674457429,
412
+ "grad_norm": 0.34676939249038696,
413
+ "learning_rate": 0.0002,
414
+ "loss": 1.8522,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.9849749582637729,
419
+ "grad_norm": 0.3389652669429779,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.7805,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 1.0,
426
+ "eval_loss": 1.8236571550369263,
427
+ "eval_runtime": 77.157,
428
+ "eval_samples_per_second": 6.675,
429
+ "eval_steps_per_second": 0.842,
430
+ "step": 599
431
+ },
432
+ {
433
+ "epoch": 1.001669449081803,
434
+ "grad_norm": 0.6550514698028564,
435
+ "learning_rate": 0.0002,
436
+ "loss": 1.7724,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.018363939899833,
441
+ "grad_norm": 0.36824166774749756,
442
+ "learning_rate": 0.0002,
443
+ "loss": 1.7601,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.0350584307178632,
448
+ "grad_norm": 0.34707099199295044,
449
+ "learning_rate": 0.0002,
450
+ "loss": 1.7684,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.0517529215358932,
455
+ "grad_norm": 0.38599663972854614,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.7552,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.0684474123539232,
462
+ "grad_norm": 0.34381693601608276,
463
+ "learning_rate": 0.0002,
464
+ "loss": 1.7396,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.0851419031719534,
469
+ "grad_norm": 0.3657481372356415,
470
+ "learning_rate": 0.0002,
471
+ "loss": 1.7621,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.1018363939899833,
476
+ "grad_norm": 0.3310803771018982,
477
+ "learning_rate": 0.0002,
478
+ "loss": 1.723,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.1185308848080133,
483
+ "grad_norm": 0.37122875452041626,
484
+ "learning_rate": 0.0002,
485
+ "loss": 1.7788,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.1352253756260433,
490
+ "grad_norm": 0.3976633548736572,
491
+ "learning_rate": 0.0002,
492
+ "loss": 1.6887,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.1519198664440735,
497
+ "grad_norm": 0.37567615509033203,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.7398,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.1686143572621035,
504
+ "grad_norm": 0.3683645725250244,
505
+ "learning_rate": 0.0002,
506
+ "loss": 1.7326,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.1853088480801335,
511
+ "grad_norm": 0.3862009644508362,
512
+ "learning_rate": 0.0002,
513
+ "loss": 1.8074,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.2020033388981637,
518
+ "grad_norm": 0.3478439450263977,
519
+ "learning_rate": 0.0002,
520
+ "loss": 1.7993,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.2186978297161937,
525
+ "grad_norm": 0.3694932162761688,
526
+ "learning_rate": 0.0002,
527
+ "loss": 1.7945,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.2353923205342237,
532
+ "grad_norm": 0.3661787211894989,
533
+ "learning_rate": 0.0002,
534
+ "loss": 1.7269,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.2520868113522536,
539
+ "grad_norm": 0.372951865196228,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.7561,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.2687813021702838,
546
+ "grad_norm": 0.38718998432159424,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.7507,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.2854757929883138,
553
+ "grad_norm": 0.37488260865211487,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.7331,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.302170283806344,
560
+ "grad_norm": 0.34794917702674866,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.7548,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.318864774624374,
567
+ "grad_norm": 0.3627476990222931,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.7592,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.335559265442404,
574
+ "grad_norm": 0.3773096799850464,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.6837,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.352253756260434,
581
+ "grad_norm": 0.36476725339889526,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7448,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.3689482470784642,
588
+ "grad_norm": 0.3767942190170288,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.7958,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.3856427378964942,
595
+ "grad_norm": 0.3502795398235321,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.7241,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.4023372287145242,
602
+ "grad_norm": 0.4008622169494629,
603
+ "learning_rate": 0.0002,
604
+ "loss": 1.736,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.4190317195325544,
609
+ "grad_norm": 0.4029707610607147,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.7211,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.4357262103505843,
616
+ "grad_norm": 0.41480565071105957,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.712,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.4524207011686143,
623
+ "grad_norm": 0.4351646900177002,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.7287,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.4691151919866443,
630
+ "grad_norm": 0.4053232967853546,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.8436,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.4858096828046745,
637
+ "grad_norm": 0.3515186607837677,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.7669,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.5025041736227045,
644
+ "grad_norm": 0.42895469069480896,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.698,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.5191986644407347,
651
+ "grad_norm": 0.40897831320762634,
652
+ "learning_rate": 0.0002,
653
+ "loss": 1.7064,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.5358931552587647,
658
+ "grad_norm": 0.3544739782810211,
659
+ "learning_rate": 0.0002,
660
+ "loss": 1.7539,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.5525876460767947,
665
+ "grad_norm": 0.3848305642604828,
666
+ "learning_rate": 0.0002,
667
+ "loss": 1.7596,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.5692821368948247,
672
+ "grad_norm": 0.36952173709869385,
673
+ "learning_rate": 0.0002,
674
+ "loss": 1.7344,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.5859766277128546,
679
+ "grad_norm": 0.36505743861198425,
680
+ "learning_rate": 0.0002,
681
+ "loss": 1.7329,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.6026711185308848,
686
+ "grad_norm": 0.3707764446735382,
687
+ "learning_rate": 0.0002,
688
+ "loss": 1.6828,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.6193656093489148,
693
+ "grad_norm": 0.35995468497276306,
694
+ "learning_rate": 0.0002,
695
+ "loss": 1.7465,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.636060100166945,
700
+ "grad_norm": 0.35458096861839294,
701
+ "learning_rate": 0.0002,
702
+ "loss": 1.7537,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.652754590984975,
707
+ "grad_norm": 0.3557756841182709,
708
+ "learning_rate": 0.0002,
709
+ "loss": 1.7075,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.669449081803005,
714
+ "grad_norm": 0.355899453163147,
715
+ "learning_rate": 0.0002,
716
+ "loss": 1.7307,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.686143572621035,
721
+ "grad_norm": 0.3709148168563843,
722
+ "learning_rate": 0.0002,
723
+ "loss": 1.7701,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.702838063439065,
728
+ "grad_norm": 0.3731614947319031,
729
+ "learning_rate": 0.0002,
730
+ "loss": 1.7637,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.7195325542570952,
735
+ "grad_norm": 0.3639261722564697,
736
+ "learning_rate": 0.0002,
737
+ "loss": 1.741,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.7362270450751254,
742
+ "grad_norm": 0.36371079087257385,
743
+ "learning_rate": 0.0002,
744
+ "loss": 1.727,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.7529215358931554,
749
+ "grad_norm": 0.38235539197921753,
750
+ "learning_rate": 0.0002,
751
+ "loss": 1.7275,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.7696160267111853,
756
+ "grad_norm": 0.4109364151954651,
757
+ "learning_rate": 0.0002,
758
+ "loss": 1.7304,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.7863105175292153,
763
+ "grad_norm": 0.3499647378921509,
764
+ "learning_rate": 0.0002,
765
+ "loss": 1.7244,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.8030050083472453,
770
+ "grad_norm": 0.3892260193824768,
771
+ "learning_rate": 0.0002,
772
+ "loss": 1.7117,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.8196994991652755,
777
+ "grad_norm": 0.3545094132423401,
778
+ "learning_rate": 0.0002,
779
+ "loss": 1.7764,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.8363939899833055,
784
+ "grad_norm": 0.40419837832450867,
785
+ "learning_rate": 0.0002,
786
+ "loss": 1.87,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.8530884808013357,
791
+ "grad_norm": 0.38423678278923035,
792
+ "learning_rate": 0.0002,
793
+ "loss": 1.6783,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.8697829716193657,
798
+ "grad_norm": 0.378408282995224,
799
+ "learning_rate": 0.0002,
800
+ "loss": 1.7714,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.8864774624373957,
805
+ "grad_norm": 0.4071941077709198,
806
+ "learning_rate": 0.0002,
807
+ "loss": 1.7461,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.9031719532554257,
812
+ "grad_norm": 0.42363739013671875,
813
+ "learning_rate": 0.0002,
814
+ "loss": 1.7281,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.9198664440734556,
819
+ "grad_norm": 0.37373560667037964,
820
+ "learning_rate": 0.0002,
821
+ "loss": 1.819,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.9365609348914858,
826
+ "grad_norm": 0.36408767104148865,
827
+ "learning_rate": 0.0002,
828
+ "loss": 1.7847,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.9532554257095158,
833
+ "grad_norm": 0.3795453906059265,
834
+ "learning_rate": 0.0002,
835
+ "loss": 1.6725,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.969949916527546,
840
+ "grad_norm": 0.34415504336357117,
841
+ "learning_rate": 0.0002,
842
+ "loss": 1.7726,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.986644407345576,
847
+ "grad_norm": 0.3491021394729614,
848
+ "learning_rate": 0.0002,
849
+ "loss": 1.6199,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 2.0,
854
+ "eval_loss": 1.8182536363601685,
855
+ "eval_runtime": 87.8767,
856
+ "eval_samples_per_second": 5.86,
857
+ "eval_steps_per_second": 0.74,
858
+ "step": 1198
859
+ },
860
+ {
861
+ "epoch": 2.003338898163606,
862
+ "grad_norm": 0.36758512258529663,
863
+ "learning_rate": 0.0002,
864
+ "loss": 1.5857,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.020033388981636,
869
+ "grad_norm": 0.36278557777404785,
870
+ "learning_rate": 0.0002,
871
+ "loss": 1.61,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.036727879799666,
876
+ "grad_norm": 0.4186977744102478,
877
+ "learning_rate": 0.0002,
878
+ "loss": 1.6733,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.053422370617696,
883
+ "grad_norm": 0.3958706855773926,
884
+ "learning_rate": 0.0002,
885
+ "loss": 1.6977,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.0701168614357264,
890
+ "grad_norm": 0.43305638432502747,
891
+ "learning_rate": 0.0002,
892
+ "loss": 1.7054,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.0868113522537564,
897
+ "grad_norm": 0.4509678781032562,
898
+ "learning_rate": 0.0002,
899
+ "loss": 1.6275,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.1035058430717863,
904
+ "grad_norm": 0.4297264516353607,
905
+ "learning_rate": 0.0002,
906
+ "loss": 1.6814,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.1202003338898163,
911
+ "grad_norm": 0.4579504132270813,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.6121,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.1368948247078463,
918
+ "grad_norm": 0.4223267138004303,
919
+ "learning_rate": 0.0002,
920
+ "loss": 1.6207,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.1535893155258763,
925
+ "grad_norm": 0.41538703441619873,
926
+ "learning_rate": 0.0002,
927
+ "loss": 1.6472,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.1702838063439067,
932
+ "grad_norm": 0.4987374544143677,
933
+ "learning_rate": 0.0002,
934
+ "loss": 1.6274,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.1869782971619367,
939
+ "grad_norm": 0.45300114154815674,
940
+ "learning_rate": 0.0002,
941
+ "loss": 1.6555,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.2036727879799667,
946
+ "grad_norm": 0.4577588737010956,
947
+ "learning_rate": 0.0002,
948
+ "loss": 1.6486,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.2203672787979967,
953
+ "grad_norm": 0.4110747277736664,
954
+ "learning_rate": 0.0002,
955
+ "loss": 1.644,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.2370617696160267,
960
+ "grad_norm": 0.5107163190841675,
961
+ "learning_rate": 0.0002,
962
+ "loss": 1.5875,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.2537562604340566,
967
+ "grad_norm": 0.41190820932388306,
968
+ "learning_rate": 0.0002,
969
+ "loss": 1.691,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.2704507512520866,
974
+ "grad_norm": 0.47458386421203613,
975
+ "learning_rate": 0.0002,
976
+ "loss": 1.5745,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.287145242070117,
981
+ "grad_norm": 0.42136940360069275,
982
+ "learning_rate": 0.0002,
983
+ "loss": 1.6964,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.303839732888147,
988
+ "grad_norm": 0.48292383551597595,
989
+ "learning_rate": 0.0002,
990
+ "loss": 1.657,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.320534223706177,
995
+ "grad_norm": 0.4519229531288147,
996
+ "learning_rate": 0.0002,
997
+ "loss": 1.6816,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.337228714524207,
1002
+ "grad_norm": 0.5860922336578369,
1003
+ "learning_rate": 0.0002,
1004
+ "loss": 1.6408,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.353923205342237,
1009
+ "grad_norm": 0.4362313747406006,
1010
+ "learning_rate": 0.0002,
1011
+ "loss": 1.5551,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.370617696160267,
1016
+ "grad_norm": 0.46916621923446655,
1017
+ "learning_rate": 0.0002,
1018
+ "loss": 1.6763,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.3873121869782974,
1023
+ "grad_norm": 0.5249663591384888,
1024
+ "learning_rate": 0.0002,
1025
+ "loss": 1.6082,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.4040066777963274,
1030
+ "grad_norm": 0.4764375388622284,
1031
+ "learning_rate": 0.0002,
1032
+ "loss": 1.6793,
1033
+ "step": 1440
1034
+ },
1035
+ {
1036
+ "epoch": 2.4207011686143574,
1037
+ "grad_norm": 0.46573784947395325,
1038
+ "learning_rate": 0.0002,
1039
+ "loss": 1.6395,
1040
+ "step": 1450
1041
+ },
1042
+ {
1043
+ "epoch": 2.4373956594323873,
1044
+ "grad_norm": 0.44539371132850647,
1045
+ "learning_rate": 0.0002,
1046
+ "loss": 1.6629,
1047
+ "step": 1460
1048
+ },
1049
+ {
1050
+ "epoch": 2.4540901502504173,
1051
+ "grad_norm": 0.40925896167755127,
1052
+ "learning_rate": 0.0002,
1053
+ "loss": 1.6149,
1054
+ "step": 1470
1055
+ },
1056
+ {
1057
+ "epoch": 2.4707846410684473,
1058
+ "grad_norm": 0.4431462287902832,
1059
+ "learning_rate": 0.0002,
1060
+ "loss": 1.6213,
1061
+ "step": 1480
1062
+ },
1063
+ {
1064
+ "epoch": 2.4874791318864773,
1065
+ "grad_norm": 0.5476022362709045,
1066
+ "learning_rate": 0.0002,
1067
+ "loss": 1.692,
1068
+ "step": 1490
1069
+ },
1070
+ {
1071
+ "epoch": 2.5041736227045073,
1072
+ "grad_norm": 0.44762539863586426,
1073
+ "learning_rate": 0.0002,
1074
+ "loss": 1.5875,
1075
+ "step": 1500
1076
+ },
1077
+ {
1078
+ "epoch": 2.5208681135225377,
1079
+ "grad_norm": 0.5470041632652283,
1080
+ "learning_rate": 0.0002,
1081
+ "loss": 1.6811,
1082
+ "step": 1510
1083
+ },
1084
+ {
1085
+ "epoch": 2.5375626043405677,
1086
+ "grad_norm": 0.4739997088909149,
1087
+ "learning_rate": 0.0002,
1088
+ "loss": 1.7411,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.5542570951585977,
1093
+ "grad_norm": 0.47115322947502136,
1094
+ "learning_rate": 0.0002,
1095
+ "loss": 1.5975,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.5709515859766277,
1100
+ "grad_norm": 0.49705708026885986,
1101
+ "learning_rate": 0.0002,
1102
+ "loss": 1.6828,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.5876460767946576,
1107
+ "grad_norm": 0.5537301301956177,
1108
+ "learning_rate": 0.0002,
1109
+ "loss": 1.7135,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.604340567612688,
1114
+ "grad_norm": 0.46930626034736633,
1115
+ "learning_rate": 0.0002,
1116
+ "loss": 1.5753,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.621035058430718,
1121
+ "grad_norm": 0.42371469736099243,
1122
+ "learning_rate": 0.0002,
1123
+ "loss": 1.6706,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.637729549248748,
1128
+ "grad_norm": 0.49005603790283203,
1129
+ "learning_rate": 0.0002,
1130
+ "loss": 1.6193,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.654424040066778,
1135
+ "grad_norm": 0.4646829068660736,
1136
+ "learning_rate": 0.0002,
1137
+ "loss": 1.7138,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.671118530884808,
1142
+ "grad_norm": 0.5091238617897034,
1143
+ "learning_rate": 0.0002,
1144
+ "loss": 1.6806,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.687813021702838,
1149
+ "grad_norm": 0.4889985918998718,
1150
+ "learning_rate": 0.0002,
1151
+ "loss": 1.65,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.704507512520868,
1156
+ "grad_norm": 0.5128234624862671,
1157
+ "learning_rate": 0.0002,
1158
+ "loss": 1.6573,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.721202003338898,
1163
+ "grad_norm": 0.46999186277389526,
1164
+ "learning_rate": 0.0002,
1165
+ "loss": 1.6739,
1166
+ "step": 1630
1167
+ },
1168
+ {
1169
+ "epoch": 2.7378964941569284,
1170
+ "grad_norm": 0.4949921667575836,
1171
+ "learning_rate": 0.0002,
1172
+ "loss": 1.6277,
1173
+ "step": 1640
1174
+ },
1175
+ {
1176
+ "epoch": 2.7545909849749584,
1177
+ "grad_norm": 0.4484370946884155,
1178
+ "learning_rate": 0.0002,
1179
+ "loss": 1.5958,
1180
+ "step": 1650
1181
+ },
1182
+ {
1183
+ "epoch": 2.7712854757929883,
1184
+ "grad_norm": 0.45599570870399475,
1185
+ "learning_rate": 0.0002,
1186
+ "loss": 1.6156,
1187
+ "step": 1660
1188
+ },
1189
+ {
1190
+ "epoch": 2.7879799666110183,
1191
+ "grad_norm": 0.5093285441398621,
1192
+ "learning_rate": 0.0002,
1193
+ "loss": 1.6037,
1194
+ "step": 1670
1195
+ },
1196
+ {
1197
+ "epoch": 2.8046744574290483,
1198
+ "grad_norm": 0.44737935066223145,
1199
+ "learning_rate": 0.0002,
1200
+ "loss": 1.6675,
1201
+ "step": 1680
1202
+ },
1203
+ {
1204
+ "epoch": 2.8213689482470787,
1205
+ "grad_norm": 0.4374251365661621,
1206
+ "learning_rate": 0.0002,
1207
+ "loss": 1.6429,
1208
+ "step": 1690
1209
+ },
1210
+ {
1211
+ "epoch": 2.8380634390651087,
1212
+ "grad_norm": 0.44765740633010864,
1213
+ "learning_rate": 0.0002,
1214
+ "loss": 1.5941,
1215
+ "step": 1700
1216
+ },
1217
+ {
1218
+ "epoch": 2.8547579298831387,
1219
+ "grad_norm": 0.44685253500938416,
1220
+ "learning_rate": 0.0002,
1221
+ "loss": 1.6841,
1222
+ "step": 1710
1223
+ },
1224
+ {
1225
+ "epoch": 2.8714524207011687,
1226
+ "grad_norm": 0.44777143001556396,
1227
+ "learning_rate": 0.0002,
1228
+ "loss": 1.6301,
1229
+ "step": 1720
1230
+ },
1231
+ {
1232
+ "epoch": 2.8881469115191987,
1233
+ "grad_norm": 0.4178132712841034,
1234
+ "learning_rate": 0.0002,
1235
+ "loss": 1.6473,
1236
+ "step": 1730
1237
+ },
1238
+ {
1239
+ "epoch": 2.9048414023372287,
1240
+ "grad_norm": 0.4487852156162262,
1241
+ "learning_rate": 0.0002,
1242
+ "loss": 1.6491,
1243
+ "step": 1740
1244
+ },
1245
+ {
1246
+ "epoch": 2.9215358931552586,
1247
+ "grad_norm": 0.47137337923049927,
1248
+ "learning_rate": 0.0002,
1249
+ "loss": 1.6616,
1250
+ "step": 1750
1251
+ },
1252
+ {
1253
+ "epoch": 2.9382303839732886,
1254
+ "grad_norm": 0.48543235659599304,
1255
+ "learning_rate": 0.0002,
1256
+ "loss": 1.6767,
1257
+ "step": 1760
1258
+ },
1259
+ {
1260
+ "epoch": 2.9549248747913186,
1261
+ "grad_norm": 0.4174182116985321,
1262
+ "learning_rate": 0.0002,
1263
+ "loss": 1.7055,
1264
+ "step": 1770
1265
+ },
1266
+ {
1267
+ "epoch": 2.971619365609349,
1268
+ "grad_norm": 0.43385711312294006,
1269
+ "learning_rate": 0.0002,
1270
+ "loss": 1.5767,
1271
+ "step": 1780
1272
+ },
1273
+ {
1274
+ "epoch": 2.988313856427379,
1275
+ "grad_norm": 0.474332332611084,
1276
+ "learning_rate": 0.0002,
1277
+ "loss": 1.6215,
1278
+ "step": 1790
1279
+ },
1280
+ {
1281
+ "epoch": 3.0,
1282
+ "eval_loss": 1.8456445932388306,
1283
+ "eval_runtime": 87.6261,
1284
+ "eval_samples_per_second": 5.877,
1285
+ "eval_steps_per_second": 0.742,
1286
+ "step": 1797
1287
+ },
1288
+ {
1289
+ "epoch": 3.005008347245409,
1290
+ "grad_norm": 0.40323764085769653,
1291
+ "learning_rate": 0.0002,
1292
+ "loss": 1.6224,
1293
+ "step": 1800
1294
+ },
1295
+ {
1296
+ "epoch": 3.021702838063439,
1297
+ "grad_norm": 0.45069044828414917,
1298
+ "learning_rate": 0.0002,
1299
+ "loss": 1.5367,
1300
+ "step": 1810
1301
+ },
1302
+ {
1303
+ "epoch": 3.038397328881469,
1304
+ "grad_norm": 0.6204925775527954,
1305
+ "learning_rate": 0.0002,
1306
+ "loss": 1.5271,
1307
+ "step": 1820
1308
+ },
1309
+ {
1310
+ "epoch": 3.0550918196994994,
1311
+ "grad_norm": 0.5857783555984497,
1312
+ "learning_rate": 0.0002,
1313
+ "loss": 1.5056,
1314
+ "step": 1830
1315
+ },
1316
+ {
1317
+ "epoch": 3.0717863105175294,
1318
+ "grad_norm": 0.6776524782180786,
1319
+ "learning_rate": 0.0002,
1320
+ "loss": 1.5137,
1321
+ "step": 1840
1322
+ },
1323
+ {
1324
+ "epoch": 3.0884808013355594,
1325
+ "grad_norm": 0.5486199855804443,
1326
+ "learning_rate": 0.0002,
1327
+ "loss": 1.5106,
1328
+ "step": 1850
1329
+ },
1330
+ {
1331
+ "epoch": 3.1051752921535893,
1332
+ "grad_norm": 0.5496503710746765,
1333
+ "learning_rate": 0.0002,
1334
+ "loss": 1.414,
1335
+ "step": 1860
1336
+ },
1337
+ {
1338
+ "epoch": 3.1218697829716193,
1339
+ "grad_norm": 0.5602648258209229,
1340
+ "learning_rate": 0.0002,
1341
+ "loss": 1.5181,
1342
+ "step": 1870
1343
+ },
1344
+ {
1345
+ "epoch": 3.1385642737896493,
1346
+ "grad_norm": 1.0697380304336548,
1347
+ "learning_rate": 0.0002,
1348
+ "loss": 1.5406,
1349
+ "step": 1880
1350
+ },
1351
+ {
1352
+ "epoch": 3.1552587646076793,
1353
+ "grad_norm": 0.6087332367897034,
1354
+ "learning_rate": 0.0002,
1355
+ "loss": 1.4889,
1356
+ "step": 1890
1357
+ },
1358
+ {
1359
+ "epoch": 3.1719532554257097,
1360
+ "grad_norm": 0.5112161040306091,
1361
+ "learning_rate": 0.0002,
1362
+ "loss": 1.5219,
1363
+ "step": 1900
1364
+ },
1365
+ {
1366
+ "epoch": 3.1886477462437397,
1367
+ "grad_norm": 0.6393680572509766,
1368
+ "learning_rate": 0.0002,
1369
+ "loss": 1.5139,
1370
+ "step": 1910
1371
+ },
1372
+ {
1373
+ "epoch": 3.2053422370617697,
1374
+ "grad_norm": 0.7201815247535706,
1375
+ "learning_rate": 0.0002,
1376
+ "loss": 1.5337,
1377
+ "step": 1920
1378
+ },
1379
+ {
1380
+ "epoch": 3.2220367278797997,
1381
+ "grad_norm": 0.5856018662452698,
1382
+ "learning_rate": 0.0002,
1383
+ "loss": 1.6055,
1384
+ "step": 1930
1385
+ },
1386
+ {
1387
+ "epoch": 3.2387312186978297,
1388
+ "grad_norm": 0.581247866153717,
1389
+ "learning_rate": 0.0002,
1390
+ "loss": 1.4791,
1391
+ "step": 1940
1392
+ },
1393
+ {
1394
+ "epoch": 3.2554257095158596,
1395
+ "grad_norm": 0.6055102944374084,
1396
+ "learning_rate": 0.0002,
1397
+ "loss": 1.5395,
1398
+ "step": 1950
1399
+ },
1400
+ {
1401
+ "epoch": 3.27212020033389,
1402
+ "grad_norm": 0.546894371509552,
1403
+ "learning_rate": 0.0002,
1404
+ "loss": 1.5086,
1405
+ "step": 1960
1406
+ },
1407
+ {
1408
+ "epoch": 3.28881469115192,
1409
+ "grad_norm": 0.565558910369873,
1410
+ "learning_rate": 0.0002,
1411
+ "loss": 1.5712,
1412
+ "step": 1970
1413
+ },
1414
+ {
1415
+ "epoch": 3.30550918196995,
1416
+ "grad_norm": 1.2238883972167969,
1417
+ "learning_rate": 0.0002,
1418
+ "loss": 1.47,
1419
+ "step": 1980
1420
+ },
1421
+ {
1422
+ "epoch": 3.32220367278798,
1423
+ "grad_norm": 0.6362585425376892,
1424
+ "learning_rate": 0.0002,
1425
+ "loss": 1.4655,
1426
+ "step": 1990
1427
+ },
1428
+ {
1429
+ "epoch": 3.33889816360601,
1430
+ "grad_norm": 0.6131124496459961,
1431
+ "learning_rate": 0.0002,
1432
+ "loss": 1.5157,
1433
+ "step": 2000
1434
+ },
1435
+ {
1436
+ "epoch": 3.35559265442404,
1437
+ "grad_norm": 0.5181341767311096,
1438
+ "learning_rate": 0.0002,
1439
+ "loss": 1.5322,
1440
+ "step": 2010
1441
+ },
1442
+ {
1443
+ "epoch": 3.37228714524207,
1444
+ "grad_norm": 0.6667609810829163,
1445
+ "learning_rate": 0.0002,
1446
+ "loss": 1.5039,
1447
+ "step": 2020
1448
+ },
1449
+ {
1450
+ "epoch": 3.3889816360601,
1451
+ "grad_norm": 0.6488749980926514,
1452
+ "learning_rate": 0.0002,
1453
+ "loss": 1.5814,
1454
+ "step": 2030
1455
+ },
1456
+ {
1457
+ "epoch": 3.4056761268781304,
1458
+ "grad_norm": 0.5693286061286926,
1459
+ "learning_rate": 0.0002,
1460
+ "loss": 1.5226,
1461
+ "step": 2040
1462
+ },
1463
+ {
1464
+ "epoch": 3.4223706176961604,
1465
+ "grad_norm": 0.6154143810272217,
1466
+ "learning_rate": 0.0002,
1467
+ "loss": 1.5121,
1468
+ "step": 2050
1469
+ },
1470
+ {
1471
+ "epoch": 3.4390651085141903,
1472
+ "grad_norm": 0.6747981309890747,
1473
+ "learning_rate": 0.0002,
1474
+ "loss": 1.6033,
1475
+ "step": 2060
1476
+ },
1477
+ {
1478
+ "epoch": 3.4557595993322203,
1479
+ "grad_norm": 0.5494789481163025,
1480
+ "learning_rate": 0.0002,
1481
+ "loss": 1.5857,
1482
+ "step": 2070
1483
+ },
1484
+ {
1485
+ "epoch": 3.4724540901502503,
1486
+ "grad_norm": 2.481968402862549,
1487
+ "learning_rate": 0.0002,
1488
+ "loss": 1.5223,
1489
+ "step": 2080
1490
+ },
1491
+ {
1492
+ "epoch": 3.4891485809682803,
1493
+ "grad_norm": 0.589784562587738,
1494
+ "learning_rate": 0.0002,
1495
+ "loss": 1.4989,
1496
+ "step": 2090
1497
+ },
1498
+ {
1499
+ "epoch": 3.5058430717863107,
1500
+ "grad_norm": 0.6449820399284363,
1501
+ "learning_rate": 0.0002,
1502
+ "loss": 1.6227,
1503
+ "step": 2100
1504
+ },
1505
+ {
1506
+ "epoch": 3.5225375626043407,
1507
+ "grad_norm": 0.6467038989067078,
1508
+ "learning_rate": 0.0002,
1509
+ "loss": 1.588,
1510
+ "step": 2110
1511
+ },
1512
+ {
1513
+ "epoch": 3.5392320534223707,
1514
+ "grad_norm": 0.6533533334732056,
1515
+ "learning_rate": 0.0002,
1516
+ "loss": 1.5655,
1517
+ "step": 2120
1518
+ },
1519
+ {
1520
+ "epoch": 3.5559265442404007,
1521
+ "grad_norm": 0.6804035902023315,
1522
+ "learning_rate": 0.0002,
1523
+ "loss": 1.6052,
1524
+ "step": 2130
1525
+ },
1526
+ {
1527
+ "epoch": 3.5726210350584306,
1528
+ "grad_norm": 0.628773033618927,
1529
+ "learning_rate": 0.0002,
1530
+ "loss": 1.5408,
1531
+ "step": 2140
1532
+ },
1533
+ {
1534
+ "epoch": 3.5893155258764606,
1535
+ "grad_norm": 0.6055739521980286,
1536
+ "learning_rate": 0.0002,
1537
+ "loss": 1.5487,
1538
+ "step": 2150
1539
+ },
1540
+ {
1541
+ "epoch": 3.6060100166944906,
1542
+ "grad_norm": 0.6000894904136658,
1543
+ "learning_rate": 0.0002,
1544
+ "loss": 1.5305,
1545
+ "step": 2160
1546
+ },
1547
+ {
1548
+ "epoch": 3.6227045075125206,
1549
+ "grad_norm": 0.5862473249435425,
1550
+ "learning_rate": 0.0002,
1551
+ "loss": 1.4742,
1552
+ "step": 2170
1553
+ },
1554
+ {
1555
+ "epoch": 3.639398998330551,
1556
+ "grad_norm": 0.6547419428825378,
1557
+ "learning_rate": 0.0002,
1558
+ "loss": 1.503,
1559
+ "step": 2180
1560
+ },
1561
+ {
1562
+ "epoch": 3.656093489148581,
1563
+ "grad_norm": 0.5610318779945374,
1564
+ "learning_rate": 0.0002,
1565
+ "loss": 1.4704,
1566
+ "step": 2190
1567
+ },
1568
+ {
1569
+ "epoch": 3.672787979966611,
1570
+ "grad_norm": 0.6387564539909363,
1571
+ "learning_rate": 0.0002,
1572
+ "loss": 1.4814,
1573
+ "step": 2200
1574
+ },
1575
+ {
1576
+ "epoch": 3.689482470784641,
1577
+ "grad_norm": 0.6065090894699097,
1578
+ "learning_rate": 0.0002,
1579
+ "loss": 1.5356,
1580
+ "step": 2210
1581
+ },
1582
+ {
1583
+ "epoch": 3.706176961602671,
1584
+ "grad_norm": 0.6266646981239319,
1585
+ "learning_rate": 0.0002,
1586
+ "loss": 1.5074,
1587
+ "step": 2220
1588
+ },
1589
+ {
1590
+ "epoch": 3.7228714524207014,
1591
+ "grad_norm": 0.626944363117218,
1592
+ "learning_rate": 0.0002,
1593
+ "loss": 1.5146,
1594
+ "step": 2230
1595
+ },
1596
+ {
1597
+ "epoch": 3.7395659432387314,
1598
+ "grad_norm": 0.6043975949287415,
1599
+ "learning_rate": 0.0002,
1600
+ "loss": 1.5131,
1601
+ "step": 2240
1602
+ },
1603
+ {
1604
+ "epoch": 3.7562604340567614,
1605
+ "grad_norm": 0.599732518196106,
1606
+ "learning_rate": 0.0002,
1607
+ "loss": 1.5929,
1608
+ "step": 2250
1609
+ },
1610
+ {
1611
+ "epoch": 3.7729549248747913,
1612
+ "grad_norm": 0.6738389134407043,
1613
+ "learning_rate": 0.0002,
1614
+ "loss": 1.5236,
1615
+ "step": 2260
1616
+ },
1617
+ {
1618
+ "epoch": 3.7896494156928213,
1619
+ "grad_norm": 0.5561335682868958,
1620
+ "learning_rate": 0.0002,
1621
+ "loss": 1.5003,
1622
+ "step": 2270
1623
+ },
1624
+ {
1625
+ "epoch": 3.8063439065108513,
1626
+ "grad_norm": 0.6185726523399353,
1627
+ "learning_rate": 0.0002,
1628
+ "loss": 1.5013,
1629
+ "step": 2280
1630
+ },
1631
+ {
1632
+ "epoch": 3.8230383973288813,
1633
+ "grad_norm": 0.6151532530784607,
1634
+ "learning_rate": 0.0002,
1635
+ "loss": 1.4996,
1636
+ "step": 2290
1637
+ },
1638
+ {
1639
+ "epoch": 3.8397328881469113,
1640
+ "grad_norm": 0.5808233022689819,
1641
+ "learning_rate": 0.0002,
1642
+ "loss": 1.5453,
1643
+ "step": 2300
1644
+ },
1645
+ {
1646
+ "epoch": 3.8564273789649417,
1647
+ "grad_norm": 0.6615163683891296,
1648
+ "learning_rate": 0.0002,
1649
+ "loss": 1.5223,
1650
+ "step": 2310
1651
+ },
1652
+ {
1653
+ "epoch": 3.8731218697829717,
1654
+ "grad_norm": 0.5832979679107666,
1655
+ "learning_rate": 0.0002,
1656
+ "loss": 1.4365,
1657
+ "step": 2320
1658
+ },
1659
+ {
1660
+ "epoch": 3.8898163606010017,
1661
+ "grad_norm": 0.6119300127029419,
1662
+ "learning_rate": 0.0002,
1663
+ "loss": 1.6036,
1664
+ "step": 2330
1665
+ },
1666
+ {
1667
+ "epoch": 3.9065108514190316,
1668
+ "grad_norm": 0.6489697694778442,
1669
+ "learning_rate": 0.0002,
1670
+ "loss": 1.5581,
1671
+ "step": 2340
1672
+ },
1673
+ {
1674
+ "epoch": 3.9232053422370616,
1675
+ "grad_norm": 0.5539063215255737,
1676
+ "learning_rate": 0.0002,
1677
+ "loss": 1.5601,
1678
+ "step": 2350
1679
+ },
1680
+ {
1681
+ "epoch": 3.939899833055092,
1682
+ "grad_norm": 0.6062877178192139,
1683
+ "learning_rate": 0.0002,
1684
+ "loss": 1.5174,
1685
+ "step": 2360
1686
+ },
1687
+ {
1688
+ "epoch": 3.956594323873122,
1689
+ "grad_norm": 0.680609941482544,
1690
+ "learning_rate": 0.0002,
1691
+ "loss": 1.5168,
1692
+ "step": 2370
1693
+ },
1694
+ {
1695
+ "epoch": 3.973288814691152,
1696
+ "grad_norm": 0.6176834106445312,
1697
+ "learning_rate": 0.0002,
1698
+ "loss": 1.4875,
1699
+ "step": 2380
1700
+ },
1701
+ {
1702
+ "epoch": 3.989983305509182,
1703
+ "grad_norm": 0.6538102030754089,
1704
+ "learning_rate": 0.0002,
1705
+ "loss": 1.4984,
1706
+ "step": 2390
1707
+ },
1708
+ {
1709
+ "epoch": 4.0,
1710
+ "eval_loss": 1.8920671939849854,
1711
+ "eval_runtime": 76.5227,
1712
+ "eval_samples_per_second": 6.73,
1713
+ "eval_steps_per_second": 0.849,
1714
+ "step": 2396
1715
+ },
1716
+ {
1717
+ "epoch": 4.006677796327212,
1718
+ "grad_norm": 0.5683762431144714,
1719
+ "learning_rate": 0.0002,
1720
+ "loss": 1.3926,
1721
+ "step": 2400
1722
+ },
1723
+ {
1724
+ "epoch": 4.023372287145242,
1725
+ "grad_norm": 0.6858044862747192,
1726
+ "learning_rate": 0.0002,
1727
+ "loss": 1.3387,
1728
+ "step": 2410
1729
+ },
1730
+ {
1731
+ "epoch": 4.040066777963272,
1732
+ "grad_norm": 0.7614858150482178,
1733
+ "learning_rate": 0.0002,
1734
+ "loss": 1.4495,
1735
+ "step": 2420
1736
+ },
1737
+ {
1738
+ "epoch": 4.056761268781302,
1739
+ "grad_norm": 0.709412693977356,
1740
+ "learning_rate": 0.0002,
1741
+ "loss": 1.2696,
1742
+ "step": 2430
1743
+ },
1744
+ {
1745
+ "epoch": 4.073455759599332,
1746
+ "grad_norm": 0.7070785760879517,
1747
+ "learning_rate": 0.0002,
1748
+ "loss": 1.3836,
1749
+ "step": 2440
1750
+ },
1751
+ {
1752
+ "epoch": 4.090150250417362,
1753
+ "grad_norm": 0.8815216422080994,
1754
+ "learning_rate": 0.0002,
1755
+ "loss": 1.3527,
1756
+ "step": 2450
1757
+ },
1758
+ {
1759
+ "epoch": 4.106844741235392,
1760
+ "grad_norm": 0.759981632232666,
1761
+ "learning_rate": 0.0002,
1762
+ "loss": 1.3731,
1763
+ "step": 2460
1764
+ },
1765
+ {
1766
+ "epoch": 4.123539232053423,
1767
+ "grad_norm": 0.6715240478515625,
1768
+ "learning_rate": 0.0002,
1769
+ "loss": 1.3393,
1770
+ "step": 2470
1771
+ },
1772
+ {
1773
+ "epoch": 4.140233722871453,
1774
+ "grad_norm": 0.7503564953804016,
1775
+ "learning_rate": 0.0002,
1776
+ "loss": 1.3934,
1777
+ "step": 2480
1778
+ },
1779
+ {
1780
+ "epoch": 4.156928213689483,
1781
+ "grad_norm": 0.773743748664856,
1782
+ "learning_rate": 0.0002,
1783
+ "loss": 1.324,
1784
+ "step": 2490
1785
+ },
1786
+ {
1787
+ "epoch": 4.173622704507513,
1788
+ "grad_norm": 0.8850100040435791,
1789
+ "learning_rate": 0.0002,
1790
+ "loss": 1.3782,
1791
+ "step": 2500
1792
+ },
1793
+ {
1794
+ "epoch": 4.190317195325543,
1795
+ "grad_norm": 0.7575962543487549,
1796
+ "learning_rate": 0.0002,
1797
+ "loss": 1.3183,
1798
+ "step": 2510
1799
+ },
1800
+ {
1801
+ "epoch": 4.207011686143573,
1802
+ "grad_norm": 0.9117498397827148,
1803
+ "learning_rate": 0.0002,
1804
+ "loss": 1.3673,
1805
+ "step": 2520
1806
+ },
1807
+ {
1808
+ "epoch": 4.223706176961603,
1809
+ "grad_norm": 0.7637559175491333,
1810
+ "learning_rate": 0.0002,
1811
+ "loss": 1.3242,
1812
+ "step": 2530
1813
+ },
1814
+ {
1815
+ "epoch": 4.240400667779633,
1816
+ "grad_norm": 0.8178390264511108,
1817
+ "learning_rate": 0.0002,
1818
+ "loss": 1.3764,
1819
+ "step": 2540
1820
+ },
1821
+ {
1822
+ "epoch": 4.257095158597663,
1823
+ "grad_norm": 0.8299263119697571,
1824
+ "learning_rate": 0.0002,
1825
+ "loss": 1.3808,
1826
+ "step": 2550
1827
+ },
1828
+ {
1829
+ "epoch": 4.273789649415693,
1830
+ "grad_norm": 0.7238091230392456,
1831
+ "learning_rate": 0.0002,
1832
+ "loss": 1.3637,
1833
+ "step": 2560
1834
+ },
1835
+ {
1836
+ "epoch": 4.290484140233723,
1837
+ "grad_norm": 0.7468036413192749,
1838
+ "learning_rate": 0.0002,
1839
+ "loss": 1.349,
1840
+ "step": 2570
1841
+ },
1842
+ {
1843
+ "epoch": 4.307178631051753,
1844
+ "grad_norm": 0.8012791275978088,
1845
+ "learning_rate": 0.0002,
1846
+ "loss": 1.4422,
1847
+ "step": 2580
1848
+ },
1849
+ {
1850
+ "epoch": 4.323873121869783,
1851
+ "grad_norm": 0.8302484154701233,
1852
+ "learning_rate": 0.0002,
1853
+ "loss": 1.3723,
1854
+ "step": 2590
1855
+ },
1856
+ {
1857
+ "epoch": 4.340567612687813,
1858
+ "grad_norm": 0.751864492893219,
1859
+ "learning_rate": 0.0002,
1860
+ "loss": 1.4013,
1861
+ "step": 2600
1862
+ },
1863
+ {
1864
+ "epoch": 4.357262103505843,
1865
+ "grad_norm": 0.8025410175323486,
1866
+ "learning_rate": 0.0002,
1867
+ "loss": 1.3881,
1868
+ "step": 2610
1869
+ },
1870
+ {
1871
+ "epoch": 4.373956594323873,
1872
+ "grad_norm": 0.7700799703598022,
1873
+ "learning_rate": 0.0002,
1874
+ "loss": 1.3831,
1875
+ "step": 2620
1876
+ },
1877
+ {
1878
+ "epoch": 4.390651085141903,
1879
+ "grad_norm": 0.8526890873908997,
1880
+ "learning_rate": 0.0002,
1881
+ "loss": 1.3721,
1882
+ "step": 2630
1883
+ },
1884
+ {
1885
+ "epoch": 4.407345575959933,
1886
+ "grad_norm": 1.0536625385284424,
1887
+ "learning_rate": 0.0002,
1888
+ "loss": 1.4253,
1889
+ "step": 2640
1890
+ },
1891
+ {
1892
+ "epoch": 4.424040066777963,
1893
+ "grad_norm": 0.7223818898200989,
1894
+ "learning_rate": 0.0002,
1895
+ "loss": 1.3736,
1896
+ "step": 2650
1897
+ },
1898
+ {
1899
+ "epoch": 4.440734557595993,
1900
+ "grad_norm": 0.7981253266334534,
1901
+ "learning_rate": 0.0002,
1902
+ "loss": 1.4652,
1903
+ "step": 2660
1904
+ },
1905
+ {
1906
+ "epoch": 4.457429048414023,
1907
+ "grad_norm": 0.7136162519454956,
1908
+ "learning_rate": 0.0002,
1909
+ "loss": 1.3878,
1910
+ "step": 2670
1911
+ },
1912
+ {
1913
+ "epoch": 4.474123539232053,
1914
+ "grad_norm": 0.8008312582969666,
1915
+ "learning_rate": 0.0002,
1916
+ "loss": 1.4242,
1917
+ "step": 2680
1918
+ },
1919
+ {
1920
+ "epoch": 4.490818030050083,
1921
+ "grad_norm": 0.7924065589904785,
1922
+ "learning_rate": 0.0002,
1923
+ "loss": 1.3448,
1924
+ "step": 2690
1925
+ },
1926
+ {
1927
+ "epoch": 4.507512520868113,
1928
+ "grad_norm": 0.8224287629127502,
1929
+ "learning_rate": 0.0002,
1930
+ "loss": 1.402,
1931
+ "step": 2700
1932
+ },
1933
+ {
1934
+ "epoch": 4.524207011686143,
1935
+ "grad_norm": 0.7494375109672546,
1936
+ "learning_rate": 0.0002,
1937
+ "loss": 1.2841,
1938
+ "step": 2710
1939
+ },
1940
+ {
1941
+ "epoch": 4.540901502504173,
1942
+ "grad_norm": 0.8097899556159973,
1943
+ "learning_rate": 0.0002,
1944
+ "loss": 1.4471,
1945
+ "step": 2720
1946
+ },
1947
+ {
1948
+ "epoch": 4.557595993322204,
1949
+ "grad_norm": 0.7728819251060486,
1950
+ "learning_rate": 0.0002,
1951
+ "loss": 1.4116,
1952
+ "step": 2730
1953
+ },
1954
+ {
1955
+ "epoch": 4.574290484140234,
1956
+ "grad_norm": 0.9112362265586853,
1957
+ "learning_rate": 0.0002,
1958
+ "loss": 1.3549,
1959
+ "step": 2740
1960
+ },
1961
+ {
1962
+ "epoch": 4.590984974958264,
1963
+ "grad_norm": 0.7502672076225281,
1964
+ "learning_rate": 0.0002,
1965
+ "loss": 1.4601,
1966
+ "step": 2750
1967
+ },
1968
+ {
1969
+ "epoch": 4.607679465776294,
1970
+ "grad_norm": 0.8816406726837158,
1971
+ "learning_rate": 0.0002,
1972
+ "loss": 1.4216,
1973
+ "step": 2760
1974
+ },
1975
+ {
1976
+ "epoch": 4.624373956594324,
1977
+ "grad_norm": 0.7117180228233337,
1978
+ "learning_rate": 0.0002,
1979
+ "loss": 1.3233,
1980
+ "step": 2770
1981
+ },
1982
+ {
1983
+ "epoch": 4.641068447412354,
1984
+ "grad_norm": 0.8224529027938843,
1985
+ "learning_rate": 0.0002,
1986
+ "loss": 1.3886,
1987
+ "step": 2780
1988
+ },
1989
+ {
1990
+ "epoch": 4.657762938230384,
1991
+ "grad_norm": 0.7625266313552856,
1992
+ "learning_rate": 0.0002,
1993
+ "loss": 1.3756,
1994
+ "step": 2790
1995
+ },
1996
+ {
1997
+ "epoch": 4.674457429048414,
1998
+ "grad_norm": 0.7754318118095398,
1999
+ "learning_rate": 0.0002,
2000
+ "loss": 1.3953,
2001
+ "step": 2800
2002
+ },
2003
+ {
2004
+ "epoch": 4.691151919866444,
2005
+ "grad_norm": 0.7907336354255676,
2006
+ "learning_rate": 0.0002,
2007
+ "loss": 1.4102,
2008
+ "step": 2810
2009
+ },
2010
+ {
2011
+ "epoch": 4.707846410684474,
2012
+ "grad_norm": 0.7377734780311584,
2013
+ "learning_rate": 0.0002,
2014
+ "loss": 1.3277,
2015
+ "step": 2820
2016
+ },
2017
+ {
2018
+ "epoch": 4.724540901502504,
2019
+ "grad_norm": 0.7380456328392029,
2020
+ "learning_rate": 0.0002,
2021
+ "loss": 1.3686,
2022
+ "step": 2830
2023
+ },
2024
+ {
2025
+ "epoch": 4.741235392320534,
2026
+ "grad_norm": 0.7148023247718811,
2027
+ "learning_rate": 0.0002,
2028
+ "loss": 1.4405,
2029
+ "step": 2840
2030
+ },
2031
+ {
2032
+ "epoch": 4.757929883138564,
2033
+ "grad_norm": 0.807048499584198,
2034
+ "learning_rate": 0.0002,
2035
+ "loss": 1.4025,
2036
+ "step": 2850
2037
+ },
2038
+ {
2039
+ "epoch": 4.774624373956595,
2040
+ "grad_norm": 0.8444154858589172,
2041
+ "learning_rate": 0.0002,
2042
+ "loss": 1.3195,
2043
+ "step": 2860
2044
+ },
2045
+ {
2046
+ "epoch": 4.791318864774624,
2047
+ "grad_norm": 0.8328704237937927,
2048
+ "learning_rate": 0.0002,
2049
+ "loss": 1.4282,
2050
+ "step": 2870
2051
+ },
2052
+ {
2053
+ "epoch": 4.808013355592655,
2054
+ "grad_norm": 0.89827960729599,
2055
+ "learning_rate": 0.0002,
2056
+ "loss": 1.413,
2057
+ "step": 2880
2058
+ },
2059
+ {
2060
+ "epoch": 4.824707846410685,
2061
+ "grad_norm": 0.7848225831985474,
2062
+ "learning_rate": 0.0002,
2063
+ "loss": 1.4488,
2064
+ "step": 2890
2065
+ },
2066
+ {
2067
+ "epoch": 4.841402337228715,
2068
+ "grad_norm": 0.703802227973938,
2069
+ "learning_rate": 0.0002,
2070
+ "loss": 1.3757,
2071
+ "step": 2900
2072
+ },
2073
+ {
2074
+ "epoch": 4.858096828046745,
2075
+ "grad_norm": 0.8092581629753113,
2076
+ "learning_rate": 0.0002,
2077
+ "loss": 1.4404,
2078
+ "step": 2910
2079
+ },
2080
+ {
2081
+ "epoch": 4.874791318864775,
2082
+ "grad_norm": 0.7537722587585449,
2083
+ "learning_rate": 0.0002,
2084
+ "loss": 1.3812,
2085
+ "step": 2920
2086
+ },
2087
+ {
2088
+ "epoch": 4.891485809682805,
2089
+ "grad_norm": 0.7966470122337341,
2090
+ "learning_rate": 0.0002,
2091
+ "loss": 1.4499,
2092
+ "step": 2930
2093
+ },
2094
+ {
2095
+ "epoch": 4.908180300500835,
2096
+ "grad_norm": 0.7860329747200012,
2097
+ "learning_rate": 0.0002,
2098
+ "loss": 1.3922,
2099
+ "step": 2940
2100
+ },
2101
+ {
2102
+ "epoch": 4.924874791318865,
2103
+ "grad_norm": 0.7964439988136292,
2104
+ "learning_rate": 0.0002,
2105
+ "loss": 1.4224,
2106
+ "step": 2950
2107
+ },
2108
+ {
2109
+ "epoch": 4.941569282136895,
2110
+ "grad_norm": 0.740288257598877,
2111
+ "learning_rate": 0.0002,
2112
+ "loss": 1.3869,
2113
+ "step": 2960
2114
+ },
2115
+ {
2116
+ "epoch": 4.958263772954925,
2117
+ "grad_norm": 0.7377685904502869,
2118
+ "learning_rate": 0.0002,
2119
+ "loss": 1.4321,
2120
+ "step": 2970
2121
+ },
2122
+ {
2123
+ "epoch": 4.974958263772955,
2124
+ "grad_norm": 0.793484628200531,
2125
+ "learning_rate": 0.0002,
2126
+ "loss": 1.4253,
2127
+ "step": 2980
2128
+ },
2129
+ {
2130
+ "epoch": 4.9916527545909855,
2131
+ "grad_norm": 0.7710573077201843,
2132
+ "learning_rate": 0.0002,
2133
+ "loss": 1.3966,
2134
+ "step": 2990
2135
+ },
2136
+ {
2137
+ "epoch": 5.0,
2138
+ "eval_loss": 1.9764225482940674,
2139
+ "eval_runtime": 87.968,
2140
+ "eval_samples_per_second": 5.854,
2141
+ "eval_steps_per_second": 0.739,
2142
+ "step": 2995
2143
+ }
2144
+ ],
2145
+ "logging_steps": 10,
2146
+ "max_steps": 4792,
2147
+ "num_input_tokens_seen": 0,
2148
+ "num_train_epochs": 8,
2149
+ "save_steps": 200,
2150
+ "stateful_callbacks": {
2151
+ "TrainerControl": {
2152
+ "args": {
2153
+ "should_epoch_stop": false,
2154
+ "should_evaluate": false,
2155
+ "should_log": false,
2156
+ "should_save": true,
2157
+ "should_training_stop": false
2158
+ },
2159
+ "attributes": {}
2160
+ }
2161
+ },
2162
+ "total_flos": 1.3860189392338944e+17,
2163
+ "train_batch_size": 1,
2164
+ "trial_name": null,
2165
+ "trial_params": null
2166
+ }
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-0.4-num-2811-sd-0/checkpoint-2995/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790482b172d64d1d94b484408c50783310f7b01be29f8cf82f809f2acd1ec121
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-0.4-num-2811-sd-0/checkpoint-3594/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-0.4-num-2811-sd-0/checkpoint-3594/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
+ }