MilaWang commited on
Commit
4a0d9a4
·
verified ·
1 Parent(s): 1f07355

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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/README.md +202 -0
  3. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/adapter_config.json +29 -0
  4. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/adapter_model.safetensors +3 -0
  5. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/README.md +202 -0
  6. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/adapter_config.json +29 -0
  7. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/adapter_model.safetensors +3 -0
  8. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/optimizer.pt +3 -0
  9. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/rng_state.pth +3 -0
  10. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/scheduler.pt +3 -0
  11. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/special_tokens_map.json +17 -0
  12. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/tokenizer.json +3 -0
  13. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/tokenizer_config.json +2063 -0
  14. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/trainer_state.json +1106 -0
  15. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/training_args.bin +3 -0
  16. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/README.md +202 -0
  17. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/adapter_config.json +29 -0
  18. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/adapter_model.safetensors +3 -0
  19. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/optimizer.pt +3 -0
  20. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/rng_state.pth +3 -0
  21. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/scheduler.pt +3 -0
  22. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/special_tokens_map.json +17 -0
  23. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/tokenizer.json +3 -0
  24. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/tokenizer_config.json +2063 -0
  25. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/trainer_state.json +1646 -0
  26. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/training_args.bin +3 -0
  27. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/README.md +202 -0
  28. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/adapter_config.json +29 -0
  29. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/adapter_model.safetensors +3 -0
  30. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/optimizer.pt +3 -0
  31. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/rng_state.pth +3 -0
  32. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/scheduler.pt +3 -0
  33. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/special_tokens_map.json +17 -0
  34. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/tokenizer.json +3 -0
  35. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/tokenizer_config.json +2063 -0
  36. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/trainer_state.json +2186 -0
  37. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/training_args.bin +3 -0
  38. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/README.md +202 -0
  39. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/adapter_config.json +29 -0
  40. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/adapter_model.safetensors +3 -0
  41. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/optimizer.pt +3 -0
  42. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/rng_state.pth +3 -0
  43. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/scheduler.pt +3 -0
  44. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/special_tokens_map.json +17 -0
  45. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/tokenizer.json +3 -0
  46. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/tokenizer_config.json +2063 -0
  47. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/trainer_state.json +2726 -0
  48. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/training_args.bin +3 -0
  49. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-4548/README.md +202 -0
  50. Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-4548/adapter_config.json +29 -0
.gitattributes CHANGED
@@ -5883,3 +5883,12 @@ gemma-2b-it_int4_hellaswag-routerbench-0shot_lr-0.0002_e-8_seq-512_lora-a-32-d-0
5883
  gemma-2b-it_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-1.0-num-7029-sd-1/checkpoint-8805/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5884
  gemma-2b-it_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-1.0-num-7029-sd-1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5885
  gemma-2-9b-it_int4_medmcqa_full_con_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.8-num-102380-sd-42/checkpoint-12181/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
5883
  gemma-2b-it_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-1.0-num-7029-sd-1/checkpoint-8805/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5884
  gemma-2b-it_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-1.0-num-7029-sd-1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5885
  gemma-2-9b-it_int4_medmcqa_full_con_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.8-num-102380-sd-42/checkpoint-12181/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5886
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5887
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5888
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5889
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5890
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-4548/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5891
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-5306/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5892
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-6064/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5893
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-758/tokenizer.json filter=lfs diff=lfs merge=lfs -text
5894
+ Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.1
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8080228e091f8054a4eeac78af9455c42c732e862c553466df0eb9e5892a233c
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8080228e091f8054a4eeac78af9455c42c732e862c553466df0eb9e5892a233c
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba20c22469618b5f3eff8283728ac9b9cb3c6fcaaa73246c3c5bec24f5e6be77
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5188d8bf5a2a21f558561b800b2985bdc037935631b8c33c74c53b697abb5804
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c92af9a68ff3c98e18da78676846d498b325ebd119fdf897d319d101ac4e39
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/trainer_state.json ADDED
@@ -0,0 +1,1106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1874967813491821,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516",
4
+ "epoch": 2.0,
5
+ "eval_steps": 10,
6
+ "global_step": 1516,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.013192612137203167,
13
+ "grad_norm": 0.7545632123947144,
14
+ "learning_rate": 0.0002,
15
+ "loss": 1.9466,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.026385224274406333,
20
+ "grad_norm": 0.5787661075592041,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.4909,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0395778364116095,
27
+ "grad_norm": 0.8616093993186951,
28
+ "learning_rate": 0.0002,
29
+ "loss": 1.3906,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.052770448548812667,
34
+ "grad_norm": 0.42088547348976135,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.4116,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.06596306068601583,
41
+ "grad_norm": 0.47704678773880005,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.3446,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.079155672823219,
48
+ "grad_norm": 0.5763994455337524,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.2476,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.09234828496042216,
55
+ "grad_norm": 0.4579846262931824,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.2268,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.10554089709762533,
62
+ "grad_norm": 0.46623846888542175,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.415,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.11873350923482849,
69
+ "grad_norm": 0.4206956624984741,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.2849,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.13192612137203166,
76
+ "grad_norm": 0.41896629333496094,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.1608,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.14511873350923482,
83
+ "grad_norm": 0.3459089398384094,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.2617,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.158311345646438,
90
+ "grad_norm": 0.4587327837944031,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.2858,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.17150395778364116,
97
+ "grad_norm": 0.433525413274765,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.2241,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.18469656992084432,
104
+ "grad_norm": 0.39253175258636475,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.2269,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.19788918205804748,
111
+ "grad_norm": 0.3602290749549866,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.2224,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.21108179419525067,
118
+ "grad_norm": 0.41160839796066284,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.2834,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.22427440633245382,
125
+ "grad_norm": 0.7213630080223083,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.1986,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.23746701846965698,
132
+ "grad_norm": 0.39086055755615234,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.2215,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.25065963060686014,
139
+ "grad_norm": 0.4465520977973938,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.3315,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.2638522427440633,
146
+ "grad_norm": 1.814679741859436,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.3798,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.2770448548812665,
153
+ "grad_norm": 0.5026423931121826,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.2259,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.29023746701846964,
160
+ "grad_norm": 0.4156292974948883,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.3306,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.3034300791556728,
167
+ "grad_norm": 0.40813493728637695,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.266,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.316622691292876,
174
+ "grad_norm": 0.3304787874221802,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.1533,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.32981530343007914,
181
+ "grad_norm": 0.46139976382255554,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.3154,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.34300791556728233,
188
+ "grad_norm": 0.37518271803855896,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.1365,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.3562005277044855,
195
+ "grad_norm": 0.35586467385292053,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.2004,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.36939313984168864,
202
+ "grad_norm": 0.32441186904907227,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.2609,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.38258575197889183,
209
+ "grad_norm": 0.3198683261871338,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.212,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.39577836411609496,
216
+ "grad_norm": 0.33663108944892883,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.2465,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.40897097625329815,
223
+ "grad_norm": 0.3711244761943817,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.1702,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.42216358839050133,
230
+ "grad_norm": 0.3209651708602905,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.0871,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.43535620052770446,
237
+ "grad_norm": 0.5152716040611267,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.2728,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.44854881266490765,
244
+ "grad_norm": 0.5431376695632935,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.1833,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.46174142480211083,
251
+ "grad_norm": 0.3069997727870941,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.1344,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.47493403693931396,
258
+ "grad_norm": 0.34260064363479614,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.2742,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.48812664907651715,
265
+ "grad_norm": 0.345653235912323,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.3161,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.5013192612137203,
272
+ "grad_norm": 0.46222734451293945,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.1552,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.5145118733509235,
279
+ "grad_norm": 0.27301734685897827,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.0616,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.5277044854881267,
286
+ "grad_norm": 0.29048439860343933,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.1944,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.5408970976253298,
293
+ "grad_norm": 0.32927802205085754,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.0956,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.554089709762533,
300
+ "grad_norm": 0.3336397409439087,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.2362,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.5672823218997362,
307
+ "grad_norm": 0.4007597267627716,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.1445,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.5804749340369393,
314
+ "grad_norm": 0.36144956946372986,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.2731,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.5936675461741425,
321
+ "grad_norm": 0.6331009864807129,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.1604,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.6068601583113457,
328
+ "grad_norm": 0.41469088196754456,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.1692,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.6200527704485488,
335
+ "grad_norm": 0.4388185143470764,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.2372,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.633245382585752,
342
+ "grad_norm": 0.3738141655921936,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.2541,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.6464379947229552,
349
+ "grad_norm": 0.7212023138999939,
350
+ "learning_rate": 0.0002,
351
+ "loss": 1.1265,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.6596306068601583,
356
+ "grad_norm": 0.2972351014614105,
357
+ "learning_rate": 0.0002,
358
+ "loss": 1.2786,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.6728232189973615,
363
+ "grad_norm": 0.45293179154396057,
364
+ "learning_rate": 0.0002,
365
+ "loss": 1.1739,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.6860158311345647,
370
+ "grad_norm": 0.4319860637187958,
371
+ "learning_rate": 0.0002,
372
+ "loss": 1.255,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.6992084432717678,
377
+ "grad_norm": 0.3050215542316437,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.0959,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.712401055408971,
384
+ "grad_norm": 0.3552611172199249,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.1608,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.7255936675461742,
391
+ "grad_norm": 0.3631151020526886,
392
+ "learning_rate": 0.0002,
393
+ "loss": 1.2546,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.7387862796833773,
398
+ "grad_norm": 0.28177931904792786,
399
+ "learning_rate": 0.0002,
400
+ "loss": 1.1371,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.7519788918205804,
405
+ "grad_norm": 0.359764039516449,
406
+ "learning_rate": 0.0002,
407
+ "loss": 1.2081,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.7651715039577837,
412
+ "grad_norm": 0.3970327377319336,
413
+ "learning_rate": 0.0002,
414
+ "loss": 1.1356,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.7783641160949868,
419
+ "grad_norm": 0.3541001081466675,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.309,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.7915567282321899,
426
+ "grad_norm": 0.3478573262691498,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.2061,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.8047493403693932,
433
+ "grad_norm": 0.3900321424007416,
434
+ "learning_rate": 0.0002,
435
+ "loss": 1.1864,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.8179419525065963,
440
+ "grad_norm": 0.3443238437175751,
441
+ "learning_rate": 0.0002,
442
+ "loss": 1.1358,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.8311345646437994,
447
+ "grad_norm": 0.44238781929016113,
448
+ "learning_rate": 0.0002,
449
+ "loss": 1.3232,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.8443271767810027,
454
+ "grad_norm": 0.36339467763900757,
455
+ "learning_rate": 0.0002,
456
+ "loss": 1.1247,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.8575197889182058,
461
+ "grad_norm": 0.6243070363998413,
462
+ "learning_rate": 0.0002,
463
+ "loss": 1.1049,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.8707124010554089,
468
+ "grad_norm": 0.3209173381328583,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.1943,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.8839050131926122,
475
+ "grad_norm": 0.35017991065979004,
476
+ "learning_rate": 0.0002,
477
+ "loss": 1.1927,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.8970976253298153,
482
+ "grad_norm": 0.3247159421443939,
483
+ "learning_rate": 0.0002,
484
+ "loss": 1.1603,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.9102902374670184,
489
+ "grad_norm": 0.4091894030570984,
490
+ "learning_rate": 0.0002,
491
+ "loss": 1.2298,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.9234828496042217,
496
+ "grad_norm": 0.3975585997104645,
497
+ "learning_rate": 0.0002,
498
+ "loss": 1.2756,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.9366754617414248,
503
+ "grad_norm": 0.3666245937347412,
504
+ "learning_rate": 0.0002,
505
+ "loss": 1.281,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.9498680738786279,
510
+ "grad_norm": 0.45216917991638184,
511
+ "learning_rate": 0.0002,
512
+ "loss": 1.2855,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.9630606860158312,
517
+ "grad_norm": 0.36108118295669556,
518
+ "learning_rate": 0.0002,
519
+ "loss": 1.2217,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.9762532981530343,
524
+ "grad_norm": 0.44550251960754395,
525
+ "learning_rate": 0.0002,
526
+ "loss": 1.17,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.9894459102902374,
531
+ "grad_norm": 0.29801255464553833,
532
+ "learning_rate": 0.0002,
533
+ "loss": 1.0672,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 1.0,
538
+ "eval_loss": 1.203244686126709,
539
+ "eval_runtime": 76.0457,
540
+ "eval_samples_per_second": 5.668,
541
+ "eval_steps_per_second": 0.71,
542
+ "step": 758
543
+ },
544
+ {
545
+ "epoch": 1.0026385224274406,
546
+ "grad_norm": 0.4096551239490509,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.0748,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.0158311345646438,
553
+ "grad_norm": 0.2649582326412201,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.1537,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.029023746701847,
560
+ "grad_norm": 0.3100722134113312,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.1676,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.04221635883905,
567
+ "grad_norm": 0.3911755383014679,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.1736,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.0554089709762533,
574
+ "grad_norm": 0.4600953757762909,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.0354,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.0686015831134565,
581
+ "grad_norm": 0.28671619296073914,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.2869,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.0817941952506596,
588
+ "grad_norm": 0.47282642126083374,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.1441,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.0949868073878628,
595
+ "grad_norm": 0.690073549747467,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.1368,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.108179419525066,
602
+ "grad_norm": 0.7317902445793152,
603
+ "learning_rate": 0.0002,
604
+ "loss": 0.9944,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.121372031662269,
609
+ "grad_norm": 0.44215938448905945,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.108,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.1345646437994723,
616
+ "grad_norm": 0.33875149488449097,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.0558,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.1477572559366755,
623
+ "grad_norm": 0.3700002431869507,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.0471,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.1609498680738786,
630
+ "grad_norm": 0.41173291206359863,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.0121,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.1741424802110818,
637
+ "grad_norm": 0.5253589749336243,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.0312,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.187335092348285,
644
+ "grad_norm": 0.3912237286567688,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.2238,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.200527704485488,
651
+ "grad_norm": 0.40990331768989563,
652
+ "learning_rate": 0.0002,
653
+ "loss": 0.9434,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.2137203166226913,
658
+ "grad_norm": 0.40377968549728394,
659
+ "learning_rate": 0.0002,
660
+ "loss": 1.0493,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.2269129287598945,
665
+ "grad_norm": 0.4605846405029297,
666
+ "learning_rate": 0.0002,
667
+ "loss": 1.1496,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.2401055408970976,
672
+ "grad_norm": 0.31564897298812866,
673
+ "learning_rate": 0.0002,
674
+ "loss": 1.1173,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.2532981530343008,
679
+ "grad_norm": 0.39808550477027893,
680
+ "learning_rate": 0.0002,
681
+ "loss": 1.0547,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.266490765171504,
686
+ "grad_norm": 0.3762115240097046,
687
+ "learning_rate": 0.0002,
688
+ "loss": 1.1367,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.279683377308707,
693
+ "grad_norm": 0.4174984097480774,
694
+ "learning_rate": 0.0002,
695
+ "loss": 1.1596,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.2928759894459103,
700
+ "grad_norm": 0.5263054966926575,
701
+ "learning_rate": 0.0002,
702
+ "loss": 1.1327,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.3060686015831133,
707
+ "grad_norm": 0.41673699021339417,
708
+ "learning_rate": 0.0002,
709
+ "loss": 1.0339,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.3192612137203166,
714
+ "grad_norm": 0.9613684415817261,
715
+ "learning_rate": 0.0002,
716
+ "loss": 1.1198,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.3324538258575198,
721
+ "grad_norm": 0.3690216839313507,
722
+ "learning_rate": 0.0002,
723
+ "loss": 1.0444,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.345646437994723,
728
+ "grad_norm": 0.521821141242981,
729
+ "learning_rate": 0.0002,
730
+ "loss": 1.0473,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.358839050131926,
735
+ "grad_norm": 0.3353094160556793,
736
+ "learning_rate": 0.0002,
737
+ "loss": 1.1065,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.3720316622691293,
742
+ "grad_norm": 0.3843843936920166,
743
+ "learning_rate": 0.0002,
744
+ "loss": 1.1286,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.3852242744063323,
749
+ "grad_norm": 0.372514545917511,
750
+ "learning_rate": 0.0002,
751
+ "loss": 1.1369,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.3984168865435356,
756
+ "grad_norm": 0.34537771344184875,
757
+ "learning_rate": 0.0002,
758
+ "loss": 1.0041,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.4116094986807388,
763
+ "grad_norm": 0.45349085330963135,
764
+ "learning_rate": 0.0002,
765
+ "loss": 1.0251,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.424802110817942,
770
+ "grad_norm": 0.5120177268981934,
771
+ "learning_rate": 0.0002,
772
+ "loss": 1.1873,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.437994722955145,
777
+ "grad_norm": 0.42800238728523254,
778
+ "learning_rate": 0.0002,
779
+ "loss": 1.0872,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.4511873350923483,
784
+ "grad_norm": 0.343832790851593,
785
+ "learning_rate": 0.0002,
786
+ "loss": 1.0734,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.4643799472295513,
791
+ "grad_norm": 0.3829841911792755,
792
+ "learning_rate": 0.0002,
793
+ "loss": 1.1286,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.4775725593667546,
798
+ "grad_norm": 0.4289931058883667,
799
+ "learning_rate": 0.0002,
800
+ "loss": 1.1268,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.4907651715039578,
805
+ "grad_norm": 0.42750850319862366,
806
+ "learning_rate": 0.0002,
807
+ "loss": 1.0676,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.503957783641161,
812
+ "grad_norm": 0.34328413009643555,
813
+ "learning_rate": 0.0002,
814
+ "loss": 1.072,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.517150395778364,
819
+ "grad_norm": 0.349096417427063,
820
+ "learning_rate": 0.0002,
821
+ "loss": 1.0863,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.5303430079155673,
826
+ "grad_norm": 0.7700717449188232,
827
+ "learning_rate": 0.0002,
828
+ "loss": 1.1462,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.5435356200527703,
833
+ "grad_norm": 0.39294949173927307,
834
+ "learning_rate": 0.0002,
835
+ "loss": 0.9528,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.5567282321899736,
840
+ "grad_norm": 0.36173608899116516,
841
+ "learning_rate": 0.0002,
842
+ "loss": 1.1603,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.5699208443271768,
847
+ "grad_norm": 0.6034277677536011,
848
+ "learning_rate": 0.0002,
849
+ "loss": 1.1508,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 1.58311345646438,
854
+ "grad_norm": 0.36694103479385376,
855
+ "learning_rate": 0.0002,
856
+ "loss": 1.0105,
857
+ "step": 1200
858
+ },
859
+ {
860
+ "epoch": 1.596306068601583,
861
+ "grad_norm": 0.4727209508419037,
862
+ "learning_rate": 0.0002,
863
+ "loss": 1.1479,
864
+ "step": 1210
865
+ },
866
+ {
867
+ "epoch": 1.6094986807387863,
868
+ "grad_norm": 0.6482883095741272,
869
+ "learning_rate": 0.0002,
870
+ "loss": 1.0689,
871
+ "step": 1220
872
+ },
873
+ {
874
+ "epoch": 1.6226912928759893,
875
+ "grad_norm": 0.5238035917282104,
876
+ "learning_rate": 0.0002,
877
+ "loss": 1.1405,
878
+ "step": 1230
879
+ },
880
+ {
881
+ "epoch": 1.6358839050131926,
882
+ "grad_norm": 0.4812222421169281,
883
+ "learning_rate": 0.0002,
884
+ "loss": 1.0596,
885
+ "step": 1240
886
+ },
887
+ {
888
+ "epoch": 1.6490765171503958,
889
+ "grad_norm": 0.7131702303886414,
890
+ "learning_rate": 0.0002,
891
+ "loss": 1.2729,
892
+ "step": 1250
893
+ },
894
+ {
895
+ "epoch": 1.662269129287599,
896
+ "grad_norm": 0.3803327977657318,
897
+ "learning_rate": 0.0002,
898
+ "loss": 0.9832,
899
+ "step": 1260
900
+ },
901
+ {
902
+ "epoch": 1.675461741424802,
903
+ "grad_norm": 0.3745088577270508,
904
+ "learning_rate": 0.0002,
905
+ "loss": 1.1433,
906
+ "step": 1270
907
+ },
908
+ {
909
+ "epoch": 1.6886543535620053,
910
+ "grad_norm": 0.4427378475666046,
911
+ "learning_rate": 0.0002,
912
+ "loss": 1.1018,
913
+ "step": 1280
914
+ },
915
+ {
916
+ "epoch": 1.7018469656992083,
917
+ "grad_norm": 0.797478973865509,
918
+ "learning_rate": 0.0002,
919
+ "loss": 1.0619,
920
+ "step": 1290
921
+ },
922
+ {
923
+ "epoch": 1.7150395778364116,
924
+ "grad_norm": 0.503620982170105,
925
+ "learning_rate": 0.0002,
926
+ "loss": 1.0853,
927
+ "step": 1300
928
+ },
929
+ {
930
+ "epoch": 1.7282321899736148,
931
+ "grad_norm": 0.4132426381111145,
932
+ "learning_rate": 0.0002,
933
+ "loss": 1.1324,
934
+ "step": 1310
935
+ },
936
+ {
937
+ "epoch": 1.741424802110818,
938
+ "grad_norm": 0.41811656951904297,
939
+ "learning_rate": 0.0002,
940
+ "loss": 1.172,
941
+ "step": 1320
942
+ },
943
+ {
944
+ "epoch": 1.754617414248021,
945
+ "grad_norm": 0.40647849440574646,
946
+ "learning_rate": 0.0002,
947
+ "loss": 1.0903,
948
+ "step": 1330
949
+ },
950
+ {
951
+ "epoch": 1.767810026385224,
952
+ "grad_norm": 0.42138347029685974,
953
+ "learning_rate": 0.0002,
954
+ "loss": 1.1316,
955
+ "step": 1340
956
+ },
957
+ {
958
+ "epoch": 1.7810026385224274,
959
+ "grad_norm": 0.46523579955101013,
960
+ "learning_rate": 0.0002,
961
+ "loss": 0.9955,
962
+ "step": 1350
963
+ },
964
+ {
965
+ "epoch": 1.7941952506596306,
966
+ "grad_norm": 0.39760419726371765,
967
+ "learning_rate": 0.0002,
968
+ "loss": 1.0307,
969
+ "step": 1360
970
+ },
971
+ {
972
+ "epoch": 1.8073878627968338,
973
+ "grad_norm": 0.37993717193603516,
974
+ "learning_rate": 0.0002,
975
+ "loss": 1.1218,
976
+ "step": 1370
977
+ },
978
+ {
979
+ "epoch": 1.820580474934037,
980
+ "grad_norm": 0.5404181480407715,
981
+ "learning_rate": 0.0002,
982
+ "loss": 1.0921,
983
+ "step": 1380
984
+ },
985
+ {
986
+ "epoch": 1.83377308707124,
987
+ "grad_norm": 0.4385245740413666,
988
+ "learning_rate": 0.0002,
989
+ "loss": 1.0903,
990
+ "step": 1390
991
+ },
992
+ {
993
+ "epoch": 1.8469656992084431,
994
+ "grad_norm": 0.529797375202179,
995
+ "learning_rate": 0.0002,
996
+ "loss": 1.1175,
997
+ "step": 1400
998
+ },
999
+ {
1000
+ "epoch": 1.8601583113456464,
1001
+ "grad_norm": 0.481567919254303,
1002
+ "learning_rate": 0.0002,
1003
+ "loss": 1.0577,
1004
+ "step": 1410
1005
+ },
1006
+ {
1007
+ "epoch": 1.8733509234828496,
1008
+ "grad_norm": 0.34787362813949585,
1009
+ "learning_rate": 0.0002,
1010
+ "loss": 1.0581,
1011
+ "step": 1420
1012
+ },
1013
+ {
1014
+ "epoch": 1.8865435356200528,
1015
+ "grad_norm": 0.6402362585067749,
1016
+ "learning_rate": 0.0002,
1017
+ "loss": 1.0536,
1018
+ "step": 1430
1019
+ },
1020
+ {
1021
+ "epoch": 1.899736147757256,
1022
+ "grad_norm": 0.3461322784423828,
1023
+ "learning_rate": 0.0002,
1024
+ "loss": 1.0787,
1025
+ "step": 1440
1026
+ },
1027
+ {
1028
+ "epoch": 1.912928759894459,
1029
+ "grad_norm": 0.44005653262138367,
1030
+ "learning_rate": 0.0002,
1031
+ "loss": 1.0925,
1032
+ "step": 1450
1033
+ },
1034
+ {
1035
+ "epoch": 1.9261213720316621,
1036
+ "grad_norm": 0.4064280688762665,
1037
+ "learning_rate": 0.0002,
1038
+ "loss": 1.0414,
1039
+ "step": 1460
1040
+ },
1041
+ {
1042
+ "epoch": 1.9393139841688654,
1043
+ "grad_norm": 0.5236523151397705,
1044
+ "learning_rate": 0.0002,
1045
+ "loss": 1.0608,
1046
+ "step": 1470
1047
+ },
1048
+ {
1049
+ "epoch": 1.9525065963060686,
1050
+ "grad_norm": 0.41030219197273254,
1051
+ "learning_rate": 0.0002,
1052
+ "loss": 1.0572,
1053
+ "step": 1480
1054
+ },
1055
+ {
1056
+ "epoch": 1.9656992084432718,
1057
+ "grad_norm": 0.39805835485458374,
1058
+ "learning_rate": 0.0002,
1059
+ "loss": 1.1204,
1060
+ "step": 1490
1061
+ },
1062
+ {
1063
+ "epoch": 1.978891820580475,
1064
+ "grad_norm": 0.42974501848220825,
1065
+ "learning_rate": 0.0002,
1066
+ "loss": 1.0364,
1067
+ "step": 1500
1068
+ },
1069
+ {
1070
+ "epoch": 1.992084432717678,
1071
+ "grad_norm": 0.4688243865966797,
1072
+ "learning_rate": 0.0002,
1073
+ "loss": 1.1169,
1074
+ "step": 1510
1075
+ },
1076
+ {
1077
+ "epoch": 2.0,
1078
+ "eval_loss": 1.1874967813491821,
1079
+ "eval_runtime": 71.9523,
1080
+ "eval_samples_per_second": 5.99,
1081
+ "eval_steps_per_second": 0.75,
1082
+ "step": 1516
1083
+ }
1084
+ ],
1085
+ "logging_steps": 10,
1086
+ "max_steps": 6064,
1087
+ "num_input_tokens_seen": 0,
1088
+ "num_train_epochs": 8,
1089
+ "save_steps": 200,
1090
+ "stateful_callbacks": {
1091
+ "TrainerControl": {
1092
+ "args": {
1093
+ "should_epoch_stop": false,
1094
+ "should_evaluate": false,
1095
+ "should_log": false,
1096
+ "should_save": true,
1097
+ "should_training_stop": false
1098
+ },
1099
+ "attributes": {}
1100
+ }
1101
+ },
1102
+ "total_flos": 7.015708553851699e+16,
1103
+ "train_batch_size": 1,
1104
+ "trial_name": null,
1105
+ "trial_params": null
1106
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e04722e246164eebe6b4f70dd50fe946c936a2bd25edd75bcedcfd4c7ff9474e
3
+ size 5624
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b4d81d7256726d2a15984dbc1440edd1bf4df949ad24ff1587acdbb4f43c46e
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:554a6e8c10fe6dadea2f77aec1f22f76b2e7c08edc93a58b6d881da141caf33a
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37b989171d122b4cdd970d745ba042f12a5ab7aba4f8cb713a66da51f2fe1722
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b93f15eec18327be530ccb8601bd0dfe23cbdc7849bea310aa5348d218c0915
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/trainer_state.json ADDED
@@ -0,0 +1,1646 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1874967813491821,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516",
4
+ "epoch": 3.0,
5
+ "eval_steps": 10,
6
+ "global_step": 2274,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.013192612137203167,
13
+ "grad_norm": 0.7545632123947144,
14
+ "learning_rate": 0.0002,
15
+ "loss": 1.9466,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.026385224274406333,
20
+ "grad_norm": 0.5787661075592041,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.4909,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0395778364116095,
27
+ "grad_norm": 0.8616093993186951,
28
+ "learning_rate": 0.0002,
29
+ "loss": 1.3906,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.052770448548812667,
34
+ "grad_norm": 0.42088547348976135,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.4116,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.06596306068601583,
41
+ "grad_norm": 0.47704678773880005,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.3446,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.079155672823219,
48
+ "grad_norm": 0.5763994455337524,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.2476,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.09234828496042216,
55
+ "grad_norm": 0.4579846262931824,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.2268,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.10554089709762533,
62
+ "grad_norm": 0.46623846888542175,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.415,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.11873350923482849,
69
+ "grad_norm": 0.4206956624984741,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.2849,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.13192612137203166,
76
+ "grad_norm": 0.41896629333496094,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.1608,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.14511873350923482,
83
+ "grad_norm": 0.3459089398384094,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.2617,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.158311345646438,
90
+ "grad_norm": 0.4587327837944031,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.2858,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.17150395778364116,
97
+ "grad_norm": 0.433525413274765,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.2241,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.18469656992084432,
104
+ "grad_norm": 0.39253175258636475,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.2269,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.19788918205804748,
111
+ "grad_norm": 0.3602290749549866,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.2224,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.21108179419525067,
118
+ "grad_norm": 0.41160839796066284,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.2834,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.22427440633245382,
125
+ "grad_norm": 0.7213630080223083,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.1986,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.23746701846965698,
132
+ "grad_norm": 0.39086055755615234,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.2215,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.25065963060686014,
139
+ "grad_norm": 0.4465520977973938,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.3315,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.2638522427440633,
146
+ "grad_norm": 1.814679741859436,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.3798,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.2770448548812665,
153
+ "grad_norm": 0.5026423931121826,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.2259,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.29023746701846964,
160
+ "grad_norm": 0.4156292974948883,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.3306,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.3034300791556728,
167
+ "grad_norm": 0.40813493728637695,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.266,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.316622691292876,
174
+ "grad_norm": 0.3304787874221802,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.1533,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.32981530343007914,
181
+ "grad_norm": 0.46139976382255554,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.3154,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.34300791556728233,
188
+ "grad_norm": 0.37518271803855896,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.1365,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.3562005277044855,
195
+ "grad_norm": 0.35586467385292053,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.2004,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.36939313984168864,
202
+ "grad_norm": 0.32441186904907227,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.2609,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.38258575197889183,
209
+ "grad_norm": 0.3198683261871338,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.212,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.39577836411609496,
216
+ "grad_norm": 0.33663108944892883,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.2465,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.40897097625329815,
223
+ "grad_norm": 0.3711244761943817,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.1702,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.42216358839050133,
230
+ "grad_norm": 0.3209651708602905,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.0871,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.43535620052770446,
237
+ "grad_norm": 0.5152716040611267,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.2728,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.44854881266490765,
244
+ "grad_norm": 0.5431376695632935,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.1833,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.46174142480211083,
251
+ "grad_norm": 0.3069997727870941,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.1344,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.47493403693931396,
258
+ "grad_norm": 0.34260064363479614,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.2742,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.48812664907651715,
265
+ "grad_norm": 0.345653235912323,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.3161,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.5013192612137203,
272
+ "grad_norm": 0.46222734451293945,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.1552,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.5145118733509235,
279
+ "grad_norm": 0.27301734685897827,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.0616,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.5277044854881267,
286
+ "grad_norm": 0.29048439860343933,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.1944,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.5408970976253298,
293
+ "grad_norm": 0.32927802205085754,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.0956,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.554089709762533,
300
+ "grad_norm": 0.3336397409439087,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.2362,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.5672823218997362,
307
+ "grad_norm": 0.4007597267627716,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.1445,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.5804749340369393,
314
+ "grad_norm": 0.36144956946372986,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.2731,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.5936675461741425,
321
+ "grad_norm": 0.6331009864807129,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.1604,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.6068601583113457,
328
+ "grad_norm": 0.41469088196754456,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.1692,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.6200527704485488,
335
+ "grad_norm": 0.4388185143470764,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.2372,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.633245382585752,
342
+ "grad_norm": 0.3738141655921936,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.2541,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.6464379947229552,
349
+ "grad_norm": 0.7212023138999939,
350
+ "learning_rate": 0.0002,
351
+ "loss": 1.1265,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.6596306068601583,
356
+ "grad_norm": 0.2972351014614105,
357
+ "learning_rate": 0.0002,
358
+ "loss": 1.2786,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.6728232189973615,
363
+ "grad_norm": 0.45293179154396057,
364
+ "learning_rate": 0.0002,
365
+ "loss": 1.1739,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.6860158311345647,
370
+ "grad_norm": 0.4319860637187958,
371
+ "learning_rate": 0.0002,
372
+ "loss": 1.255,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.6992084432717678,
377
+ "grad_norm": 0.3050215542316437,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.0959,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.712401055408971,
384
+ "grad_norm": 0.3552611172199249,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.1608,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.7255936675461742,
391
+ "grad_norm": 0.3631151020526886,
392
+ "learning_rate": 0.0002,
393
+ "loss": 1.2546,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.7387862796833773,
398
+ "grad_norm": 0.28177931904792786,
399
+ "learning_rate": 0.0002,
400
+ "loss": 1.1371,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.7519788918205804,
405
+ "grad_norm": 0.359764039516449,
406
+ "learning_rate": 0.0002,
407
+ "loss": 1.2081,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.7651715039577837,
412
+ "grad_norm": 0.3970327377319336,
413
+ "learning_rate": 0.0002,
414
+ "loss": 1.1356,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.7783641160949868,
419
+ "grad_norm": 0.3541001081466675,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.309,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.7915567282321899,
426
+ "grad_norm": 0.3478573262691498,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.2061,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.8047493403693932,
433
+ "grad_norm": 0.3900321424007416,
434
+ "learning_rate": 0.0002,
435
+ "loss": 1.1864,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.8179419525065963,
440
+ "grad_norm": 0.3443238437175751,
441
+ "learning_rate": 0.0002,
442
+ "loss": 1.1358,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.8311345646437994,
447
+ "grad_norm": 0.44238781929016113,
448
+ "learning_rate": 0.0002,
449
+ "loss": 1.3232,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.8443271767810027,
454
+ "grad_norm": 0.36339467763900757,
455
+ "learning_rate": 0.0002,
456
+ "loss": 1.1247,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.8575197889182058,
461
+ "grad_norm": 0.6243070363998413,
462
+ "learning_rate": 0.0002,
463
+ "loss": 1.1049,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.8707124010554089,
468
+ "grad_norm": 0.3209173381328583,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.1943,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.8839050131926122,
475
+ "grad_norm": 0.35017991065979004,
476
+ "learning_rate": 0.0002,
477
+ "loss": 1.1927,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.8970976253298153,
482
+ "grad_norm": 0.3247159421443939,
483
+ "learning_rate": 0.0002,
484
+ "loss": 1.1603,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.9102902374670184,
489
+ "grad_norm": 0.4091894030570984,
490
+ "learning_rate": 0.0002,
491
+ "loss": 1.2298,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.9234828496042217,
496
+ "grad_norm": 0.3975585997104645,
497
+ "learning_rate": 0.0002,
498
+ "loss": 1.2756,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.9366754617414248,
503
+ "grad_norm": 0.3666245937347412,
504
+ "learning_rate": 0.0002,
505
+ "loss": 1.281,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.9498680738786279,
510
+ "grad_norm": 0.45216917991638184,
511
+ "learning_rate": 0.0002,
512
+ "loss": 1.2855,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.9630606860158312,
517
+ "grad_norm": 0.36108118295669556,
518
+ "learning_rate": 0.0002,
519
+ "loss": 1.2217,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.9762532981530343,
524
+ "grad_norm": 0.44550251960754395,
525
+ "learning_rate": 0.0002,
526
+ "loss": 1.17,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.9894459102902374,
531
+ "grad_norm": 0.29801255464553833,
532
+ "learning_rate": 0.0002,
533
+ "loss": 1.0672,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 1.0,
538
+ "eval_loss": 1.203244686126709,
539
+ "eval_runtime": 76.0457,
540
+ "eval_samples_per_second": 5.668,
541
+ "eval_steps_per_second": 0.71,
542
+ "step": 758
543
+ },
544
+ {
545
+ "epoch": 1.0026385224274406,
546
+ "grad_norm": 0.4096551239490509,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.0748,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.0158311345646438,
553
+ "grad_norm": 0.2649582326412201,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.1537,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.029023746701847,
560
+ "grad_norm": 0.3100722134113312,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.1676,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.04221635883905,
567
+ "grad_norm": 0.3911755383014679,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.1736,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.0554089709762533,
574
+ "grad_norm": 0.4600953757762909,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.0354,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.0686015831134565,
581
+ "grad_norm": 0.28671619296073914,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.2869,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.0817941952506596,
588
+ "grad_norm": 0.47282642126083374,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.1441,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.0949868073878628,
595
+ "grad_norm": 0.690073549747467,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.1368,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.108179419525066,
602
+ "grad_norm": 0.7317902445793152,
603
+ "learning_rate": 0.0002,
604
+ "loss": 0.9944,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.121372031662269,
609
+ "grad_norm": 0.44215938448905945,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.108,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.1345646437994723,
616
+ "grad_norm": 0.33875149488449097,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.0558,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.1477572559366755,
623
+ "grad_norm": 0.3700002431869507,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.0471,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.1609498680738786,
630
+ "grad_norm": 0.41173291206359863,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.0121,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.1741424802110818,
637
+ "grad_norm": 0.5253589749336243,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.0312,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.187335092348285,
644
+ "grad_norm": 0.3912237286567688,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.2238,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.200527704485488,
651
+ "grad_norm": 0.40990331768989563,
652
+ "learning_rate": 0.0002,
653
+ "loss": 0.9434,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.2137203166226913,
658
+ "grad_norm": 0.40377968549728394,
659
+ "learning_rate": 0.0002,
660
+ "loss": 1.0493,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.2269129287598945,
665
+ "grad_norm": 0.4605846405029297,
666
+ "learning_rate": 0.0002,
667
+ "loss": 1.1496,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.2401055408970976,
672
+ "grad_norm": 0.31564897298812866,
673
+ "learning_rate": 0.0002,
674
+ "loss": 1.1173,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.2532981530343008,
679
+ "grad_norm": 0.39808550477027893,
680
+ "learning_rate": 0.0002,
681
+ "loss": 1.0547,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.266490765171504,
686
+ "grad_norm": 0.3762115240097046,
687
+ "learning_rate": 0.0002,
688
+ "loss": 1.1367,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.279683377308707,
693
+ "grad_norm": 0.4174984097480774,
694
+ "learning_rate": 0.0002,
695
+ "loss": 1.1596,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.2928759894459103,
700
+ "grad_norm": 0.5263054966926575,
701
+ "learning_rate": 0.0002,
702
+ "loss": 1.1327,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.3060686015831133,
707
+ "grad_norm": 0.41673699021339417,
708
+ "learning_rate": 0.0002,
709
+ "loss": 1.0339,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.3192612137203166,
714
+ "grad_norm": 0.9613684415817261,
715
+ "learning_rate": 0.0002,
716
+ "loss": 1.1198,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.3324538258575198,
721
+ "grad_norm": 0.3690216839313507,
722
+ "learning_rate": 0.0002,
723
+ "loss": 1.0444,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.345646437994723,
728
+ "grad_norm": 0.521821141242981,
729
+ "learning_rate": 0.0002,
730
+ "loss": 1.0473,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.358839050131926,
735
+ "grad_norm": 0.3353094160556793,
736
+ "learning_rate": 0.0002,
737
+ "loss": 1.1065,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.3720316622691293,
742
+ "grad_norm": 0.3843843936920166,
743
+ "learning_rate": 0.0002,
744
+ "loss": 1.1286,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.3852242744063323,
749
+ "grad_norm": 0.372514545917511,
750
+ "learning_rate": 0.0002,
751
+ "loss": 1.1369,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.3984168865435356,
756
+ "grad_norm": 0.34537771344184875,
757
+ "learning_rate": 0.0002,
758
+ "loss": 1.0041,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.4116094986807388,
763
+ "grad_norm": 0.45349085330963135,
764
+ "learning_rate": 0.0002,
765
+ "loss": 1.0251,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.424802110817942,
770
+ "grad_norm": 0.5120177268981934,
771
+ "learning_rate": 0.0002,
772
+ "loss": 1.1873,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.437994722955145,
777
+ "grad_norm": 0.42800238728523254,
778
+ "learning_rate": 0.0002,
779
+ "loss": 1.0872,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.4511873350923483,
784
+ "grad_norm": 0.343832790851593,
785
+ "learning_rate": 0.0002,
786
+ "loss": 1.0734,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.4643799472295513,
791
+ "grad_norm": 0.3829841911792755,
792
+ "learning_rate": 0.0002,
793
+ "loss": 1.1286,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.4775725593667546,
798
+ "grad_norm": 0.4289931058883667,
799
+ "learning_rate": 0.0002,
800
+ "loss": 1.1268,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.4907651715039578,
805
+ "grad_norm": 0.42750850319862366,
806
+ "learning_rate": 0.0002,
807
+ "loss": 1.0676,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.503957783641161,
812
+ "grad_norm": 0.34328413009643555,
813
+ "learning_rate": 0.0002,
814
+ "loss": 1.072,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.517150395778364,
819
+ "grad_norm": 0.349096417427063,
820
+ "learning_rate": 0.0002,
821
+ "loss": 1.0863,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.5303430079155673,
826
+ "grad_norm": 0.7700717449188232,
827
+ "learning_rate": 0.0002,
828
+ "loss": 1.1462,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.5435356200527703,
833
+ "grad_norm": 0.39294949173927307,
834
+ "learning_rate": 0.0002,
835
+ "loss": 0.9528,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.5567282321899736,
840
+ "grad_norm": 0.36173608899116516,
841
+ "learning_rate": 0.0002,
842
+ "loss": 1.1603,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.5699208443271768,
847
+ "grad_norm": 0.6034277677536011,
848
+ "learning_rate": 0.0002,
849
+ "loss": 1.1508,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 1.58311345646438,
854
+ "grad_norm": 0.36694103479385376,
855
+ "learning_rate": 0.0002,
856
+ "loss": 1.0105,
857
+ "step": 1200
858
+ },
859
+ {
860
+ "epoch": 1.596306068601583,
861
+ "grad_norm": 0.4727209508419037,
862
+ "learning_rate": 0.0002,
863
+ "loss": 1.1479,
864
+ "step": 1210
865
+ },
866
+ {
867
+ "epoch": 1.6094986807387863,
868
+ "grad_norm": 0.6482883095741272,
869
+ "learning_rate": 0.0002,
870
+ "loss": 1.0689,
871
+ "step": 1220
872
+ },
873
+ {
874
+ "epoch": 1.6226912928759893,
875
+ "grad_norm": 0.5238035917282104,
876
+ "learning_rate": 0.0002,
877
+ "loss": 1.1405,
878
+ "step": 1230
879
+ },
880
+ {
881
+ "epoch": 1.6358839050131926,
882
+ "grad_norm": 0.4812222421169281,
883
+ "learning_rate": 0.0002,
884
+ "loss": 1.0596,
885
+ "step": 1240
886
+ },
887
+ {
888
+ "epoch": 1.6490765171503958,
889
+ "grad_norm": 0.7131702303886414,
890
+ "learning_rate": 0.0002,
891
+ "loss": 1.2729,
892
+ "step": 1250
893
+ },
894
+ {
895
+ "epoch": 1.662269129287599,
896
+ "grad_norm": 0.3803327977657318,
897
+ "learning_rate": 0.0002,
898
+ "loss": 0.9832,
899
+ "step": 1260
900
+ },
901
+ {
902
+ "epoch": 1.675461741424802,
903
+ "grad_norm": 0.3745088577270508,
904
+ "learning_rate": 0.0002,
905
+ "loss": 1.1433,
906
+ "step": 1270
907
+ },
908
+ {
909
+ "epoch": 1.6886543535620053,
910
+ "grad_norm": 0.4427378475666046,
911
+ "learning_rate": 0.0002,
912
+ "loss": 1.1018,
913
+ "step": 1280
914
+ },
915
+ {
916
+ "epoch": 1.7018469656992083,
917
+ "grad_norm": 0.797478973865509,
918
+ "learning_rate": 0.0002,
919
+ "loss": 1.0619,
920
+ "step": 1290
921
+ },
922
+ {
923
+ "epoch": 1.7150395778364116,
924
+ "grad_norm": 0.503620982170105,
925
+ "learning_rate": 0.0002,
926
+ "loss": 1.0853,
927
+ "step": 1300
928
+ },
929
+ {
930
+ "epoch": 1.7282321899736148,
931
+ "grad_norm": 0.4132426381111145,
932
+ "learning_rate": 0.0002,
933
+ "loss": 1.1324,
934
+ "step": 1310
935
+ },
936
+ {
937
+ "epoch": 1.741424802110818,
938
+ "grad_norm": 0.41811656951904297,
939
+ "learning_rate": 0.0002,
940
+ "loss": 1.172,
941
+ "step": 1320
942
+ },
943
+ {
944
+ "epoch": 1.754617414248021,
945
+ "grad_norm": 0.40647849440574646,
946
+ "learning_rate": 0.0002,
947
+ "loss": 1.0903,
948
+ "step": 1330
949
+ },
950
+ {
951
+ "epoch": 1.767810026385224,
952
+ "grad_norm": 0.42138347029685974,
953
+ "learning_rate": 0.0002,
954
+ "loss": 1.1316,
955
+ "step": 1340
956
+ },
957
+ {
958
+ "epoch": 1.7810026385224274,
959
+ "grad_norm": 0.46523579955101013,
960
+ "learning_rate": 0.0002,
961
+ "loss": 0.9955,
962
+ "step": 1350
963
+ },
964
+ {
965
+ "epoch": 1.7941952506596306,
966
+ "grad_norm": 0.39760419726371765,
967
+ "learning_rate": 0.0002,
968
+ "loss": 1.0307,
969
+ "step": 1360
970
+ },
971
+ {
972
+ "epoch": 1.8073878627968338,
973
+ "grad_norm": 0.37993717193603516,
974
+ "learning_rate": 0.0002,
975
+ "loss": 1.1218,
976
+ "step": 1370
977
+ },
978
+ {
979
+ "epoch": 1.820580474934037,
980
+ "grad_norm": 0.5404181480407715,
981
+ "learning_rate": 0.0002,
982
+ "loss": 1.0921,
983
+ "step": 1380
984
+ },
985
+ {
986
+ "epoch": 1.83377308707124,
987
+ "grad_norm": 0.4385245740413666,
988
+ "learning_rate": 0.0002,
989
+ "loss": 1.0903,
990
+ "step": 1390
991
+ },
992
+ {
993
+ "epoch": 1.8469656992084431,
994
+ "grad_norm": 0.529797375202179,
995
+ "learning_rate": 0.0002,
996
+ "loss": 1.1175,
997
+ "step": 1400
998
+ },
999
+ {
1000
+ "epoch": 1.8601583113456464,
1001
+ "grad_norm": 0.481567919254303,
1002
+ "learning_rate": 0.0002,
1003
+ "loss": 1.0577,
1004
+ "step": 1410
1005
+ },
1006
+ {
1007
+ "epoch": 1.8733509234828496,
1008
+ "grad_norm": 0.34787362813949585,
1009
+ "learning_rate": 0.0002,
1010
+ "loss": 1.0581,
1011
+ "step": 1420
1012
+ },
1013
+ {
1014
+ "epoch": 1.8865435356200528,
1015
+ "grad_norm": 0.6402362585067749,
1016
+ "learning_rate": 0.0002,
1017
+ "loss": 1.0536,
1018
+ "step": 1430
1019
+ },
1020
+ {
1021
+ "epoch": 1.899736147757256,
1022
+ "grad_norm": 0.3461322784423828,
1023
+ "learning_rate": 0.0002,
1024
+ "loss": 1.0787,
1025
+ "step": 1440
1026
+ },
1027
+ {
1028
+ "epoch": 1.912928759894459,
1029
+ "grad_norm": 0.44005653262138367,
1030
+ "learning_rate": 0.0002,
1031
+ "loss": 1.0925,
1032
+ "step": 1450
1033
+ },
1034
+ {
1035
+ "epoch": 1.9261213720316621,
1036
+ "grad_norm": 0.4064280688762665,
1037
+ "learning_rate": 0.0002,
1038
+ "loss": 1.0414,
1039
+ "step": 1460
1040
+ },
1041
+ {
1042
+ "epoch": 1.9393139841688654,
1043
+ "grad_norm": 0.5236523151397705,
1044
+ "learning_rate": 0.0002,
1045
+ "loss": 1.0608,
1046
+ "step": 1470
1047
+ },
1048
+ {
1049
+ "epoch": 1.9525065963060686,
1050
+ "grad_norm": 0.41030219197273254,
1051
+ "learning_rate": 0.0002,
1052
+ "loss": 1.0572,
1053
+ "step": 1480
1054
+ },
1055
+ {
1056
+ "epoch": 1.9656992084432718,
1057
+ "grad_norm": 0.39805835485458374,
1058
+ "learning_rate": 0.0002,
1059
+ "loss": 1.1204,
1060
+ "step": 1490
1061
+ },
1062
+ {
1063
+ "epoch": 1.978891820580475,
1064
+ "grad_norm": 0.42974501848220825,
1065
+ "learning_rate": 0.0002,
1066
+ "loss": 1.0364,
1067
+ "step": 1500
1068
+ },
1069
+ {
1070
+ "epoch": 1.992084432717678,
1071
+ "grad_norm": 0.4688243865966797,
1072
+ "learning_rate": 0.0002,
1073
+ "loss": 1.1169,
1074
+ "step": 1510
1075
+ },
1076
+ {
1077
+ "epoch": 2.0,
1078
+ "eval_loss": 1.1874967813491821,
1079
+ "eval_runtime": 71.9523,
1080
+ "eval_samples_per_second": 5.99,
1081
+ "eval_steps_per_second": 0.75,
1082
+ "step": 1516
1083
+ },
1084
+ {
1085
+ "epoch": 2.005277044854881,
1086
+ "grad_norm": 0.4121631383895874,
1087
+ "learning_rate": 0.0002,
1088
+ "loss": 1.0401,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.0184696569920844,
1093
+ "grad_norm": 0.4844197928905487,
1094
+ "learning_rate": 0.0002,
1095
+ "loss": 0.9384,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.0316622691292876,
1100
+ "grad_norm": 0.45408546924591064,
1101
+ "learning_rate": 0.0002,
1102
+ "loss": 0.8686,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.044854881266491,
1107
+ "grad_norm": 0.48662951588630676,
1108
+ "learning_rate": 0.0002,
1109
+ "loss": 1.0399,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.058047493403694,
1114
+ "grad_norm": 0.7195899486541748,
1115
+ "learning_rate": 0.0002,
1116
+ "loss": 0.936,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.0712401055408973,
1121
+ "grad_norm": 0.5071077346801758,
1122
+ "learning_rate": 0.0002,
1123
+ "loss": 0.9486,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.0844327176781,
1128
+ "grad_norm": 0.7473958730697632,
1129
+ "learning_rate": 0.0002,
1130
+ "loss": 1.0055,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.0976253298153034,
1135
+ "grad_norm": 0.5509232878684998,
1136
+ "learning_rate": 0.0002,
1137
+ "loss": 0.8309,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.1108179419525066,
1142
+ "grad_norm": 0.5108042359352112,
1143
+ "learning_rate": 0.0002,
1144
+ "loss": 0.9181,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.12401055408971,
1149
+ "grad_norm": 0.42331448197364807,
1150
+ "learning_rate": 0.0002,
1151
+ "loss": 0.9499,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.137203166226913,
1156
+ "grad_norm": 0.46621623635292053,
1157
+ "learning_rate": 0.0002,
1158
+ "loss": 0.9359,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.150395778364116,
1163
+ "grad_norm": 0.43802836537361145,
1164
+ "learning_rate": 0.0002,
1165
+ "loss": 0.9065,
1166
+ "step": 1630
1167
+ },
1168
+ {
1169
+ "epoch": 2.163588390501319,
1170
+ "grad_norm": 0.49908021092414856,
1171
+ "learning_rate": 0.0002,
1172
+ "loss": 0.9375,
1173
+ "step": 1640
1174
+ },
1175
+ {
1176
+ "epoch": 2.1767810026385224,
1177
+ "grad_norm": 0.4195636808872223,
1178
+ "learning_rate": 0.0002,
1179
+ "loss": 1.0389,
1180
+ "step": 1650
1181
+ },
1182
+ {
1183
+ "epoch": 2.1899736147757256,
1184
+ "grad_norm": 0.49515822529792786,
1185
+ "learning_rate": 0.0002,
1186
+ "loss": 0.8501,
1187
+ "step": 1660
1188
+ },
1189
+ {
1190
+ "epoch": 2.203166226912929,
1191
+ "grad_norm": 0.4607589542865753,
1192
+ "learning_rate": 0.0002,
1193
+ "loss": 1.0557,
1194
+ "step": 1670
1195
+ },
1196
+ {
1197
+ "epoch": 2.216358839050132,
1198
+ "grad_norm": 0.4489196836948395,
1199
+ "learning_rate": 0.0002,
1200
+ "loss": 1.0206,
1201
+ "step": 1680
1202
+ },
1203
+ {
1204
+ "epoch": 2.229551451187335,
1205
+ "grad_norm": 0.49300864338874817,
1206
+ "learning_rate": 0.0002,
1207
+ "loss": 0.9657,
1208
+ "step": 1690
1209
+ },
1210
+ {
1211
+ "epoch": 2.242744063324538,
1212
+ "grad_norm": 0.6624954342842102,
1213
+ "learning_rate": 0.0002,
1214
+ "loss": 0.8371,
1215
+ "step": 1700
1216
+ },
1217
+ {
1218
+ "epoch": 2.2559366754617414,
1219
+ "grad_norm": 0.8391500115394592,
1220
+ "learning_rate": 0.0002,
1221
+ "loss": 0.8555,
1222
+ "step": 1710
1223
+ },
1224
+ {
1225
+ "epoch": 2.2691292875989446,
1226
+ "grad_norm": 0.5193073749542236,
1227
+ "learning_rate": 0.0002,
1228
+ "loss": 1.0113,
1229
+ "step": 1720
1230
+ },
1231
+ {
1232
+ "epoch": 2.282321899736148,
1233
+ "grad_norm": 0.6180613040924072,
1234
+ "learning_rate": 0.0002,
1235
+ "loss": 0.9979,
1236
+ "step": 1730
1237
+ },
1238
+ {
1239
+ "epoch": 2.295514511873351,
1240
+ "grad_norm": 0.591191291809082,
1241
+ "learning_rate": 0.0002,
1242
+ "loss": 0.9579,
1243
+ "step": 1740
1244
+ },
1245
+ {
1246
+ "epoch": 2.308707124010554,
1247
+ "grad_norm": 0.546897828578949,
1248
+ "learning_rate": 0.0002,
1249
+ "loss": 0.8879,
1250
+ "step": 1750
1251
+ },
1252
+ {
1253
+ "epoch": 2.321899736147757,
1254
+ "grad_norm": 0.5470401644706726,
1255
+ "learning_rate": 0.0002,
1256
+ "loss": 0.9321,
1257
+ "step": 1760
1258
+ },
1259
+ {
1260
+ "epoch": 2.3350923482849604,
1261
+ "grad_norm": 0.4590282738208771,
1262
+ "learning_rate": 0.0002,
1263
+ "loss": 0.9104,
1264
+ "step": 1770
1265
+ },
1266
+ {
1267
+ "epoch": 2.3482849604221636,
1268
+ "grad_norm": 0.622164785861969,
1269
+ "learning_rate": 0.0002,
1270
+ "loss": 1.0384,
1271
+ "step": 1780
1272
+ },
1273
+ {
1274
+ "epoch": 2.361477572559367,
1275
+ "grad_norm": 0.5753812193870544,
1276
+ "learning_rate": 0.0002,
1277
+ "loss": 1.0297,
1278
+ "step": 1790
1279
+ },
1280
+ {
1281
+ "epoch": 2.37467018469657,
1282
+ "grad_norm": 0.47958624362945557,
1283
+ "learning_rate": 0.0002,
1284
+ "loss": 0.9569,
1285
+ "step": 1800
1286
+ },
1287
+ {
1288
+ "epoch": 2.387862796833773,
1289
+ "grad_norm": 0.48042672872543335,
1290
+ "learning_rate": 0.0002,
1291
+ "loss": 1.0519,
1292
+ "step": 1810
1293
+ },
1294
+ {
1295
+ "epoch": 2.401055408970976,
1296
+ "grad_norm": 0.44586366415023804,
1297
+ "learning_rate": 0.0002,
1298
+ "loss": 0.9042,
1299
+ "step": 1820
1300
+ },
1301
+ {
1302
+ "epoch": 2.4142480211081794,
1303
+ "grad_norm": 0.7239416837692261,
1304
+ "learning_rate": 0.0002,
1305
+ "loss": 0.9783,
1306
+ "step": 1830
1307
+ },
1308
+ {
1309
+ "epoch": 2.4274406332453826,
1310
+ "grad_norm": 0.5515341758728027,
1311
+ "learning_rate": 0.0002,
1312
+ "loss": 0.8818,
1313
+ "step": 1840
1314
+ },
1315
+ {
1316
+ "epoch": 2.440633245382586,
1317
+ "grad_norm": 0.6280064582824707,
1318
+ "learning_rate": 0.0002,
1319
+ "loss": 0.9503,
1320
+ "step": 1850
1321
+ },
1322
+ {
1323
+ "epoch": 2.453825857519789,
1324
+ "grad_norm": 0.4832057058811188,
1325
+ "learning_rate": 0.0002,
1326
+ "loss": 0.8943,
1327
+ "step": 1860
1328
+ },
1329
+ {
1330
+ "epoch": 2.467018469656992,
1331
+ "grad_norm": 0.5789321064949036,
1332
+ "learning_rate": 0.0002,
1333
+ "loss": 0.8744,
1334
+ "step": 1870
1335
+ },
1336
+ {
1337
+ "epoch": 2.480211081794195,
1338
+ "grad_norm": 0.48491886258125305,
1339
+ "learning_rate": 0.0002,
1340
+ "loss": 0.9332,
1341
+ "step": 1880
1342
+ },
1343
+ {
1344
+ "epoch": 2.4934036939313984,
1345
+ "grad_norm": 0.532365620136261,
1346
+ "learning_rate": 0.0002,
1347
+ "loss": 0.943,
1348
+ "step": 1890
1349
+ },
1350
+ {
1351
+ "epoch": 2.5065963060686016,
1352
+ "grad_norm": 0.7087852954864502,
1353
+ "learning_rate": 0.0002,
1354
+ "loss": 0.9734,
1355
+ "step": 1900
1356
+ },
1357
+ {
1358
+ "epoch": 2.519788918205805,
1359
+ "grad_norm": 0.48157402873039246,
1360
+ "learning_rate": 0.0002,
1361
+ "loss": 0.9767,
1362
+ "step": 1910
1363
+ },
1364
+ {
1365
+ "epoch": 2.532981530343008,
1366
+ "grad_norm": 0.5886041522026062,
1367
+ "learning_rate": 0.0002,
1368
+ "loss": 0.9851,
1369
+ "step": 1920
1370
+ },
1371
+ {
1372
+ "epoch": 2.5461741424802113,
1373
+ "grad_norm": 0.6332622766494751,
1374
+ "learning_rate": 0.0002,
1375
+ "loss": 1.0144,
1376
+ "step": 1930
1377
+ },
1378
+ {
1379
+ "epoch": 2.559366754617414,
1380
+ "grad_norm": 0.5463117957115173,
1381
+ "learning_rate": 0.0002,
1382
+ "loss": 0.9516,
1383
+ "step": 1940
1384
+ },
1385
+ {
1386
+ "epoch": 2.5725593667546174,
1387
+ "grad_norm": 0.5432228446006775,
1388
+ "learning_rate": 0.0002,
1389
+ "loss": 0.9373,
1390
+ "step": 1950
1391
+ },
1392
+ {
1393
+ "epoch": 2.5857519788918206,
1394
+ "grad_norm": 0.5929186940193176,
1395
+ "learning_rate": 0.0002,
1396
+ "loss": 0.8974,
1397
+ "step": 1960
1398
+ },
1399
+ {
1400
+ "epoch": 2.598944591029024,
1401
+ "grad_norm": 0.5120641589164734,
1402
+ "learning_rate": 0.0002,
1403
+ "loss": 1.0062,
1404
+ "step": 1970
1405
+ },
1406
+ {
1407
+ "epoch": 2.6121372031662267,
1408
+ "grad_norm": 0.5372339487075806,
1409
+ "learning_rate": 0.0002,
1410
+ "loss": 0.9143,
1411
+ "step": 1980
1412
+ },
1413
+ {
1414
+ "epoch": 2.62532981530343,
1415
+ "grad_norm": 0.5519838929176331,
1416
+ "learning_rate": 0.0002,
1417
+ "loss": 1.0786,
1418
+ "step": 1990
1419
+ },
1420
+ {
1421
+ "epoch": 2.638522427440633,
1422
+ "grad_norm": 0.7304037809371948,
1423
+ "learning_rate": 0.0002,
1424
+ "loss": 1.021,
1425
+ "step": 2000
1426
+ },
1427
+ {
1428
+ "epoch": 2.6517150395778364,
1429
+ "grad_norm": 0.6182340979576111,
1430
+ "learning_rate": 0.0002,
1431
+ "loss": 0.8708,
1432
+ "step": 2010
1433
+ },
1434
+ {
1435
+ "epoch": 2.6649076517150396,
1436
+ "grad_norm": 0.4874444305896759,
1437
+ "learning_rate": 0.0002,
1438
+ "loss": 1.0501,
1439
+ "step": 2020
1440
+ },
1441
+ {
1442
+ "epoch": 2.678100263852243,
1443
+ "grad_norm": 0.5850239396095276,
1444
+ "learning_rate": 0.0002,
1445
+ "loss": 0.9612,
1446
+ "step": 2030
1447
+ },
1448
+ {
1449
+ "epoch": 2.691292875989446,
1450
+ "grad_norm": 0.6495311856269836,
1451
+ "learning_rate": 0.0002,
1452
+ "loss": 0.9808,
1453
+ "step": 2040
1454
+ },
1455
+ {
1456
+ "epoch": 2.7044854881266494,
1457
+ "grad_norm": 1.002830147743225,
1458
+ "learning_rate": 0.0002,
1459
+ "loss": 1.0187,
1460
+ "step": 2050
1461
+ },
1462
+ {
1463
+ "epoch": 2.717678100263852,
1464
+ "grad_norm": 0.49076753854751587,
1465
+ "learning_rate": 0.0002,
1466
+ "loss": 1.0386,
1467
+ "step": 2060
1468
+ },
1469
+ {
1470
+ "epoch": 2.7308707124010554,
1471
+ "grad_norm": 0.4736326336860657,
1472
+ "learning_rate": 0.0002,
1473
+ "loss": 0.9416,
1474
+ "step": 2070
1475
+ },
1476
+ {
1477
+ "epoch": 2.7440633245382586,
1478
+ "grad_norm": 0.5527601838111877,
1479
+ "learning_rate": 0.0002,
1480
+ "loss": 0.8424,
1481
+ "step": 2080
1482
+ },
1483
+ {
1484
+ "epoch": 2.757255936675462,
1485
+ "grad_norm": 0.7295718193054199,
1486
+ "learning_rate": 0.0002,
1487
+ "loss": 0.9149,
1488
+ "step": 2090
1489
+ },
1490
+ {
1491
+ "epoch": 2.7704485488126647,
1492
+ "grad_norm": 0.5437536835670471,
1493
+ "learning_rate": 0.0002,
1494
+ "loss": 0.9032,
1495
+ "step": 2100
1496
+ },
1497
+ {
1498
+ "epoch": 2.783641160949868,
1499
+ "grad_norm": 0.5997128486633301,
1500
+ "learning_rate": 0.0002,
1501
+ "loss": 0.8254,
1502
+ "step": 2110
1503
+ },
1504
+ {
1505
+ "epoch": 2.796833773087071,
1506
+ "grad_norm": 0.6498191356658936,
1507
+ "learning_rate": 0.0002,
1508
+ "loss": 0.976,
1509
+ "step": 2120
1510
+ },
1511
+ {
1512
+ "epoch": 2.8100263852242744,
1513
+ "grad_norm": 0.5237268805503845,
1514
+ "learning_rate": 0.0002,
1515
+ "loss": 0.9543,
1516
+ "step": 2130
1517
+ },
1518
+ {
1519
+ "epoch": 2.8232189973614776,
1520
+ "grad_norm": 0.6033027172088623,
1521
+ "learning_rate": 0.0002,
1522
+ "loss": 0.9302,
1523
+ "step": 2140
1524
+ },
1525
+ {
1526
+ "epoch": 2.836411609498681,
1527
+ "grad_norm": 0.6077138781547546,
1528
+ "learning_rate": 0.0002,
1529
+ "loss": 0.9625,
1530
+ "step": 2150
1531
+ },
1532
+ {
1533
+ "epoch": 2.849604221635884,
1534
+ "grad_norm": 0.4127797484397888,
1535
+ "learning_rate": 0.0002,
1536
+ "loss": 0.9347,
1537
+ "step": 2160
1538
+ },
1539
+ {
1540
+ "epoch": 2.862796833773087,
1541
+ "grad_norm": 0.8448635339736938,
1542
+ "learning_rate": 0.0002,
1543
+ "loss": 1.0459,
1544
+ "step": 2170
1545
+ },
1546
+ {
1547
+ "epoch": 2.87598944591029,
1548
+ "grad_norm": 0.5669729113578796,
1549
+ "learning_rate": 0.0002,
1550
+ "loss": 0.8185,
1551
+ "step": 2180
1552
+ },
1553
+ {
1554
+ "epoch": 2.8891820580474934,
1555
+ "grad_norm": 0.510231077671051,
1556
+ "learning_rate": 0.0002,
1557
+ "loss": 0.8555,
1558
+ "step": 2190
1559
+ },
1560
+ {
1561
+ "epoch": 2.9023746701846966,
1562
+ "grad_norm": 0.8072245121002197,
1563
+ "learning_rate": 0.0002,
1564
+ "loss": 0.9267,
1565
+ "step": 2200
1566
+ },
1567
+ {
1568
+ "epoch": 2.9155672823219,
1569
+ "grad_norm": 0.6055923104286194,
1570
+ "learning_rate": 0.0002,
1571
+ "loss": 0.9685,
1572
+ "step": 2210
1573
+ },
1574
+ {
1575
+ "epoch": 2.9287598944591027,
1576
+ "grad_norm": 0.7384416460990906,
1577
+ "learning_rate": 0.0002,
1578
+ "loss": 0.9157,
1579
+ "step": 2220
1580
+ },
1581
+ {
1582
+ "epoch": 2.941952506596306,
1583
+ "grad_norm": 0.4922751784324646,
1584
+ "learning_rate": 0.0002,
1585
+ "loss": 0.9712,
1586
+ "step": 2230
1587
+ },
1588
+ {
1589
+ "epoch": 2.955145118733509,
1590
+ "grad_norm": 0.6039906740188599,
1591
+ "learning_rate": 0.0002,
1592
+ "loss": 0.9487,
1593
+ "step": 2240
1594
+ },
1595
+ {
1596
+ "epoch": 2.9683377308707124,
1597
+ "grad_norm": 0.4751701354980469,
1598
+ "learning_rate": 0.0002,
1599
+ "loss": 0.9776,
1600
+ "step": 2250
1601
+ },
1602
+ {
1603
+ "epoch": 2.9815303430079156,
1604
+ "grad_norm": 0.5698353052139282,
1605
+ "learning_rate": 0.0002,
1606
+ "loss": 1.0619,
1607
+ "step": 2260
1608
+ },
1609
+ {
1610
+ "epoch": 2.994722955145119,
1611
+ "grad_norm": 0.893563449382782,
1612
+ "learning_rate": 0.0002,
1613
+ "loss": 1.1184,
1614
+ "step": 2270
1615
+ },
1616
+ {
1617
+ "epoch": 3.0,
1618
+ "eval_loss": 1.2046419382095337,
1619
+ "eval_runtime": 71.5992,
1620
+ "eval_samples_per_second": 6.02,
1621
+ "eval_steps_per_second": 0.754,
1622
+ "step": 2274
1623
+ }
1624
+ ],
1625
+ "logging_steps": 10,
1626
+ "max_steps": 6064,
1627
+ "num_input_tokens_seen": 0,
1628
+ "num_train_epochs": 8,
1629
+ "save_steps": 200,
1630
+ "stateful_callbacks": {
1631
+ "TrainerControl": {
1632
+ "args": {
1633
+ "should_epoch_stop": false,
1634
+ "should_evaluate": false,
1635
+ "should_log": false,
1636
+ "should_save": true,
1637
+ "should_training_stop": false
1638
+ },
1639
+ "attributes": {}
1640
+ }
1641
+ },
1642
+ "total_flos": 1.0523562830777549e+17,
1643
+ "train_batch_size": 1,
1644
+ "trial_name": null,
1645
+ "trial_params": null
1646
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-2274/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e04722e246164eebe6b4f70dd50fe946c936a2bd25edd75bcedcfd4c7ff9474e
3
+ size 5624
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec1cbc4628b3fee3f1829d92255ffddc551acb3e80520fa386a6a0dd03eeee5
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f02935c5cf306e25d9ca300b5c56058666be776ec46e54e9941227d9a294b306
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9653dfeb17315af1012d18ce6b4eb4ca95cc7a4f59f3b8dc429d007d4017c7
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2caab0cf3fae0f533d57c0fc3a50ce930197ee3c8baeeb49aacb2ff5ef6f469b
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/trainer_state.json ADDED
@@ -0,0 +1,2186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1874967813491821,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516",
4
+ "epoch": 4.0,
5
+ "eval_steps": 10,
6
+ "global_step": 3032,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.013192612137203167,
13
+ "grad_norm": 0.7545632123947144,
14
+ "learning_rate": 0.0002,
15
+ "loss": 1.9466,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.026385224274406333,
20
+ "grad_norm": 0.5787661075592041,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.4909,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0395778364116095,
27
+ "grad_norm": 0.8616093993186951,
28
+ "learning_rate": 0.0002,
29
+ "loss": 1.3906,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.052770448548812667,
34
+ "grad_norm": 0.42088547348976135,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.4116,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.06596306068601583,
41
+ "grad_norm": 0.47704678773880005,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.3446,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.079155672823219,
48
+ "grad_norm": 0.5763994455337524,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.2476,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.09234828496042216,
55
+ "grad_norm": 0.4579846262931824,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.2268,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.10554089709762533,
62
+ "grad_norm": 0.46623846888542175,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.415,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.11873350923482849,
69
+ "grad_norm": 0.4206956624984741,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.2849,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.13192612137203166,
76
+ "grad_norm": 0.41896629333496094,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.1608,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.14511873350923482,
83
+ "grad_norm": 0.3459089398384094,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.2617,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.158311345646438,
90
+ "grad_norm": 0.4587327837944031,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.2858,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.17150395778364116,
97
+ "grad_norm": 0.433525413274765,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.2241,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.18469656992084432,
104
+ "grad_norm": 0.39253175258636475,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.2269,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.19788918205804748,
111
+ "grad_norm": 0.3602290749549866,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.2224,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.21108179419525067,
118
+ "grad_norm": 0.41160839796066284,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.2834,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.22427440633245382,
125
+ "grad_norm": 0.7213630080223083,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.1986,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.23746701846965698,
132
+ "grad_norm": 0.39086055755615234,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.2215,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.25065963060686014,
139
+ "grad_norm": 0.4465520977973938,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.3315,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.2638522427440633,
146
+ "grad_norm": 1.814679741859436,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.3798,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.2770448548812665,
153
+ "grad_norm": 0.5026423931121826,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.2259,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.29023746701846964,
160
+ "grad_norm": 0.4156292974948883,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.3306,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.3034300791556728,
167
+ "grad_norm": 0.40813493728637695,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.266,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.316622691292876,
174
+ "grad_norm": 0.3304787874221802,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.1533,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.32981530343007914,
181
+ "grad_norm": 0.46139976382255554,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.3154,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.34300791556728233,
188
+ "grad_norm": 0.37518271803855896,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.1365,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.3562005277044855,
195
+ "grad_norm": 0.35586467385292053,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.2004,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.36939313984168864,
202
+ "grad_norm": 0.32441186904907227,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.2609,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.38258575197889183,
209
+ "grad_norm": 0.3198683261871338,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.212,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.39577836411609496,
216
+ "grad_norm": 0.33663108944892883,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.2465,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.40897097625329815,
223
+ "grad_norm": 0.3711244761943817,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.1702,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.42216358839050133,
230
+ "grad_norm": 0.3209651708602905,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.0871,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.43535620052770446,
237
+ "grad_norm": 0.5152716040611267,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.2728,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.44854881266490765,
244
+ "grad_norm": 0.5431376695632935,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.1833,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.46174142480211083,
251
+ "grad_norm": 0.3069997727870941,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.1344,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.47493403693931396,
258
+ "grad_norm": 0.34260064363479614,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.2742,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.48812664907651715,
265
+ "grad_norm": 0.345653235912323,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.3161,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.5013192612137203,
272
+ "grad_norm": 0.46222734451293945,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.1552,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.5145118733509235,
279
+ "grad_norm": 0.27301734685897827,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.0616,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.5277044854881267,
286
+ "grad_norm": 0.29048439860343933,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.1944,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.5408970976253298,
293
+ "grad_norm": 0.32927802205085754,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.0956,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.554089709762533,
300
+ "grad_norm": 0.3336397409439087,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.2362,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.5672823218997362,
307
+ "grad_norm": 0.4007597267627716,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.1445,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.5804749340369393,
314
+ "grad_norm": 0.36144956946372986,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.2731,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.5936675461741425,
321
+ "grad_norm": 0.6331009864807129,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.1604,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.6068601583113457,
328
+ "grad_norm": 0.41469088196754456,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.1692,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.6200527704485488,
335
+ "grad_norm": 0.4388185143470764,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.2372,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.633245382585752,
342
+ "grad_norm": 0.3738141655921936,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.2541,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.6464379947229552,
349
+ "grad_norm": 0.7212023138999939,
350
+ "learning_rate": 0.0002,
351
+ "loss": 1.1265,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.6596306068601583,
356
+ "grad_norm": 0.2972351014614105,
357
+ "learning_rate": 0.0002,
358
+ "loss": 1.2786,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.6728232189973615,
363
+ "grad_norm": 0.45293179154396057,
364
+ "learning_rate": 0.0002,
365
+ "loss": 1.1739,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.6860158311345647,
370
+ "grad_norm": 0.4319860637187958,
371
+ "learning_rate": 0.0002,
372
+ "loss": 1.255,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.6992084432717678,
377
+ "grad_norm": 0.3050215542316437,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.0959,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.712401055408971,
384
+ "grad_norm": 0.3552611172199249,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.1608,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.7255936675461742,
391
+ "grad_norm": 0.3631151020526886,
392
+ "learning_rate": 0.0002,
393
+ "loss": 1.2546,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.7387862796833773,
398
+ "grad_norm": 0.28177931904792786,
399
+ "learning_rate": 0.0002,
400
+ "loss": 1.1371,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.7519788918205804,
405
+ "grad_norm": 0.359764039516449,
406
+ "learning_rate": 0.0002,
407
+ "loss": 1.2081,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.7651715039577837,
412
+ "grad_norm": 0.3970327377319336,
413
+ "learning_rate": 0.0002,
414
+ "loss": 1.1356,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.7783641160949868,
419
+ "grad_norm": 0.3541001081466675,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.309,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.7915567282321899,
426
+ "grad_norm": 0.3478573262691498,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.2061,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.8047493403693932,
433
+ "grad_norm": 0.3900321424007416,
434
+ "learning_rate": 0.0002,
435
+ "loss": 1.1864,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.8179419525065963,
440
+ "grad_norm": 0.3443238437175751,
441
+ "learning_rate": 0.0002,
442
+ "loss": 1.1358,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.8311345646437994,
447
+ "grad_norm": 0.44238781929016113,
448
+ "learning_rate": 0.0002,
449
+ "loss": 1.3232,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.8443271767810027,
454
+ "grad_norm": 0.36339467763900757,
455
+ "learning_rate": 0.0002,
456
+ "loss": 1.1247,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.8575197889182058,
461
+ "grad_norm": 0.6243070363998413,
462
+ "learning_rate": 0.0002,
463
+ "loss": 1.1049,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.8707124010554089,
468
+ "grad_norm": 0.3209173381328583,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.1943,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.8839050131926122,
475
+ "grad_norm": 0.35017991065979004,
476
+ "learning_rate": 0.0002,
477
+ "loss": 1.1927,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.8970976253298153,
482
+ "grad_norm": 0.3247159421443939,
483
+ "learning_rate": 0.0002,
484
+ "loss": 1.1603,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.9102902374670184,
489
+ "grad_norm": 0.4091894030570984,
490
+ "learning_rate": 0.0002,
491
+ "loss": 1.2298,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.9234828496042217,
496
+ "grad_norm": 0.3975585997104645,
497
+ "learning_rate": 0.0002,
498
+ "loss": 1.2756,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.9366754617414248,
503
+ "grad_norm": 0.3666245937347412,
504
+ "learning_rate": 0.0002,
505
+ "loss": 1.281,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.9498680738786279,
510
+ "grad_norm": 0.45216917991638184,
511
+ "learning_rate": 0.0002,
512
+ "loss": 1.2855,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.9630606860158312,
517
+ "grad_norm": 0.36108118295669556,
518
+ "learning_rate": 0.0002,
519
+ "loss": 1.2217,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.9762532981530343,
524
+ "grad_norm": 0.44550251960754395,
525
+ "learning_rate": 0.0002,
526
+ "loss": 1.17,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.9894459102902374,
531
+ "grad_norm": 0.29801255464553833,
532
+ "learning_rate": 0.0002,
533
+ "loss": 1.0672,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 1.0,
538
+ "eval_loss": 1.203244686126709,
539
+ "eval_runtime": 76.0457,
540
+ "eval_samples_per_second": 5.668,
541
+ "eval_steps_per_second": 0.71,
542
+ "step": 758
543
+ },
544
+ {
545
+ "epoch": 1.0026385224274406,
546
+ "grad_norm": 0.4096551239490509,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.0748,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.0158311345646438,
553
+ "grad_norm": 0.2649582326412201,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.1537,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.029023746701847,
560
+ "grad_norm": 0.3100722134113312,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.1676,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.04221635883905,
567
+ "grad_norm": 0.3911755383014679,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.1736,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.0554089709762533,
574
+ "grad_norm": 0.4600953757762909,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.0354,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.0686015831134565,
581
+ "grad_norm": 0.28671619296073914,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.2869,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.0817941952506596,
588
+ "grad_norm": 0.47282642126083374,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.1441,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.0949868073878628,
595
+ "grad_norm": 0.690073549747467,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.1368,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.108179419525066,
602
+ "grad_norm": 0.7317902445793152,
603
+ "learning_rate": 0.0002,
604
+ "loss": 0.9944,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.121372031662269,
609
+ "grad_norm": 0.44215938448905945,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.108,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.1345646437994723,
616
+ "grad_norm": 0.33875149488449097,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.0558,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.1477572559366755,
623
+ "grad_norm": 0.3700002431869507,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.0471,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.1609498680738786,
630
+ "grad_norm": 0.41173291206359863,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.0121,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.1741424802110818,
637
+ "grad_norm": 0.5253589749336243,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.0312,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.187335092348285,
644
+ "grad_norm": 0.3912237286567688,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.2238,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.200527704485488,
651
+ "grad_norm": 0.40990331768989563,
652
+ "learning_rate": 0.0002,
653
+ "loss": 0.9434,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.2137203166226913,
658
+ "grad_norm": 0.40377968549728394,
659
+ "learning_rate": 0.0002,
660
+ "loss": 1.0493,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.2269129287598945,
665
+ "grad_norm": 0.4605846405029297,
666
+ "learning_rate": 0.0002,
667
+ "loss": 1.1496,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.2401055408970976,
672
+ "grad_norm": 0.31564897298812866,
673
+ "learning_rate": 0.0002,
674
+ "loss": 1.1173,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.2532981530343008,
679
+ "grad_norm": 0.39808550477027893,
680
+ "learning_rate": 0.0002,
681
+ "loss": 1.0547,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.266490765171504,
686
+ "grad_norm": 0.3762115240097046,
687
+ "learning_rate": 0.0002,
688
+ "loss": 1.1367,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.279683377308707,
693
+ "grad_norm": 0.4174984097480774,
694
+ "learning_rate": 0.0002,
695
+ "loss": 1.1596,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.2928759894459103,
700
+ "grad_norm": 0.5263054966926575,
701
+ "learning_rate": 0.0002,
702
+ "loss": 1.1327,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.3060686015831133,
707
+ "grad_norm": 0.41673699021339417,
708
+ "learning_rate": 0.0002,
709
+ "loss": 1.0339,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.3192612137203166,
714
+ "grad_norm": 0.9613684415817261,
715
+ "learning_rate": 0.0002,
716
+ "loss": 1.1198,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.3324538258575198,
721
+ "grad_norm": 0.3690216839313507,
722
+ "learning_rate": 0.0002,
723
+ "loss": 1.0444,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.345646437994723,
728
+ "grad_norm": 0.521821141242981,
729
+ "learning_rate": 0.0002,
730
+ "loss": 1.0473,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.358839050131926,
735
+ "grad_norm": 0.3353094160556793,
736
+ "learning_rate": 0.0002,
737
+ "loss": 1.1065,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.3720316622691293,
742
+ "grad_norm": 0.3843843936920166,
743
+ "learning_rate": 0.0002,
744
+ "loss": 1.1286,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.3852242744063323,
749
+ "grad_norm": 0.372514545917511,
750
+ "learning_rate": 0.0002,
751
+ "loss": 1.1369,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.3984168865435356,
756
+ "grad_norm": 0.34537771344184875,
757
+ "learning_rate": 0.0002,
758
+ "loss": 1.0041,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.4116094986807388,
763
+ "grad_norm": 0.45349085330963135,
764
+ "learning_rate": 0.0002,
765
+ "loss": 1.0251,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.424802110817942,
770
+ "grad_norm": 0.5120177268981934,
771
+ "learning_rate": 0.0002,
772
+ "loss": 1.1873,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.437994722955145,
777
+ "grad_norm": 0.42800238728523254,
778
+ "learning_rate": 0.0002,
779
+ "loss": 1.0872,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.4511873350923483,
784
+ "grad_norm": 0.343832790851593,
785
+ "learning_rate": 0.0002,
786
+ "loss": 1.0734,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.4643799472295513,
791
+ "grad_norm": 0.3829841911792755,
792
+ "learning_rate": 0.0002,
793
+ "loss": 1.1286,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.4775725593667546,
798
+ "grad_norm": 0.4289931058883667,
799
+ "learning_rate": 0.0002,
800
+ "loss": 1.1268,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.4907651715039578,
805
+ "grad_norm": 0.42750850319862366,
806
+ "learning_rate": 0.0002,
807
+ "loss": 1.0676,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.503957783641161,
812
+ "grad_norm": 0.34328413009643555,
813
+ "learning_rate": 0.0002,
814
+ "loss": 1.072,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.517150395778364,
819
+ "grad_norm": 0.349096417427063,
820
+ "learning_rate": 0.0002,
821
+ "loss": 1.0863,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.5303430079155673,
826
+ "grad_norm": 0.7700717449188232,
827
+ "learning_rate": 0.0002,
828
+ "loss": 1.1462,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.5435356200527703,
833
+ "grad_norm": 0.39294949173927307,
834
+ "learning_rate": 0.0002,
835
+ "loss": 0.9528,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.5567282321899736,
840
+ "grad_norm": 0.36173608899116516,
841
+ "learning_rate": 0.0002,
842
+ "loss": 1.1603,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.5699208443271768,
847
+ "grad_norm": 0.6034277677536011,
848
+ "learning_rate": 0.0002,
849
+ "loss": 1.1508,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 1.58311345646438,
854
+ "grad_norm": 0.36694103479385376,
855
+ "learning_rate": 0.0002,
856
+ "loss": 1.0105,
857
+ "step": 1200
858
+ },
859
+ {
860
+ "epoch": 1.596306068601583,
861
+ "grad_norm": 0.4727209508419037,
862
+ "learning_rate": 0.0002,
863
+ "loss": 1.1479,
864
+ "step": 1210
865
+ },
866
+ {
867
+ "epoch": 1.6094986807387863,
868
+ "grad_norm": 0.6482883095741272,
869
+ "learning_rate": 0.0002,
870
+ "loss": 1.0689,
871
+ "step": 1220
872
+ },
873
+ {
874
+ "epoch": 1.6226912928759893,
875
+ "grad_norm": 0.5238035917282104,
876
+ "learning_rate": 0.0002,
877
+ "loss": 1.1405,
878
+ "step": 1230
879
+ },
880
+ {
881
+ "epoch": 1.6358839050131926,
882
+ "grad_norm": 0.4812222421169281,
883
+ "learning_rate": 0.0002,
884
+ "loss": 1.0596,
885
+ "step": 1240
886
+ },
887
+ {
888
+ "epoch": 1.6490765171503958,
889
+ "grad_norm": 0.7131702303886414,
890
+ "learning_rate": 0.0002,
891
+ "loss": 1.2729,
892
+ "step": 1250
893
+ },
894
+ {
895
+ "epoch": 1.662269129287599,
896
+ "grad_norm": 0.3803327977657318,
897
+ "learning_rate": 0.0002,
898
+ "loss": 0.9832,
899
+ "step": 1260
900
+ },
901
+ {
902
+ "epoch": 1.675461741424802,
903
+ "grad_norm": 0.3745088577270508,
904
+ "learning_rate": 0.0002,
905
+ "loss": 1.1433,
906
+ "step": 1270
907
+ },
908
+ {
909
+ "epoch": 1.6886543535620053,
910
+ "grad_norm": 0.4427378475666046,
911
+ "learning_rate": 0.0002,
912
+ "loss": 1.1018,
913
+ "step": 1280
914
+ },
915
+ {
916
+ "epoch": 1.7018469656992083,
917
+ "grad_norm": 0.797478973865509,
918
+ "learning_rate": 0.0002,
919
+ "loss": 1.0619,
920
+ "step": 1290
921
+ },
922
+ {
923
+ "epoch": 1.7150395778364116,
924
+ "grad_norm": 0.503620982170105,
925
+ "learning_rate": 0.0002,
926
+ "loss": 1.0853,
927
+ "step": 1300
928
+ },
929
+ {
930
+ "epoch": 1.7282321899736148,
931
+ "grad_norm": 0.4132426381111145,
932
+ "learning_rate": 0.0002,
933
+ "loss": 1.1324,
934
+ "step": 1310
935
+ },
936
+ {
937
+ "epoch": 1.741424802110818,
938
+ "grad_norm": 0.41811656951904297,
939
+ "learning_rate": 0.0002,
940
+ "loss": 1.172,
941
+ "step": 1320
942
+ },
943
+ {
944
+ "epoch": 1.754617414248021,
945
+ "grad_norm": 0.40647849440574646,
946
+ "learning_rate": 0.0002,
947
+ "loss": 1.0903,
948
+ "step": 1330
949
+ },
950
+ {
951
+ "epoch": 1.767810026385224,
952
+ "grad_norm": 0.42138347029685974,
953
+ "learning_rate": 0.0002,
954
+ "loss": 1.1316,
955
+ "step": 1340
956
+ },
957
+ {
958
+ "epoch": 1.7810026385224274,
959
+ "grad_norm": 0.46523579955101013,
960
+ "learning_rate": 0.0002,
961
+ "loss": 0.9955,
962
+ "step": 1350
963
+ },
964
+ {
965
+ "epoch": 1.7941952506596306,
966
+ "grad_norm": 0.39760419726371765,
967
+ "learning_rate": 0.0002,
968
+ "loss": 1.0307,
969
+ "step": 1360
970
+ },
971
+ {
972
+ "epoch": 1.8073878627968338,
973
+ "grad_norm": 0.37993717193603516,
974
+ "learning_rate": 0.0002,
975
+ "loss": 1.1218,
976
+ "step": 1370
977
+ },
978
+ {
979
+ "epoch": 1.820580474934037,
980
+ "grad_norm": 0.5404181480407715,
981
+ "learning_rate": 0.0002,
982
+ "loss": 1.0921,
983
+ "step": 1380
984
+ },
985
+ {
986
+ "epoch": 1.83377308707124,
987
+ "grad_norm": 0.4385245740413666,
988
+ "learning_rate": 0.0002,
989
+ "loss": 1.0903,
990
+ "step": 1390
991
+ },
992
+ {
993
+ "epoch": 1.8469656992084431,
994
+ "grad_norm": 0.529797375202179,
995
+ "learning_rate": 0.0002,
996
+ "loss": 1.1175,
997
+ "step": 1400
998
+ },
999
+ {
1000
+ "epoch": 1.8601583113456464,
1001
+ "grad_norm": 0.481567919254303,
1002
+ "learning_rate": 0.0002,
1003
+ "loss": 1.0577,
1004
+ "step": 1410
1005
+ },
1006
+ {
1007
+ "epoch": 1.8733509234828496,
1008
+ "grad_norm": 0.34787362813949585,
1009
+ "learning_rate": 0.0002,
1010
+ "loss": 1.0581,
1011
+ "step": 1420
1012
+ },
1013
+ {
1014
+ "epoch": 1.8865435356200528,
1015
+ "grad_norm": 0.6402362585067749,
1016
+ "learning_rate": 0.0002,
1017
+ "loss": 1.0536,
1018
+ "step": 1430
1019
+ },
1020
+ {
1021
+ "epoch": 1.899736147757256,
1022
+ "grad_norm": 0.3461322784423828,
1023
+ "learning_rate": 0.0002,
1024
+ "loss": 1.0787,
1025
+ "step": 1440
1026
+ },
1027
+ {
1028
+ "epoch": 1.912928759894459,
1029
+ "grad_norm": 0.44005653262138367,
1030
+ "learning_rate": 0.0002,
1031
+ "loss": 1.0925,
1032
+ "step": 1450
1033
+ },
1034
+ {
1035
+ "epoch": 1.9261213720316621,
1036
+ "grad_norm": 0.4064280688762665,
1037
+ "learning_rate": 0.0002,
1038
+ "loss": 1.0414,
1039
+ "step": 1460
1040
+ },
1041
+ {
1042
+ "epoch": 1.9393139841688654,
1043
+ "grad_norm": 0.5236523151397705,
1044
+ "learning_rate": 0.0002,
1045
+ "loss": 1.0608,
1046
+ "step": 1470
1047
+ },
1048
+ {
1049
+ "epoch": 1.9525065963060686,
1050
+ "grad_norm": 0.41030219197273254,
1051
+ "learning_rate": 0.0002,
1052
+ "loss": 1.0572,
1053
+ "step": 1480
1054
+ },
1055
+ {
1056
+ "epoch": 1.9656992084432718,
1057
+ "grad_norm": 0.39805835485458374,
1058
+ "learning_rate": 0.0002,
1059
+ "loss": 1.1204,
1060
+ "step": 1490
1061
+ },
1062
+ {
1063
+ "epoch": 1.978891820580475,
1064
+ "grad_norm": 0.42974501848220825,
1065
+ "learning_rate": 0.0002,
1066
+ "loss": 1.0364,
1067
+ "step": 1500
1068
+ },
1069
+ {
1070
+ "epoch": 1.992084432717678,
1071
+ "grad_norm": 0.4688243865966797,
1072
+ "learning_rate": 0.0002,
1073
+ "loss": 1.1169,
1074
+ "step": 1510
1075
+ },
1076
+ {
1077
+ "epoch": 2.0,
1078
+ "eval_loss": 1.1874967813491821,
1079
+ "eval_runtime": 71.9523,
1080
+ "eval_samples_per_second": 5.99,
1081
+ "eval_steps_per_second": 0.75,
1082
+ "step": 1516
1083
+ },
1084
+ {
1085
+ "epoch": 2.005277044854881,
1086
+ "grad_norm": 0.4121631383895874,
1087
+ "learning_rate": 0.0002,
1088
+ "loss": 1.0401,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.0184696569920844,
1093
+ "grad_norm": 0.4844197928905487,
1094
+ "learning_rate": 0.0002,
1095
+ "loss": 0.9384,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.0316622691292876,
1100
+ "grad_norm": 0.45408546924591064,
1101
+ "learning_rate": 0.0002,
1102
+ "loss": 0.8686,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.044854881266491,
1107
+ "grad_norm": 0.48662951588630676,
1108
+ "learning_rate": 0.0002,
1109
+ "loss": 1.0399,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.058047493403694,
1114
+ "grad_norm": 0.7195899486541748,
1115
+ "learning_rate": 0.0002,
1116
+ "loss": 0.936,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.0712401055408973,
1121
+ "grad_norm": 0.5071077346801758,
1122
+ "learning_rate": 0.0002,
1123
+ "loss": 0.9486,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.0844327176781,
1128
+ "grad_norm": 0.7473958730697632,
1129
+ "learning_rate": 0.0002,
1130
+ "loss": 1.0055,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.0976253298153034,
1135
+ "grad_norm": 0.5509232878684998,
1136
+ "learning_rate": 0.0002,
1137
+ "loss": 0.8309,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.1108179419525066,
1142
+ "grad_norm": 0.5108042359352112,
1143
+ "learning_rate": 0.0002,
1144
+ "loss": 0.9181,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.12401055408971,
1149
+ "grad_norm": 0.42331448197364807,
1150
+ "learning_rate": 0.0002,
1151
+ "loss": 0.9499,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.137203166226913,
1156
+ "grad_norm": 0.46621623635292053,
1157
+ "learning_rate": 0.0002,
1158
+ "loss": 0.9359,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.150395778364116,
1163
+ "grad_norm": 0.43802836537361145,
1164
+ "learning_rate": 0.0002,
1165
+ "loss": 0.9065,
1166
+ "step": 1630
1167
+ },
1168
+ {
1169
+ "epoch": 2.163588390501319,
1170
+ "grad_norm": 0.49908021092414856,
1171
+ "learning_rate": 0.0002,
1172
+ "loss": 0.9375,
1173
+ "step": 1640
1174
+ },
1175
+ {
1176
+ "epoch": 2.1767810026385224,
1177
+ "grad_norm": 0.4195636808872223,
1178
+ "learning_rate": 0.0002,
1179
+ "loss": 1.0389,
1180
+ "step": 1650
1181
+ },
1182
+ {
1183
+ "epoch": 2.1899736147757256,
1184
+ "grad_norm": 0.49515822529792786,
1185
+ "learning_rate": 0.0002,
1186
+ "loss": 0.8501,
1187
+ "step": 1660
1188
+ },
1189
+ {
1190
+ "epoch": 2.203166226912929,
1191
+ "grad_norm": 0.4607589542865753,
1192
+ "learning_rate": 0.0002,
1193
+ "loss": 1.0557,
1194
+ "step": 1670
1195
+ },
1196
+ {
1197
+ "epoch": 2.216358839050132,
1198
+ "grad_norm": 0.4489196836948395,
1199
+ "learning_rate": 0.0002,
1200
+ "loss": 1.0206,
1201
+ "step": 1680
1202
+ },
1203
+ {
1204
+ "epoch": 2.229551451187335,
1205
+ "grad_norm": 0.49300864338874817,
1206
+ "learning_rate": 0.0002,
1207
+ "loss": 0.9657,
1208
+ "step": 1690
1209
+ },
1210
+ {
1211
+ "epoch": 2.242744063324538,
1212
+ "grad_norm": 0.6624954342842102,
1213
+ "learning_rate": 0.0002,
1214
+ "loss": 0.8371,
1215
+ "step": 1700
1216
+ },
1217
+ {
1218
+ "epoch": 2.2559366754617414,
1219
+ "grad_norm": 0.8391500115394592,
1220
+ "learning_rate": 0.0002,
1221
+ "loss": 0.8555,
1222
+ "step": 1710
1223
+ },
1224
+ {
1225
+ "epoch": 2.2691292875989446,
1226
+ "grad_norm": 0.5193073749542236,
1227
+ "learning_rate": 0.0002,
1228
+ "loss": 1.0113,
1229
+ "step": 1720
1230
+ },
1231
+ {
1232
+ "epoch": 2.282321899736148,
1233
+ "grad_norm": 0.6180613040924072,
1234
+ "learning_rate": 0.0002,
1235
+ "loss": 0.9979,
1236
+ "step": 1730
1237
+ },
1238
+ {
1239
+ "epoch": 2.295514511873351,
1240
+ "grad_norm": 0.591191291809082,
1241
+ "learning_rate": 0.0002,
1242
+ "loss": 0.9579,
1243
+ "step": 1740
1244
+ },
1245
+ {
1246
+ "epoch": 2.308707124010554,
1247
+ "grad_norm": 0.546897828578949,
1248
+ "learning_rate": 0.0002,
1249
+ "loss": 0.8879,
1250
+ "step": 1750
1251
+ },
1252
+ {
1253
+ "epoch": 2.321899736147757,
1254
+ "grad_norm": 0.5470401644706726,
1255
+ "learning_rate": 0.0002,
1256
+ "loss": 0.9321,
1257
+ "step": 1760
1258
+ },
1259
+ {
1260
+ "epoch": 2.3350923482849604,
1261
+ "grad_norm": 0.4590282738208771,
1262
+ "learning_rate": 0.0002,
1263
+ "loss": 0.9104,
1264
+ "step": 1770
1265
+ },
1266
+ {
1267
+ "epoch": 2.3482849604221636,
1268
+ "grad_norm": 0.622164785861969,
1269
+ "learning_rate": 0.0002,
1270
+ "loss": 1.0384,
1271
+ "step": 1780
1272
+ },
1273
+ {
1274
+ "epoch": 2.361477572559367,
1275
+ "grad_norm": 0.5753812193870544,
1276
+ "learning_rate": 0.0002,
1277
+ "loss": 1.0297,
1278
+ "step": 1790
1279
+ },
1280
+ {
1281
+ "epoch": 2.37467018469657,
1282
+ "grad_norm": 0.47958624362945557,
1283
+ "learning_rate": 0.0002,
1284
+ "loss": 0.9569,
1285
+ "step": 1800
1286
+ },
1287
+ {
1288
+ "epoch": 2.387862796833773,
1289
+ "grad_norm": 0.48042672872543335,
1290
+ "learning_rate": 0.0002,
1291
+ "loss": 1.0519,
1292
+ "step": 1810
1293
+ },
1294
+ {
1295
+ "epoch": 2.401055408970976,
1296
+ "grad_norm": 0.44586366415023804,
1297
+ "learning_rate": 0.0002,
1298
+ "loss": 0.9042,
1299
+ "step": 1820
1300
+ },
1301
+ {
1302
+ "epoch": 2.4142480211081794,
1303
+ "grad_norm": 0.7239416837692261,
1304
+ "learning_rate": 0.0002,
1305
+ "loss": 0.9783,
1306
+ "step": 1830
1307
+ },
1308
+ {
1309
+ "epoch": 2.4274406332453826,
1310
+ "grad_norm": 0.5515341758728027,
1311
+ "learning_rate": 0.0002,
1312
+ "loss": 0.8818,
1313
+ "step": 1840
1314
+ },
1315
+ {
1316
+ "epoch": 2.440633245382586,
1317
+ "grad_norm": 0.6280064582824707,
1318
+ "learning_rate": 0.0002,
1319
+ "loss": 0.9503,
1320
+ "step": 1850
1321
+ },
1322
+ {
1323
+ "epoch": 2.453825857519789,
1324
+ "grad_norm": 0.4832057058811188,
1325
+ "learning_rate": 0.0002,
1326
+ "loss": 0.8943,
1327
+ "step": 1860
1328
+ },
1329
+ {
1330
+ "epoch": 2.467018469656992,
1331
+ "grad_norm": 0.5789321064949036,
1332
+ "learning_rate": 0.0002,
1333
+ "loss": 0.8744,
1334
+ "step": 1870
1335
+ },
1336
+ {
1337
+ "epoch": 2.480211081794195,
1338
+ "grad_norm": 0.48491886258125305,
1339
+ "learning_rate": 0.0002,
1340
+ "loss": 0.9332,
1341
+ "step": 1880
1342
+ },
1343
+ {
1344
+ "epoch": 2.4934036939313984,
1345
+ "grad_norm": 0.532365620136261,
1346
+ "learning_rate": 0.0002,
1347
+ "loss": 0.943,
1348
+ "step": 1890
1349
+ },
1350
+ {
1351
+ "epoch": 2.5065963060686016,
1352
+ "grad_norm": 0.7087852954864502,
1353
+ "learning_rate": 0.0002,
1354
+ "loss": 0.9734,
1355
+ "step": 1900
1356
+ },
1357
+ {
1358
+ "epoch": 2.519788918205805,
1359
+ "grad_norm": 0.48157402873039246,
1360
+ "learning_rate": 0.0002,
1361
+ "loss": 0.9767,
1362
+ "step": 1910
1363
+ },
1364
+ {
1365
+ "epoch": 2.532981530343008,
1366
+ "grad_norm": 0.5886041522026062,
1367
+ "learning_rate": 0.0002,
1368
+ "loss": 0.9851,
1369
+ "step": 1920
1370
+ },
1371
+ {
1372
+ "epoch": 2.5461741424802113,
1373
+ "grad_norm": 0.6332622766494751,
1374
+ "learning_rate": 0.0002,
1375
+ "loss": 1.0144,
1376
+ "step": 1930
1377
+ },
1378
+ {
1379
+ "epoch": 2.559366754617414,
1380
+ "grad_norm": 0.5463117957115173,
1381
+ "learning_rate": 0.0002,
1382
+ "loss": 0.9516,
1383
+ "step": 1940
1384
+ },
1385
+ {
1386
+ "epoch": 2.5725593667546174,
1387
+ "grad_norm": 0.5432228446006775,
1388
+ "learning_rate": 0.0002,
1389
+ "loss": 0.9373,
1390
+ "step": 1950
1391
+ },
1392
+ {
1393
+ "epoch": 2.5857519788918206,
1394
+ "grad_norm": 0.5929186940193176,
1395
+ "learning_rate": 0.0002,
1396
+ "loss": 0.8974,
1397
+ "step": 1960
1398
+ },
1399
+ {
1400
+ "epoch": 2.598944591029024,
1401
+ "grad_norm": 0.5120641589164734,
1402
+ "learning_rate": 0.0002,
1403
+ "loss": 1.0062,
1404
+ "step": 1970
1405
+ },
1406
+ {
1407
+ "epoch": 2.6121372031662267,
1408
+ "grad_norm": 0.5372339487075806,
1409
+ "learning_rate": 0.0002,
1410
+ "loss": 0.9143,
1411
+ "step": 1980
1412
+ },
1413
+ {
1414
+ "epoch": 2.62532981530343,
1415
+ "grad_norm": 0.5519838929176331,
1416
+ "learning_rate": 0.0002,
1417
+ "loss": 1.0786,
1418
+ "step": 1990
1419
+ },
1420
+ {
1421
+ "epoch": 2.638522427440633,
1422
+ "grad_norm": 0.7304037809371948,
1423
+ "learning_rate": 0.0002,
1424
+ "loss": 1.021,
1425
+ "step": 2000
1426
+ },
1427
+ {
1428
+ "epoch": 2.6517150395778364,
1429
+ "grad_norm": 0.6182340979576111,
1430
+ "learning_rate": 0.0002,
1431
+ "loss": 0.8708,
1432
+ "step": 2010
1433
+ },
1434
+ {
1435
+ "epoch": 2.6649076517150396,
1436
+ "grad_norm": 0.4874444305896759,
1437
+ "learning_rate": 0.0002,
1438
+ "loss": 1.0501,
1439
+ "step": 2020
1440
+ },
1441
+ {
1442
+ "epoch": 2.678100263852243,
1443
+ "grad_norm": 0.5850239396095276,
1444
+ "learning_rate": 0.0002,
1445
+ "loss": 0.9612,
1446
+ "step": 2030
1447
+ },
1448
+ {
1449
+ "epoch": 2.691292875989446,
1450
+ "grad_norm": 0.6495311856269836,
1451
+ "learning_rate": 0.0002,
1452
+ "loss": 0.9808,
1453
+ "step": 2040
1454
+ },
1455
+ {
1456
+ "epoch": 2.7044854881266494,
1457
+ "grad_norm": 1.002830147743225,
1458
+ "learning_rate": 0.0002,
1459
+ "loss": 1.0187,
1460
+ "step": 2050
1461
+ },
1462
+ {
1463
+ "epoch": 2.717678100263852,
1464
+ "grad_norm": 0.49076753854751587,
1465
+ "learning_rate": 0.0002,
1466
+ "loss": 1.0386,
1467
+ "step": 2060
1468
+ },
1469
+ {
1470
+ "epoch": 2.7308707124010554,
1471
+ "grad_norm": 0.4736326336860657,
1472
+ "learning_rate": 0.0002,
1473
+ "loss": 0.9416,
1474
+ "step": 2070
1475
+ },
1476
+ {
1477
+ "epoch": 2.7440633245382586,
1478
+ "grad_norm": 0.5527601838111877,
1479
+ "learning_rate": 0.0002,
1480
+ "loss": 0.8424,
1481
+ "step": 2080
1482
+ },
1483
+ {
1484
+ "epoch": 2.757255936675462,
1485
+ "grad_norm": 0.7295718193054199,
1486
+ "learning_rate": 0.0002,
1487
+ "loss": 0.9149,
1488
+ "step": 2090
1489
+ },
1490
+ {
1491
+ "epoch": 2.7704485488126647,
1492
+ "grad_norm": 0.5437536835670471,
1493
+ "learning_rate": 0.0002,
1494
+ "loss": 0.9032,
1495
+ "step": 2100
1496
+ },
1497
+ {
1498
+ "epoch": 2.783641160949868,
1499
+ "grad_norm": 0.5997128486633301,
1500
+ "learning_rate": 0.0002,
1501
+ "loss": 0.8254,
1502
+ "step": 2110
1503
+ },
1504
+ {
1505
+ "epoch": 2.796833773087071,
1506
+ "grad_norm": 0.6498191356658936,
1507
+ "learning_rate": 0.0002,
1508
+ "loss": 0.976,
1509
+ "step": 2120
1510
+ },
1511
+ {
1512
+ "epoch": 2.8100263852242744,
1513
+ "grad_norm": 0.5237268805503845,
1514
+ "learning_rate": 0.0002,
1515
+ "loss": 0.9543,
1516
+ "step": 2130
1517
+ },
1518
+ {
1519
+ "epoch": 2.8232189973614776,
1520
+ "grad_norm": 0.6033027172088623,
1521
+ "learning_rate": 0.0002,
1522
+ "loss": 0.9302,
1523
+ "step": 2140
1524
+ },
1525
+ {
1526
+ "epoch": 2.836411609498681,
1527
+ "grad_norm": 0.6077138781547546,
1528
+ "learning_rate": 0.0002,
1529
+ "loss": 0.9625,
1530
+ "step": 2150
1531
+ },
1532
+ {
1533
+ "epoch": 2.849604221635884,
1534
+ "grad_norm": 0.4127797484397888,
1535
+ "learning_rate": 0.0002,
1536
+ "loss": 0.9347,
1537
+ "step": 2160
1538
+ },
1539
+ {
1540
+ "epoch": 2.862796833773087,
1541
+ "grad_norm": 0.8448635339736938,
1542
+ "learning_rate": 0.0002,
1543
+ "loss": 1.0459,
1544
+ "step": 2170
1545
+ },
1546
+ {
1547
+ "epoch": 2.87598944591029,
1548
+ "grad_norm": 0.5669729113578796,
1549
+ "learning_rate": 0.0002,
1550
+ "loss": 0.8185,
1551
+ "step": 2180
1552
+ },
1553
+ {
1554
+ "epoch": 2.8891820580474934,
1555
+ "grad_norm": 0.510231077671051,
1556
+ "learning_rate": 0.0002,
1557
+ "loss": 0.8555,
1558
+ "step": 2190
1559
+ },
1560
+ {
1561
+ "epoch": 2.9023746701846966,
1562
+ "grad_norm": 0.8072245121002197,
1563
+ "learning_rate": 0.0002,
1564
+ "loss": 0.9267,
1565
+ "step": 2200
1566
+ },
1567
+ {
1568
+ "epoch": 2.9155672823219,
1569
+ "grad_norm": 0.6055923104286194,
1570
+ "learning_rate": 0.0002,
1571
+ "loss": 0.9685,
1572
+ "step": 2210
1573
+ },
1574
+ {
1575
+ "epoch": 2.9287598944591027,
1576
+ "grad_norm": 0.7384416460990906,
1577
+ "learning_rate": 0.0002,
1578
+ "loss": 0.9157,
1579
+ "step": 2220
1580
+ },
1581
+ {
1582
+ "epoch": 2.941952506596306,
1583
+ "grad_norm": 0.4922751784324646,
1584
+ "learning_rate": 0.0002,
1585
+ "loss": 0.9712,
1586
+ "step": 2230
1587
+ },
1588
+ {
1589
+ "epoch": 2.955145118733509,
1590
+ "grad_norm": 0.6039906740188599,
1591
+ "learning_rate": 0.0002,
1592
+ "loss": 0.9487,
1593
+ "step": 2240
1594
+ },
1595
+ {
1596
+ "epoch": 2.9683377308707124,
1597
+ "grad_norm": 0.4751701354980469,
1598
+ "learning_rate": 0.0002,
1599
+ "loss": 0.9776,
1600
+ "step": 2250
1601
+ },
1602
+ {
1603
+ "epoch": 2.9815303430079156,
1604
+ "grad_norm": 0.5698353052139282,
1605
+ "learning_rate": 0.0002,
1606
+ "loss": 1.0619,
1607
+ "step": 2260
1608
+ },
1609
+ {
1610
+ "epoch": 2.994722955145119,
1611
+ "grad_norm": 0.893563449382782,
1612
+ "learning_rate": 0.0002,
1613
+ "loss": 1.1184,
1614
+ "step": 2270
1615
+ },
1616
+ {
1617
+ "epoch": 3.0,
1618
+ "eval_loss": 1.2046419382095337,
1619
+ "eval_runtime": 71.5992,
1620
+ "eval_samples_per_second": 6.02,
1621
+ "eval_steps_per_second": 0.754,
1622
+ "step": 2274
1623
+ },
1624
+ {
1625
+ "epoch": 3.007915567282322,
1626
+ "grad_norm": 0.41119325160980225,
1627
+ "learning_rate": 0.0002,
1628
+ "loss": 0.8269,
1629
+ "step": 2280
1630
+ },
1631
+ {
1632
+ "epoch": 3.021108179419525,
1633
+ "grad_norm": 0.8169420957565308,
1634
+ "learning_rate": 0.0002,
1635
+ "loss": 0.7856,
1636
+ "step": 2290
1637
+ },
1638
+ {
1639
+ "epoch": 3.034300791556728,
1640
+ "grad_norm": 0.6033818125724792,
1641
+ "learning_rate": 0.0002,
1642
+ "loss": 0.794,
1643
+ "step": 2300
1644
+ },
1645
+ {
1646
+ "epoch": 3.0474934036939314,
1647
+ "grad_norm": 0.9600058197975159,
1648
+ "learning_rate": 0.0002,
1649
+ "loss": 0.7607,
1650
+ "step": 2310
1651
+ },
1652
+ {
1653
+ "epoch": 3.0606860158311346,
1654
+ "grad_norm": 0.5859250426292419,
1655
+ "learning_rate": 0.0002,
1656
+ "loss": 0.8353,
1657
+ "step": 2320
1658
+ },
1659
+ {
1660
+ "epoch": 3.073878627968338,
1661
+ "grad_norm": 0.6758618950843811,
1662
+ "learning_rate": 0.0002,
1663
+ "loss": 0.7598,
1664
+ "step": 2330
1665
+ },
1666
+ {
1667
+ "epoch": 3.0870712401055407,
1668
+ "grad_norm": 0.8407140970230103,
1669
+ "learning_rate": 0.0002,
1670
+ "loss": 0.7631,
1671
+ "step": 2340
1672
+ },
1673
+ {
1674
+ "epoch": 3.100263852242744,
1675
+ "grad_norm": 0.767779529094696,
1676
+ "learning_rate": 0.0002,
1677
+ "loss": 0.7664,
1678
+ "step": 2350
1679
+ },
1680
+ {
1681
+ "epoch": 3.113456464379947,
1682
+ "grad_norm": 0.5572896599769592,
1683
+ "learning_rate": 0.0002,
1684
+ "loss": 0.7121,
1685
+ "step": 2360
1686
+ },
1687
+ {
1688
+ "epoch": 3.1266490765171504,
1689
+ "grad_norm": 0.5908368825912476,
1690
+ "learning_rate": 0.0002,
1691
+ "loss": 0.7419,
1692
+ "step": 2370
1693
+ },
1694
+ {
1695
+ "epoch": 3.1398416886543536,
1696
+ "grad_norm": 0.8047826290130615,
1697
+ "learning_rate": 0.0002,
1698
+ "loss": 0.8024,
1699
+ "step": 2380
1700
+ },
1701
+ {
1702
+ "epoch": 3.153034300791557,
1703
+ "grad_norm": 0.8041718006134033,
1704
+ "learning_rate": 0.0002,
1705
+ "loss": 0.8686,
1706
+ "step": 2390
1707
+ },
1708
+ {
1709
+ "epoch": 3.16622691292876,
1710
+ "grad_norm": 0.57078617811203,
1711
+ "learning_rate": 0.0002,
1712
+ "loss": 0.668,
1713
+ "step": 2400
1714
+ },
1715
+ {
1716
+ "epoch": 3.179419525065963,
1717
+ "grad_norm": 0.5125322937965393,
1718
+ "learning_rate": 0.0002,
1719
+ "loss": 0.7976,
1720
+ "step": 2410
1721
+ },
1722
+ {
1723
+ "epoch": 3.192612137203166,
1724
+ "grad_norm": 0.6356934309005737,
1725
+ "learning_rate": 0.0002,
1726
+ "loss": 0.741,
1727
+ "step": 2420
1728
+ },
1729
+ {
1730
+ "epoch": 3.2058047493403694,
1731
+ "grad_norm": 1.0129680633544922,
1732
+ "learning_rate": 0.0002,
1733
+ "loss": 0.687,
1734
+ "step": 2430
1735
+ },
1736
+ {
1737
+ "epoch": 3.2189973614775726,
1738
+ "grad_norm": 0.8104226589202881,
1739
+ "learning_rate": 0.0002,
1740
+ "loss": 0.8316,
1741
+ "step": 2440
1742
+ },
1743
+ {
1744
+ "epoch": 3.232189973614776,
1745
+ "grad_norm": 0.7276079058647156,
1746
+ "learning_rate": 0.0002,
1747
+ "loss": 0.8343,
1748
+ "step": 2450
1749
+ },
1750
+ {
1751
+ "epoch": 3.2453825857519787,
1752
+ "grad_norm": 0.9753884077072144,
1753
+ "learning_rate": 0.0002,
1754
+ "loss": 0.8183,
1755
+ "step": 2460
1756
+ },
1757
+ {
1758
+ "epoch": 3.258575197889182,
1759
+ "grad_norm": 0.9753183722496033,
1760
+ "learning_rate": 0.0002,
1761
+ "loss": 0.7776,
1762
+ "step": 2470
1763
+ },
1764
+ {
1765
+ "epoch": 3.271767810026385,
1766
+ "grad_norm": 0.6791225075721741,
1767
+ "learning_rate": 0.0002,
1768
+ "loss": 0.8815,
1769
+ "step": 2480
1770
+ },
1771
+ {
1772
+ "epoch": 3.2849604221635884,
1773
+ "grad_norm": 0.6797150373458862,
1774
+ "learning_rate": 0.0002,
1775
+ "loss": 0.7548,
1776
+ "step": 2490
1777
+ },
1778
+ {
1779
+ "epoch": 3.2981530343007917,
1780
+ "grad_norm": 0.8107194900512695,
1781
+ "learning_rate": 0.0002,
1782
+ "loss": 0.8395,
1783
+ "step": 2500
1784
+ },
1785
+ {
1786
+ "epoch": 3.311345646437995,
1787
+ "grad_norm": 0.5878375172615051,
1788
+ "learning_rate": 0.0002,
1789
+ "loss": 0.7869,
1790
+ "step": 2510
1791
+ },
1792
+ {
1793
+ "epoch": 3.324538258575198,
1794
+ "grad_norm": 0.5882975459098816,
1795
+ "learning_rate": 0.0002,
1796
+ "loss": 0.7992,
1797
+ "step": 2520
1798
+ },
1799
+ {
1800
+ "epoch": 3.337730870712401,
1801
+ "grad_norm": 0.6180013418197632,
1802
+ "learning_rate": 0.0002,
1803
+ "loss": 0.7472,
1804
+ "step": 2530
1805
+ },
1806
+ {
1807
+ "epoch": 3.350923482849604,
1808
+ "grad_norm": 1.0008151531219482,
1809
+ "learning_rate": 0.0002,
1810
+ "loss": 0.8033,
1811
+ "step": 2540
1812
+ },
1813
+ {
1814
+ "epoch": 3.3641160949868074,
1815
+ "grad_norm": 0.6404656767845154,
1816
+ "learning_rate": 0.0002,
1817
+ "loss": 0.8464,
1818
+ "step": 2550
1819
+ },
1820
+ {
1821
+ "epoch": 3.3773087071240107,
1822
+ "grad_norm": 0.8481354117393494,
1823
+ "learning_rate": 0.0002,
1824
+ "loss": 0.7533,
1825
+ "step": 2560
1826
+ },
1827
+ {
1828
+ "epoch": 3.390501319261214,
1829
+ "grad_norm": 0.8068035244941711,
1830
+ "learning_rate": 0.0002,
1831
+ "loss": 0.7852,
1832
+ "step": 2570
1833
+ },
1834
+ {
1835
+ "epoch": 3.4036939313984167,
1836
+ "grad_norm": 0.7477166056632996,
1837
+ "learning_rate": 0.0002,
1838
+ "loss": 0.8621,
1839
+ "step": 2580
1840
+ },
1841
+ {
1842
+ "epoch": 3.41688654353562,
1843
+ "grad_norm": 0.6202635765075684,
1844
+ "learning_rate": 0.0002,
1845
+ "loss": 0.8352,
1846
+ "step": 2590
1847
+ },
1848
+ {
1849
+ "epoch": 3.430079155672823,
1850
+ "grad_norm": 0.6981159448623657,
1851
+ "learning_rate": 0.0002,
1852
+ "loss": 0.7572,
1853
+ "step": 2600
1854
+ },
1855
+ {
1856
+ "epoch": 3.4432717678100264,
1857
+ "grad_norm": 0.6611084342002869,
1858
+ "learning_rate": 0.0002,
1859
+ "loss": 0.7846,
1860
+ "step": 2610
1861
+ },
1862
+ {
1863
+ "epoch": 3.4564643799472297,
1864
+ "grad_norm": 0.5727696418762207,
1865
+ "learning_rate": 0.0002,
1866
+ "loss": 0.7503,
1867
+ "step": 2620
1868
+ },
1869
+ {
1870
+ "epoch": 3.469656992084433,
1871
+ "grad_norm": 1.2354545593261719,
1872
+ "learning_rate": 0.0002,
1873
+ "loss": 0.8427,
1874
+ "step": 2630
1875
+ },
1876
+ {
1877
+ "epoch": 3.4828496042216357,
1878
+ "grad_norm": 0.6347638368606567,
1879
+ "learning_rate": 0.0002,
1880
+ "loss": 0.7747,
1881
+ "step": 2640
1882
+ },
1883
+ {
1884
+ "epoch": 3.496042216358839,
1885
+ "grad_norm": 0.6975704431533813,
1886
+ "learning_rate": 0.0002,
1887
+ "loss": 0.8426,
1888
+ "step": 2650
1889
+ },
1890
+ {
1891
+ "epoch": 3.509234828496042,
1892
+ "grad_norm": 0.6569573879241943,
1893
+ "learning_rate": 0.0002,
1894
+ "loss": 0.8773,
1895
+ "step": 2660
1896
+ },
1897
+ {
1898
+ "epoch": 3.5224274406332454,
1899
+ "grad_norm": 0.6979609131813049,
1900
+ "learning_rate": 0.0002,
1901
+ "loss": 0.7908,
1902
+ "step": 2670
1903
+ },
1904
+ {
1905
+ "epoch": 3.5356200527704487,
1906
+ "grad_norm": 0.6287988424301147,
1907
+ "learning_rate": 0.0002,
1908
+ "loss": 0.8254,
1909
+ "step": 2680
1910
+ },
1911
+ {
1912
+ "epoch": 3.5488126649076515,
1913
+ "grad_norm": 0.8682637214660645,
1914
+ "learning_rate": 0.0002,
1915
+ "loss": 0.7815,
1916
+ "step": 2690
1917
+ },
1918
+ {
1919
+ "epoch": 3.5620052770448547,
1920
+ "grad_norm": 0.7062831521034241,
1921
+ "learning_rate": 0.0002,
1922
+ "loss": 0.7566,
1923
+ "step": 2700
1924
+ },
1925
+ {
1926
+ "epoch": 3.575197889182058,
1927
+ "grad_norm": 1.0061452388763428,
1928
+ "learning_rate": 0.0002,
1929
+ "loss": 0.713,
1930
+ "step": 2710
1931
+ },
1932
+ {
1933
+ "epoch": 3.588390501319261,
1934
+ "grad_norm": 0.719097375869751,
1935
+ "learning_rate": 0.0002,
1936
+ "loss": 0.7738,
1937
+ "step": 2720
1938
+ },
1939
+ {
1940
+ "epoch": 3.6015831134564644,
1941
+ "grad_norm": 0.7583496570587158,
1942
+ "learning_rate": 0.0002,
1943
+ "loss": 0.8145,
1944
+ "step": 2730
1945
+ },
1946
+ {
1947
+ "epoch": 3.6147757255936677,
1948
+ "grad_norm": 0.7543531060218811,
1949
+ "learning_rate": 0.0002,
1950
+ "loss": 0.91,
1951
+ "step": 2740
1952
+ },
1953
+ {
1954
+ "epoch": 3.627968337730871,
1955
+ "grad_norm": 0.8873646855354309,
1956
+ "learning_rate": 0.0002,
1957
+ "loss": 0.8325,
1958
+ "step": 2750
1959
+ },
1960
+ {
1961
+ "epoch": 3.641160949868074,
1962
+ "grad_norm": 1.0657562017440796,
1963
+ "learning_rate": 0.0002,
1964
+ "loss": 0.7116,
1965
+ "step": 2760
1966
+ },
1967
+ {
1968
+ "epoch": 3.654353562005277,
1969
+ "grad_norm": 0.8641113638877869,
1970
+ "learning_rate": 0.0002,
1971
+ "loss": 0.8291,
1972
+ "step": 2770
1973
+ },
1974
+ {
1975
+ "epoch": 3.66754617414248,
1976
+ "grad_norm": 0.6620645523071289,
1977
+ "learning_rate": 0.0002,
1978
+ "loss": 0.8302,
1979
+ "step": 2780
1980
+ },
1981
+ {
1982
+ "epoch": 3.6807387862796834,
1983
+ "grad_norm": 0.6919541954994202,
1984
+ "learning_rate": 0.0002,
1985
+ "loss": 0.8261,
1986
+ "step": 2790
1987
+ },
1988
+ {
1989
+ "epoch": 3.6939313984168867,
1990
+ "grad_norm": 0.7305743098258972,
1991
+ "learning_rate": 0.0002,
1992
+ "loss": 0.8388,
1993
+ "step": 2800
1994
+ },
1995
+ {
1996
+ "epoch": 3.7071240105540895,
1997
+ "grad_norm": 0.7464777827262878,
1998
+ "learning_rate": 0.0002,
1999
+ "loss": 0.8053,
2000
+ "step": 2810
2001
+ },
2002
+ {
2003
+ "epoch": 3.7203166226912927,
2004
+ "grad_norm": 0.8067063093185425,
2005
+ "learning_rate": 0.0002,
2006
+ "loss": 0.8019,
2007
+ "step": 2820
2008
+ },
2009
+ {
2010
+ "epoch": 3.733509234828496,
2011
+ "grad_norm": 0.7789416313171387,
2012
+ "learning_rate": 0.0002,
2013
+ "loss": 0.8259,
2014
+ "step": 2830
2015
+ },
2016
+ {
2017
+ "epoch": 3.746701846965699,
2018
+ "grad_norm": 0.507529079914093,
2019
+ "learning_rate": 0.0002,
2020
+ "loss": 0.774,
2021
+ "step": 2840
2022
+ },
2023
+ {
2024
+ "epoch": 3.7598944591029024,
2025
+ "grad_norm": 0.6509260535240173,
2026
+ "learning_rate": 0.0002,
2027
+ "loss": 0.832,
2028
+ "step": 2850
2029
+ },
2030
+ {
2031
+ "epoch": 3.7730870712401057,
2032
+ "grad_norm": 0.9141367673873901,
2033
+ "learning_rate": 0.0002,
2034
+ "loss": 0.8257,
2035
+ "step": 2860
2036
+ },
2037
+ {
2038
+ "epoch": 3.786279683377309,
2039
+ "grad_norm": 0.7852635979652405,
2040
+ "learning_rate": 0.0002,
2041
+ "loss": 0.9436,
2042
+ "step": 2870
2043
+ },
2044
+ {
2045
+ "epoch": 3.7994722955145117,
2046
+ "grad_norm": 0.5340318083763123,
2047
+ "learning_rate": 0.0002,
2048
+ "loss": 0.8842,
2049
+ "step": 2880
2050
+ },
2051
+ {
2052
+ "epoch": 3.812664907651715,
2053
+ "grad_norm": 0.6246042847633362,
2054
+ "learning_rate": 0.0002,
2055
+ "loss": 0.7468,
2056
+ "step": 2890
2057
+ },
2058
+ {
2059
+ "epoch": 3.825857519788918,
2060
+ "grad_norm": 0.7064066529273987,
2061
+ "learning_rate": 0.0002,
2062
+ "loss": 0.8184,
2063
+ "step": 2900
2064
+ },
2065
+ {
2066
+ "epoch": 3.8390501319261214,
2067
+ "grad_norm": 0.6144065856933594,
2068
+ "learning_rate": 0.0002,
2069
+ "loss": 0.8515,
2070
+ "step": 2910
2071
+ },
2072
+ {
2073
+ "epoch": 3.8522427440633247,
2074
+ "grad_norm": 0.5268424153327942,
2075
+ "learning_rate": 0.0002,
2076
+ "loss": 0.7484,
2077
+ "step": 2920
2078
+ },
2079
+ {
2080
+ "epoch": 3.8654353562005275,
2081
+ "grad_norm": 0.9508116841316223,
2082
+ "learning_rate": 0.0002,
2083
+ "loss": 0.7594,
2084
+ "step": 2930
2085
+ },
2086
+ {
2087
+ "epoch": 3.8786279683377307,
2088
+ "grad_norm": 0.9133715629577637,
2089
+ "learning_rate": 0.0002,
2090
+ "loss": 0.8437,
2091
+ "step": 2940
2092
+ },
2093
+ {
2094
+ "epoch": 3.891820580474934,
2095
+ "grad_norm": 1.0144646167755127,
2096
+ "learning_rate": 0.0002,
2097
+ "loss": 0.8611,
2098
+ "step": 2950
2099
+ },
2100
+ {
2101
+ "epoch": 3.905013192612137,
2102
+ "grad_norm": 0.6397877931594849,
2103
+ "learning_rate": 0.0002,
2104
+ "loss": 0.8043,
2105
+ "step": 2960
2106
+ },
2107
+ {
2108
+ "epoch": 3.9182058047493404,
2109
+ "grad_norm": 0.734835147857666,
2110
+ "learning_rate": 0.0002,
2111
+ "loss": 0.8285,
2112
+ "step": 2970
2113
+ },
2114
+ {
2115
+ "epoch": 3.9313984168865437,
2116
+ "grad_norm": 0.784853994846344,
2117
+ "learning_rate": 0.0002,
2118
+ "loss": 0.7831,
2119
+ "step": 2980
2120
+ },
2121
+ {
2122
+ "epoch": 3.944591029023747,
2123
+ "grad_norm": 0.805831789970398,
2124
+ "learning_rate": 0.0002,
2125
+ "loss": 0.8148,
2126
+ "step": 2990
2127
+ },
2128
+ {
2129
+ "epoch": 3.9577836411609497,
2130
+ "grad_norm": 0.6299595236778259,
2131
+ "learning_rate": 0.0002,
2132
+ "loss": 0.8252,
2133
+ "step": 3000
2134
+ },
2135
+ {
2136
+ "epoch": 3.970976253298153,
2137
+ "grad_norm": 0.6264058351516724,
2138
+ "learning_rate": 0.0002,
2139
+ "loss": 0.8244,
2140
+ "step": 3010
2141
+ },
2142
+ {
2143
+ "epoch": 3.984168865435356,
2144
+ "grad_norm": 0.6419739723205566,
2145
+ "learning_rate": 0.0002,
2146
+ "loss": 0.8185,
2147
+ "step": 3020
2148
+ },
2149
+ {
2150
+ "epoch": 3.9973614775725594,
2151
+ "grad_norm": 0.7737036943435669,
2152
+ "learning_rate": 0.0002,
2153
+ "loss": 0.8174,
2154
+ "step": 3030
2155
+ },
2156
+ {
2157
+ "epoch": 4.0,
2158
+ "eval_loss": 1.2454297542572021,
2159
+ "eval_runtime": 71.8558,
2160
+ "eval_samples_per_second": 5.998,
2161
+ "eval_steps_per_second": 0.752,
2162
+ "step": 3032
2163
+ }
2164
+ ],
2165
+ "logging_steps": 10,
2166
+ "max_steps": 6064,
2167
+ "num_input_tokens_seen": 0,
2168
+ "num_train_epochs": 8,
2169
+ "save_steps": 200,
2170
+ "stateful_callbacks": {
2171
+ "TrainerControl": {
2172
+ "args": {
2173
+ "should_epoch_stop": false,
2174
+ "should_evaluate": false,
2175
+ "should_log": false,
2176
+ "should_save": true,
2177
+ "should_training_stop": false
2178
+ },
2179
+ "attributes": {}
2180
+ }
2181
+ },
2182
+ "total_flos": 1.4031417107703398e+17,
2183
+ "train_batch_size": 1,
2184
+ "trial_name": null,
2185
+ "trial_params": null
2186
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3032/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e04722e246164eebe6b4f70dd50fe946c936a2bd25edd75bcedcfd4c7ff9474e
3
+ size 5624
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0abb8ce220189985e1d92cd920ffac58338081eb5a9b06dd4e2a9f59804fb63
3
+ size 109069176
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:853504d70ffcd4907d6951e8dfe1974e9fb551fb777f7c82dbe48509cc78e7bf
3
+ size 55532666
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b7e36910ca9df80c1bd60717cb32b049b54870c08d539535c378fece8e4068
3
+ size 14244
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89147f06daea8413d82a4b7b928b4c476779123cd562b0a5ce13276f70c01eaa
3
+ size 1064
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/trainer_state.json ADDED
@@ -0,0 +1,2726 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1874967813491821,
3
+ "best_model_checkpoint": "outputs-001/Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-1516",
4
+ "epoch": 5.0,
5
+ "eval_steps": 10,
6
+ "global_step": 3790,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.013192612137203167,
13
+ "grad_norm": 0.7545632123947144,
14
+ "learning_rate": 0.0002,
15
+ "loss": 1.9466,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.026385224274406333,
20
+ "grad_norm": 0.5787661075592041,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.4909,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0395778364116095,
27
+ "grad_norm": 0.8616093993186951,
28
+ "learning_rate": 0.0002,
29
+ "loss": 1.3906,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.052770448548812667,
34
+ "grad_norm": 0.42088547348976135,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.4116,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.06596306068601583,
41
+ "grad_norm": 0.47704678773880005,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.3446,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.079155672823219,
48
+ "grad_norm": 0.5763994455337524,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.2476,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.09234828496042216,
55
+ "grad_norm": 0.4579846262931824,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.2268,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.10554089709762533,
62
+ "grad_norm": 0.46623846888542175,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.415,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.11873350923482849,
69
+ "grad_norm": 0.4206956624984741,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.2849,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.13192612137203166,
76
+ "grad_norm": 0.41896629333496094,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.1608,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.14511873350923482,
83
+ "grad_norm": 0.3459089398384094,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.2617,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.158311345646438,
90
+ "grad_norm": 0.4587327837944031,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.2858,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.17150395778364116,
97
+ "grad_norm": 0.433525413274765,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.2241,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.18469656992084432,
104
+ "grad_norm": 0.39253175258636475,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.2269,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.19788918205804748,
111
+ "grad_norm": 0.3602290749549866,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.2224,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.21108179419525067,
118
+ "grad_norm": 0.41160839796066284,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.2834,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.22427440633245382,
125
+ "grad_norm": 0.7213630080223083,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.1986,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.23746701846965698,
132
+ "grad_norm": 0.39086055755615234,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.2215,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.25065963060686014,
139
+ "grad_norm": 0.4465520977973938,
140
+ "learning_rate": 0.0002,
141
+ "loss": 1.3315,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.2638522427440633,
146
+ "grad_norm": 1.814679741859436,
147
+ "learning_rate": 0.0002,
148
+ "loss": 1.3798,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.2770448548812665,
153
+ "grad_norm": 0.5026423931121826,
154
+ "learning_rate": 0.0002,
155
+ "loss": 1.2259,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.29023746701846964,
160
+ "grad_norm": 0.4156292974948883,
161
+ "learning_rate": 0.0002,
162
+ "loss": 1.3306,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.3034300791556728,
167
+ "grad_norm": 0.40813493728637695,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.266,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.316622691292876,
174
+ "grad_norm": 0.3304787874221802,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.1533,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.32981530343007914,
181
+ "grad_norm": 0.46139976382255554,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.3154,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.34300791556728233,
188
+ "grad_norm": 0.37518271803855896,
189
+ "learning_rate": 0.0002,
190
+ "loss": 1.1365,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.3562005277044855,
195
+ "grad_norm": 0.35586467385292053,
196
+ "learning_rate": 0.0002,
197
+ "loss": 1.2004,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.36939313984168864,
202
+ "grad_norm": 0.32441186904907227,
203
+ "learning_rate": 0.0002,
204
+ "loss": 1.2609,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.38258575197889183,
209
+ "grad_norm": 0.3198683261871338,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.212,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.39577836411609496,
216
+ "grad_norm": 0.33663108944892883,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.2465,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.40897097625329815,
223
+ "grad_norm": 0.3711244761943817,
224
+ "learning_rate": 0.0002,
225
+ "loss": 1.1702,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.42216358839050133,
230
+ "grad_norm": 0.3209651708602905,
231
+ "learning_rate": 0.0002,
232
+ "loss": 1.0871,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.43535620052770446,
237
+ "grad_norm": 0.5152716040611267,
238
+ "learning_rate": 0.0002,
239
+ "loss": 1.2728,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.44854881266490765,
244
+ "grad_norm": 0.5431376695632935,
245
+ "learning_rate": 0.0002,
246
+ "loss": 1.1833,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.46174142480211083,
251
+ "grad_norm": 0.3069997727870941,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.1344,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.47493403693931396,
258
+ "grad_norm": 0.34260064363479614,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.2742,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.48812664907651715,
265
+ "grad_norm": 0.345653235912323,
266
+ "learning_rate": 0.0002,
267
+ "loss": 1.3161,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.5013192612137203,
272
+ "grad_norm": 0.46222734451293945,
273
+ "learning_rate": 0.0002,
274
+ "loss": 1.1552,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.5145118733509235,
279
+ "grad_norm": 0.27301734685897827,
280
+ "learning_rate": 0.0002,
281
+ "loss": 1.0616,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.5277044854881267,
286
+ "grad_norm": 0.29048439860343933,
287
+ "learning_rate": 0.0002,
288
+ "loss": 1.1944,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.5408970976253298,
293
+ "grad_norm": 0.32927802205085754,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.0956,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.554089709762533,
300
+ "grad_norm": 0.3336397409439087,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.2362,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.5672823218997362,
307
+ "grad_norm": 0.4007597267627716,
308
+ "learning_rate": 0.0002,
309
+ "loss": 1.1445,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.5804749340369393,
314
+ "grad_norm": 0.36144956946372986,
315
+ "learning_rate": 0.0002,
316
+ "loss": 1.2731,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.5936675461741425,
321
+ "grad_norm": 0.6331009864807129,
322
+ "learning_rate": 0.0002,
323
+ "loss": 1.1604,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.6068601583113457,
328
+ "grad_norm": 0.41469088196754456,
329
+ "learning_rate": 0.0002,
330
+ "loss": 1.1692,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.6200527704485488,
335
+ "grad_norm": 0.4388185143470764,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.2372,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.633245382585752,
342
+ "grad_norm": 0.3738141655921936,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.2541,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.6464379947229552,
349
+ "grad_norm": 0.7212023138999939,
350
+ "learning_rate": 0.0002,
351
+ "loss": 1.1265,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.6596306068601583,
356
+ "grad_norm": 0.2972351014614105,
357
+ "learning_rate": 0.0002,
358
+ "loss": 1.2786,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.6728232189973615,
363
+ "grad_norm": 0.45293179154396057,
364
+ "learning_rate": 0.0002,
365
+ "loss": 1.1739,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.6860158311345647,
370
+ "grad_norm": 0.4319860637187958,
371
+ "learning_rate": 0.0002,
372
+ "loss": 1.255,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.6992084432717678,
377
+ "grad_norm": 0.3050215542316437,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.0959,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.712401055408971,
384
+ "grad_norm": 0.3552611172199249,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.1608,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.7255936675461742,
391
+ "grad_norm": 0.3631151020526886,
392
+ "learning_rate": 0.0002,
393
+ "loss": 1.2546,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.7387862796833773,
398
+ "grad_norm": 0.28177931904792786,
399
+ "learning_rate": 0.0002,
400
+ "loss": 1.1371,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.7519788918205804,
405
+ "grad_norm": 0.359764039516449,
406
+ "learning_rate": 0.0002,
407
+ "loss": 1.2081,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.7651715039577837,
412
+ "grad_norm": 0.3970327377319336,
413
+ "learning_rate": 0.0002,
414
+ "loss": 1.1356,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.7783641160949868,
419
+ "grad_norm": 0.3541001081466675,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.309,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.7915567282321899,
426
+ "grad_norm": 0.3478573262691498,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.2061,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.8047493403693932,
433
+ "grad_norm": 0.3900321424007416,
434
+ "learning_rate": 0.0002,
435
+ "loss": 1.1864,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.8179419525065963,
440
+ "grad_norm": 0.3443238437175751,
441
+ "learning_rate": 0.0002,
442
+ "loss": 1.1358,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.8311345646437994,
447
+ "grad_norm": 0.44238781929016113,
448
+ "learning_rate": 0.0002,
449
+ "loss": 1.3232,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.8443271767810027,
454
+ "grad_norm": 0.36339467763900757,
455
+ "learning_rate": 0.0002,
456
+ "loss": 1.1247,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.8575197889182058,
461
+ "grad_norm": 0.6243070363998413,
462
+ "learning_rate": 0.0002,
463
+ "loss": 1.1049,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.8707124010554089,
468
+ "grad_norm": 0.3209173381328583,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.1943,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.8839050131926122,
475
+ "grad_norm": 0.35017991065979004,
476
+ "learning_rate": 0.0002,
477
+ "loss": 1.1927,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.8970976253298153,
482
+ "grad_norm": 0.3247159421443939,
483
+ "learning_rate": 0.0002,
484
+ "loss": 1.1603,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.9102902374670184,
489
+ "grad_norm": 0.4091894030570984,
490
+ "learning_rate": 0.0002,
491
+ "loss": 1.2298,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.9234828496042217,
496
+ "grad_norm": 0.3975585997104645,
497
+ "learning_rate": 0.0002,
498
+ "loss": 1.2756,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.9366754617414248,
503
+ "grad_norm": 0.3666245937347412,
504
+ "learning_rate": 0.0002,
505
+ "loss": 1.281,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.9498680738786279,
510
+ "grad_norm": 0.45216917991638184,
511
+ "learning_rate": 0.0002,
512
+ "loss": 1.2855,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.9630606860158312,
517
+ "grad_norm": 0.36108118295669556,
518
+ "learning_rate": 0.0002,
519
+ "loss": 1.2217,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.9762532981530343,
524
+ "grad_norm": 0.44550251960754395,
525
+ "learning_rate": 0.0002,
526
+ "loss": 1.17,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.9894459102902374,
531
+ "grad_norm": 0.29801255464553833,
532
+ "learning_rate": 0.0002,
533
+ "loss": 1.0672,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 1.0,
538
+ "eval_loss": 1.203244686126709,
539
+ "eval_runtime": 76.0457,
540
+ "eval_samples_per_second": 5.668,
541
+ "eval_steps_per_second": 0.71,
542
+ "step": 758
543
+ },
544
+ {
545
+ "epoch": 1.0026385224274406,
546
+ "grad_norm": 0.4096551239490509,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.0748,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.0158311345646438,
553
+ "grad_norm": 0.2649582326412201,
554
+ "learning_rate": 0.0002,
555
+ "loss": 1.1537,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.029023746701847,
560
+ "grad_norm": 0.3100722134113312,
561
+ "learning_rate": 0.0002,
562
+ "loss": 1.1676,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.04221635883905,
567
+ "grad_norm": 0.3911755383014679,
568
+ "learning_rate": 0.0002,
569
+ "loss": 1.1736,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.0554089709762533,
574
+ "grad_norm": 0.4600953757762909,
575
+ "learning_rate": 0.0002,
576
+ "loss": 1.0354,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.0686015831134565,
581
+ "grad_norm": 0.28671619296073914,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.2869,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.0817941952506596,
588
+ "grad_norm": 0.47282642126083374,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.1441,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.0949868073878628,
595
+ "grad_norm": 0.690073549747467,
596
+ "learning_rate": 0.0002,
597
+ "loss": 1.1368,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.108179419525066,
602
+ "grad_norm": 0.7317902445793152,
603
+ "learning_rate": 0.0002,
604
+ "loss": 0.9944,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.121372031662269,
609
+ "grad_norm": 0.44215938448905945,
610
+ "learning_rate": 0.0002,
611
+ "loss": 1.108,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.1345646437994723,
616
+ "grad_norm": 0.33875149488449097,
617
+ "learning_rate": 0.0002,
618
+ "loss": 1.0558,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.1477572559366755,
623
+ "grad_norm": 0.3700002431869507,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.0471,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.1609498680738786,
630
+ "grad_norm": 0.41173291206359863,
631
+ "learning_rate": 0.0002,
632
+ "loss": 1.0121,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.1741424802110818,
637
+ "grad_norm": 0.5253589749336243,
638
+ "learning_rate": 0.0002,
639
+ "loss": 1.0312,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.187335092348285,
644
+ "grad_norm": 0.3912237286567688,
645
+ "learning_rate": 0.0002,
646
+ "loss": 1.2238,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.200527704485488,
651
+ "grad_norm": 0.40990331768989563,
652
+ "learning_rate": 0.0002,
653
+ "loss": 0.9434,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.2137203166226913,
658
+ "grad_norm": 0.40377968549728394,
659
+ "learning_rate": 0.0002,
660
+ "loss": 1.0493,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.2269129287598945,
665
+ "grad_norm": 0.4605846405029297,
666
+ "learning_rate": 0.0002,
667
+ "loss": 1.1496,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.2401055408970976,
672
+ "grad_norm": 0.31564897298812866,
673
+ "learning_rate": 0.0002,
674
+ "loss": 1.1173,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.2532981530343008,
679
+ "grad_norm": 0.39808550477027893,
680
+ "learning_rate": 0.0002,
681
+ "loss": 1.0547,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 1.266490765171504,
686
+ "grad_norm": 0.3762115240097046,
687
+ "learning_rate": 0.0002,
688
+ "loss": 1.1367,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 1.279683377308707,
693
+ "grad_norm": 0.4174984097480774,
694
+ "learning_rate": 0.0002,
695
+ "loss": 1.1596,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 1.2928759894459103,
700
+ "grad_norm": 0.5263054966926575,
701
+ "learning_rate": 0.0002,
702
+ "loss": 1.1327,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 1.3060686015831133,
707
+ "grad_norm": 0.41673699021339417,
708
+ "learning_rate": 0.0002,
709
+ "loss": 1.0339,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 1.3192612137203166,
714
+ "grad_norm": 0.9613684415817261,
715
+ "learning_rate": 0.0002,
716
+ "loss": 1.1198,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 1.3324538258575198,
721
+ "grad_norm": 0.3690216839313507,
722
+ "learning_rate": 0.0002,
723
+ "loss": 1.0444,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 1.345646437994723,
728
+ "grad_norm": 0.521821141242981,
729
+ "learning_rate": 0.0002,
730
+ "loss": 1.0473,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 1.358839050131926,
735
+ "grad_norm": 0.3353094160556793,
736
+ "learning_rate": 0.0002,
737
+ "loss": 1.1065,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 1.3720316622691293,
742
+ "grad_norm": 0.3843843936920166,
743
+ "learning_rate": 0.0002,
744
+ "loss": 1.1286,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 1.3852242744063323,
749
+ "grad_norm": 0.372514545917511,
750
+ "learning_rate": 0.0002,
751
+ "loss": 1.1369,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 1.3984168865435356,
756
+ "grad_norm": 0.34537771344184875,
757
+ "learning_rate": 0.0002,
758
+ "loss": 1.0041,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 1.4116094986807388,
763
+ "grad_norm": 0.45349085330963135,
764
+ "learning_rate": 0.0002,
765
+ "loss": 1.0251,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 1.424802110817942,
770
+ "grad_norm": 0.5120177268981934,
771
+ "learning_rate": 0.0002,
772
+ "loss": 1.1873,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 1.437994722955145,
777
+ "grad_norm": 0.42800238728523254,
778
+ "learning_rate": 0.0002,
779
+ "loss": 1.0872,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 1.4511873350923483,
784
+ "grad_norm": 0.343832790851593,
785
+ "learning_rate": 0.0002,
786
+ "loss": 1.0734,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 1.4643799472295513,
791
+ "grad_norm": 0.3829841911792755,
792
+ "learning_rate": 0.0002,
793
+ "loss": 1.1286,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 1.4775725593667546,
798
+ "grad_norm": 0.4289931058883667,
799
+ "learning_rate": 0.0002,
800
+ "loss": 1.1268,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 1.4907651715039578,
805
+ "grad_norm": 0.42750850319862366,
806
+ "learning_rate": 0.0002,
807
+ "loss": 1.0676,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 1.503957783641161,
812
+ "grad_norm": 0.34328413009643555,
813
+ "learning_rate": 0.0002,
814
+ "loss": 1.072,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 1.517150395778364,
819
+ "grad_norm": 0.349096417427063,
820
+ "learning_rate": 0.0002,
821
+ "loss": 1.0863,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 1.5303430079155673,
826
+ "grad_norm": 0.7700717449188232,
827
+ "learning_rate": 0.0002,
828
+ "loss": 1.1462,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 1.5435356200527703,
833
+ "grad_norm": 0.39294949173927307,
834
+ "learning_rate": 0.0002,
835
+ "loss": 0.9528,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 1.5567282321899736,
840
+ "grad_norm": 0.36173608899116516,
841
+ "learning_rate": 0.0002,
842
+ "loss": 1.1603,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 1.5699208443271768,
847
+ "grad_norm": 0.6034277677536011,
848
+ "learning_rate": 0.0002,
849
+ "loss": 1.1508,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 1.58311345646438,
854
+ "grad_norm": 0.36694103479385376,
855
+ "learning_rate": 0.0002,
856
+ "loss": 1.0105,
857
+ "step": 1200
858
+ },
859
+ {
860
+ "epoch": 1.596306068601583,
861
+ "grad_norm": 0.4727209508419037,
862
+ "learning_rate": 0.0002,
863
+ "loss": 1.1479,
864
+ "step": 1210
865
+ },
866
+ {
867
+ "epoch": 1.6094986807387863,
868
+ "grad_norm": 0.6482883095741272,
869
+ "learning_rate": 0.0002,
870
+ "loss": 1.0689,
871
+ "step": 1220
872
+ },
873
+ {
874
+ "epoch": 1.6226912928759893,
875
+ "grad_norm": 0.5238035917282104,
876
+ "learning_rate": 0.0002,
877
+ "loss": 1.1405,
878
+ "step": 1230
879
+ },
880
+ {
881
+ "epoch": 1.6358839050131926,
882
+ "grad_norm": 0.4812222421169281,
883
+ "learning_rate": 0.0002,
884
+ "loss": 1.0596,
885
+ "step": 1240
886
+ },
887
+ {
888
+ "epoch": 1.6490765171503958,
889
+ "grad_norm": 0.7131702303886414,
890
+ "learning_rate": 0.0002,
891
+ "loss": 1.2729,
892
+ "step": 1250
893
+ },
894
+ {
895
+ "epoch": 1.662269129287599,
896
+ "grad_norm": 0.3803327977657318,
897
+ "learning_rate": 0.0002,
898
+ "loss": 0.9832,
899
+ "step": 1260
900
+ },
901
+ {
902
+ "epoch": 1.675461741424802,
903
+ "grad_norm": 0.3745088577270508,
904
+ "learning_rate": 0.0002,
905
+ "loss": 1.1433,
906
+ "step": 1270
907
+ },
908
+ {
909
+ "epoch": 1.6886543535620053,
910
+ "grad_norm": 0.4427378475666046,
911
+ "learning_rate": 0.0002,
912
+ "loss": 1.1018,
913
+ "step": 1280
914
+ },
915
+ {
916
+ "epoch": 1.7018469656992083,
917
+ "grad_norm": 0.797478973865509,
918
+ "learning_rate": 0.0002,
919
+ "loss": 1.0619,
920
+ "step": 1290
921
+ },
922
+ {
923
+ "epoch": 1.7150395778364116,
924
+ "grad_norm": 0.503620982170105,
925
+ "learning_rate": 0.0002,
926
+ "loss": 1.0853,
927
+ "step": 1300
928
+ },
929
+ {
930
+ "epoch": 1.7282321899736148,
931
+ "grad_norm": 0.4132426381111145,
932
+ "learning_rate": 0.0002,
933
+ "loss": 1.1324,
934
+ "step": 1310
935
+ },
936
+ {
937
+ "epoch": 1.741424802110818,
938
+ "grad_norm": 0.41811656951904297,
939
+ "learning_rate": 0.0002,
940
+ "loss": 1.172,
941
+ "step": 1320
942
+ },
943
+ {
944
+ "epoch": 1.754617414248021,
945
+ "grad_norm": 0.40647849440574646,
946
+ "learning_rate": 0.0002,
947
+ "loss": 1.0903,
948
+ "step": 1330
949
+ },
950
+ {
951
+ "epoch": 1.767810026385224,
952
+ "grad_norm": 0.42138347029685974,
953
+ "learning_rate": 0.0002,
954
+ "loss": 1.1316,
955
+ "step": 1340
956
+ },
957
+ {
958
+ "epoch": 1.7810026385224274,
959
+ "grad_norm": 0.46523579955101013,
960
+ "learning_rate": 0.0002,
961
+ "loss": 0.9955,
962
+ "step": 1350
963
+ },
964
+ {
965
+ "epoch": 1.7941952506596306,
966
+ "grad_norm": 0.39760419726371765,
967
+ "learning_rate": 0.0002,
968
+ "loss": 1.0307,
969
+ "step": 1360
970
+ },
971
+ {
972
+ "epoch": 1.8073878627968338,
973
+ "grad_norm": 0.37993717193603516,
974
+ "learning_rate": 0.0002,
975
+ "loss": 1.1218,
976
+ "step": 1370
977
+ },
978
+ {
979
+ "epoch": 1.820580474934037,
980
+ "grad_norm": 0.5404181480407715,
981
+ "learning_rate": 0.0002,
982
+ "loss": 1.0921,
983
+ "step": 1380
984
+ },
985
+ {
986
+ "epoch": 1.83377308707124,
987
+ "grad_norm": 0.4385245740413666,
988
+ "learning_rate": 0.0002,
989
+ "loss": 1.0903,
990
+ "step": 1390
991
+ },
992
+ {
993
+ "epoch": 1.8469656992084431,
994
+ "grad_norm": 0.529797375202179,
995
+ "learning_rate": 0.0002,
996
+ "loss": 1.1175,
997
+ "step": 1400
998
+ },
999
+ {
1000
+ "epoch": 1.8601583113456464,
1001
+ "grad_norm": 0.481567919254303,
1002
+ "learning_rate": 0.0002,
1003
+ "loss": 1.0577,
1004
+ "step": 1410
1005
+ },
1006
+ {
1007
+ "epoch": 1.8733509234828496,
1008
+ "grad_norm": 0.34787362813949585,
1009
+ "learning_rate": 0.0002,
1010
+ "loss": 1.0581,
1011
+ "step": 1420
1012
+ },
1013
+ {
1014
+ "epoch": 1.8865435356200528,
1015
+ "grad_norm": 0.6402362585067749,
1016
+ "learning_rate": 0.0002,
1017
+ "loss": 1.0536,
1018
+ "step": 1430
1019
+ },
1020
+ {
1021
+ "epoch": 1.899736147757256,
1022
+ "grad_norm": 0.3461322784423828,
1023
+ "learning_rate": 0.0002,
1024
+ "loss": 1.0787,
1025
+ "step": 1440
1026
+ },
1027
+ {
1028
+ "epoch": 1.912928759894459,
1029
+ "grad_norm": 0.44005653262138367,
1030
+ "learning_rate": 0.0002,
1031
+ "loss": 1.0925,
1032
+ "step": 1450
1033
+ },
1034
+ {
1035
+ "epoch": 1.9261213720316621,
1036
+ "grad_norm": 0.4064280688762665,
1037
+ "learning_rate": 0.0002,
1038
+ "loss": 1.0414,
1039
+ "step": 1460
1040
+ },
1041
+ {
1042
+ "epoch": 1.9393139841688654,
1043
+ "grad_norm": 0.5236523151397705,
1044
+ "learning_rate": 0.0002,
1045
+ "loss": 1.0608,
1046
+ "step": 1470
1047
+ },
1048
+ {
1049
+ "epoch": 1.9525065963060686,
1050
+ "grad_norm": 0.41030219197273254,
1051
+ "learning_rate": 0.0002,
1052
+ "loss": 1.0572,
1053
+ "step": 1480
1054
+ },
1055
+ {
1056
+ "epoch": 1.9656992084432718,
1057
+ "grad_norm": 0.39805835485458374,
1058
+ "learning_rate": 0.0002,
1059
+ "loss": 1.1204,
1060
+ "step": 1490
1061
+ },
1062
+ {
1063
+ "epoch": 1.978891820580475,
1064
+ "grad_norm": 0.42974501848220825,
1065
+ "learning_rate": 0.0002,
1066
+ "loss": 1.0364,
1067
+ "step": 1500
1068
+ },
1069
+ {
1070
+ "epoch": 1.992084432717678,
1071
+ "grad_norm": 0.4688243865966797,
1072
+ "learning_rate": 0.0002,
1073
+ "loss": 1.1169,
1074
+ "step": 1510
1075
+ },
1076
+ {
1077
+ "epoch": 2.0,
1078
+ "eval_loss": 1.1874967813491821,
1079
+ "eval_runtime": 71.9523,
1080
+ "eval_samples_per_second": 5.99,
1081
+ "eval_steps_per_second": 0.75,
1082
+ "step": 1516
1083
+ },
1084
+ {
1085
+ "epoch": 2.005277044854881,
1086
+ "grad_norm": 0.4121631383895874,
1087
+ "learning_rate": 0.0002,
1088
+ "loss": 1.0401,
1089
+ "step": 1520
1090
+ },
1091
+ {
1092
+ "epoch": 2.0184696569920844,
1093
+ "grad_norm": 0.4844197928905487,
1094
+ "learning_rate": 0.0002,
1095
+ "loss": 0.9384,
1096
+ "step": 1530
1097
+ },
1098
+ {
1099
+ "epoch": 2.0316622691292876,
1100
+ "grad_norm": 0.45408546924591064,
1101
+ "learning_rate": 0.0002,
1102
+ "loss": 0.8686,
1103
+ "step": 1540
1104
+ },
1105
+ {
1106
+ "epoch": 2.044854881266491,
1107
+ "grad_norm": 0.48662951588630676,
1108
+ "learning_rate": 0.0002,
1109
+ "loss": 1.0399,
1110
+ "step": 1550
1111
+ },
1112
+ {
1113
+ "epoch": 2.058047493403694,
1114
+ "grad_norm": 0.7195899486541748,
1115
+ "learning_rate": 0.0002,
1116
+ "loss": 0.936,
1117
+ "step": 1560
1118
+ },
1119
+ {
1120
+ "epoch": 2.0712401055408973,
1121
+ "grad_norm": 0.5071077346801758,
1122
+ "learning_rate": 0.0002,
1123
+ "loss": 0.9486,
1124
+ "step": 1570
1125
+ },
1126
+ {
1127
+ "epoch": 2.0844327176781,
1128
+ "grad_norm": 0.7473958730697632,
1129
+ "learning_rate": 0.0002,
1130
+ "loss": 1.0055,
1131
+ "step": 1580
1132
+ },
1133
+ {
1134
+ "epoch": 2.0976253298153034,
1135
+ "grad_norm": 0.5509232878684998,
1136
+ "learning_rate": 0.0002,
1137
+ "loss": 0.8309,
1138
+ "step": 1590
1139
+ },
1140
+ {
1141
+ "epoch": 2.1108179419525066,
1142
+ "grad_norm": 0.5108042359352112,
1143
+ "learning_rate": 0.0002,
1144
+ "loss": 0.9181,
1145
+ "step": 1600
1146
+ },
1147
+ {
1148
+ "epoch": 2.12401055408971,
1149
+ "grad_norm": 0.42331448197364807,
1150
+ "learning_rate": 0.0002,
1151
+ "loss": 0.9499,
1152
+ "step": 1610
1153
+ },
1154
+ {
1155
+ "epoch": 2.137203166226913,
1156
+ "grad_norm": 0.46621623635292053,
1157
+ "learning_rate": 0.0002,
1158
+ "loss": 0.9359,
1159
+ "step": 1620
1160
+ },
1161
+ {
1162
+ "epoch": 2.150395778364116,
1163
+ "grad_norm": 0.43802836537361145,
1164
+ "learning_rate": 0.0002,
1165
+ "loss": 0.9065,
1166
+ "step": 1630
1167
+ },
1168
+ {
1169
+ "epoch": 2.163588390501319,
1170
+ "grad_norm": 0.49908021092414856,
1171
+ "learning_rate": 0.0002,
1172
+ "loss": 0.9375,
1173
+ "step": 1640
1174
+ },
1175
+ {
1176
+ "epoch": 2.1767810026385224,
1177
+ "grad_norm": 0.4195636808872223,
1178
+ "learning_rate": 0.0002,
1179
+ "loss": 1.0389,
1180
+ "step": 1650
1181
+ },
1182
+ {
1183
+ "epoch": 2.1899736147757256,
1184
+ "grad_norm": 0.49515822529792786,
1185
+ "learning_rate": 0.0002,
1186
+ "loss": 0.8501,
1187
+ "step": 1660
1188
+ },
1189
+ {
1190
+ "epoch": 2.203166226912929,
1191
+ "grad_norm": 0.4607589542865753,
1192
+ "learning_rate": 0.0002,
1193
+ "loss": 1.0557,
1194
+ "step": 1670
1195
+ },
1196
+ {
1197
+ "epoch": 2.216358839050132,
1198
+ "grad_norm": 0.4489196836948395,
1199
+ "learning_rate": 0.0002,
1200
+ "loss": 1.0206,
1201
+ "step": 1680
1202
+ },
1203
+ {
1204
+ "epoch": 2.229551451187335,
1205
+ "grad_norm": 0.49300864338874817,
1206
+ "learning_rate": 0.0002,
1207
+ "loss": 0.9657,
1208
+ "step": 1690
1209
+ },
1210
+ {
1211
+ "epoch": 2.242744063324538,
1212
+ "grad_norm": 0.6624954342842102,
1213
+ "learning_rate": 0.0002,
1214
+ "loss": 0.8371,
1215
+ "step": 1700
1216
+ },
1217
+ {
1218
+ "epoch": 2.2559366754617414,
1219
+ "grad_norm": 0.8391500115394592,
1220
+ "learning_rate": 0.0002,
1221
+ "loss": 0.8555,
1222
+ "step": 1710
1223
+ },
1224
+ {
1225
+ "epoch": 2.2691292875989446,
1226
+ "grad_norm": 0.5193073749542236,
1227
+ "learning_rate": 0.0002,
1228
+ "loss": 1.0113,
1229
+ "step": 1720
1230
+ },
1231
+ {
1232
+ "epoch": 2.282321899736148,
1233
+ "grad_norm": 0.6180613040924072,
1234
+ "learning_rate": 0.0002,
1235
+ "loss": 0.9979,
1236
+ "step": 1730
1237
+ },
1238
+ {
1239
+ "epoch": 2.295514511873351,
1240
+ "grad_norm": 0.591191291809082,
1241
+ "learning_rate": 0.0002,
1242
+ "loss": 0.9579,
1243
+ "step": 1740
1244
+ },
1245
+ {
1246
+ "epoch": 2.308707124010554,
1247
+ "grad_norm": 0.546897828578949,
1248
+ "learning_rate": 0.0002,
1249
+ "loss": 0.8879,
1250
+ "step": 1750
1251
+ },
1252
+ {
1253
+ "epoch": 2.321899736147757,
1254
+ "grad_norm": 0.5470401644706726,
1255
+ "learning_rate": 0.0002,
1256
+ "loss": 0.9321,
1257
+ "step": 1760
1258
+ },
1259
+ {
1260
+ "epoch": 2.3350923482849604,
1261
+ "grad_norm": 0.4590282738208771,
1262
+ "learning_rate": 0.0002,
1263
+ "loss": 0.9104,
1264
+ "step": 1770
1265
+ },
1266
+ {
1267
+ "epoch": 2.3482849604221636,
1268
+ "grad_norm": 0.622164785861969,
1269
+ "learning_rate": 0.0002,
1270
+ "loss": 1.0384,
1271
+ "step": 1780
1272
+ },
1273
+ {
1274
+ "epoch": 2.361477572559367,
1275
+ "grad_norm": 0.5753812193870544,
1276
+ "learning_rate": 0.0002,
1277
+ "loss": 1.0297,
1278
+ "step": 1790
1279
+ },
1280
+ {
1281
+ "epoch": 2.37467018469657,
1282
+ "grad_norm": 0.47958624362945557,
1283
+ "learning_rate": 0.0002,
1284
+ "loss": 0.9569,
1285
+ "step": 1800
1286
+ },
1287
+ {
1288
+ "epoch": 2.387862796833773,
1289
+ "grad_norm": 0.48042672872543335,
1290
+ "learning_rate": 0.0002,
1291
+ "loss": 1.0519,
1292
+ "step": 1810
1293
+ },
1294
+ {
1295
+ "epoch": 2.401055408970976,
1296
+ "grad_norm": 0.44586366415023804,
1297
+ "learning_rate": 0.0002,
1298
+ "loss": 0.9042,
1299
+ "step": 1820
1300
+ },
1301
+ {
1302
+ "epoch": 2.4142480211081794,
1303
+ "grad_norm": 0.7239416837692261,
1304
+ "learning_rate": 0.0002,
1305
+ "loss": 0.9783,
1306
+ "step": 1830
1307
+ },
1308
+ {
1309
+ "epoch": 2.4274406332453826,
1310
+ "grad_norm": 0.5515341758728027,
1311
+ "learning_rate": 0.0002,
1312
+ "loss": 0.8818,
1313
+ "step": 1840
1314
+ },
1315
+ {
1316
+ "epoch": 2.440633245382586,
1317
+ "grad_norm": 0.6280064582824707,
1318
+ "learning_rate": 0.0002,
1319
+ "loss": 0.9503,
1320
+ "step": 1850
1321
+ },
1322
+ {
1323
+ "epoch": 2.453825857519789,
1324
+ "grad_norm": 0.4832057058811188,
1325
+ "learning_rate": 0.0002,
1326
+ "loss": 0.8943,
1327
+ "step": 1860
1328
+ },
1329
+ {
1330
+ "epoch": 2.467018469656992,
1331
+ "grad_norm": 0.5789321064949036,
1332
+ "learning_rate": 0.0002,
1333
+ "loss": 0.8744,
1334
+ "step": 1870
1335
+ },
1336
+ {
1337
+ "epoch": 2.480211081794195,
1338
+ "grad_norm": 0.48491886258125305,
1339
+ "learning_rate": 0.0002,
1340
+ "loss": 0.9332,
1341
+ "step": 1880
1342
+ },
1343
+ {
1344
+ "epoch": 2.4934036939313984,
1345
+ "grad_norm": 0.532365620136261,
1346
+ "learning_rate": 0.0002,
1347
+ "loss": 0.943,
1348
+ "step": 1890
1349
+ },
1350
+ {
1351
+ "epoch": 2.5065963060686016,
1352
+ "grad_norm": 0.7087852954864502,
1353
+ "learning_rate": 0.0002,
1354
+ "loss": 0.9734,
1355
+ "step": 1900
1356
+ },
1357
+ {
1358
+ "epoch": 2.519788918205805,
1359
+ "grad_norm": 0.48157402873039246,
1360
+ "learning_rate": 0.0002,
1361
+ "loss": 0.9767,
1362
+ "step": 1910
1363
+ },
1364
+ {
1365
+ "epoch": 2.532981530343008,
1366
+ "grad_norm": 0.5886041522026062,
1367
+ "learning_rate": 0.0002,
1368
+ "loss": 0.9851,
1369
+ "step": 1920
1370
+ },
1371
+ {
1372
+ "epoch": 2.5461741424802113,
1373
+ "grad_norm": 0.6332622766494751,
1374
+ "learning_rate": 0.0002,
1375
+ "loss": 1.0144,
1376
+ "step": 1930
1377
+ },
1378
+ {
1379
+ "epoch": 2.559366754617414,
1380
+ "grad_norm": 0.5463117957115173,
1381
+ "learning_rate": 0.0002,
1382
+ "loss": 0.9516,
1383
+ "step": 1940
1384
+ },
1385
+ {
1386
+ "epoch": 2.5725593667546174,
1387
+ "grad_norm": 0.5432228446006775,
1388
+ "learning_rate": 0.0002,
1389
+ "loss": 0.9373,
1390
+ "step": 1950
1391
+ },
1392
+ {
1393
+ "epoch": 2.5857519788918206,
1394
+ "grad_norm": 0.5929186940193176,
1395
+ "learning_rate": 0.0002,
1396
+ "loss": 0.8974,
1397
+ "step": 1960
1398
+ },
1399
+ {
1400
+ "epoch": 2.598944591029024,
1401
+ "grad_norm": 0.5120641589164734,
1402
+ "learning_rate": 0.0002,
1403
+ "loss": 1.0062,
1404
+ "step": 1970
1405
+ },
1406
+ {
1407
+ "epoch": 2.6121372031662267,
1408
+ "grad_norm": 0.5372339487075806,
1409
+ "learning_rate": 0.0002,
1410
+ "loss": 0.9143,
1411
+ "step": 1980
1412
+ },
1413
+ {
1414
+ "epoch": 2.62532981530343,
1415
+ "grad_norm": 0.5519838929176331,
1416
+ "learning_rate": 0.0002,
1417
+ "loss": 1.0786,
1418
+ "step": 1990
1419
+ },
1420
+ {
1421
+ "epoch": 2.638522427440633,
1422
+ "grad_norm": 0.7304037809371948,
1423
+ "learning_rate": 0.0002,
1424
+ "loss": 1.021,
1425
+ "step": 2000
1426
+ },
1427
+ {
1428
+ "epoch": 2.6517150395778364,
1429
+ "grad_norm": 0.6182340979576111,
1430
+ "learning_rate": 0.0002,
1431
+ "loss": 0.8708,
1432
+ "step": 2010
1433
+ },
1434
+ {
1435
+ "epoch": 2.6649076517150396,
1436
+ "grad_norm": 0.4874444305896759,
1437
+ "learning_rate": 0.0002,
1438
+ "loss": 1.0501,
1439
+ "step": 2020
1440
+ },
1441
+ {
1442
+ "epoch": 2.678100263852243,
1443
+ "grad_norm": 0.5850239396095276,
1444
+ "learning_rate": 0.0002,
1445
+ "loss": 0.9612,
1446
+ "step": 2030
1447
+ },
1448
+ {
1449
+ "epoch": 2.691292875989446,
1450
+ "grad_norm": 0.6495311856269836,
1451
+ "learning_rate": 0.0002,
1452
+ "loss": 0.9808,
1453
+ "step": 2040
1454
+ },
1455
+ {
1456
+ "epoch": 2.7044854881266494,
1457
+ "grad_norm": 1.002830147743225,
1458
+ "learning_rate": 0.0002,
1459
+ "loss": 1.0187,
1460
+ "step": 2050
1461
+ },
1462
+ {
1463
+ "epoch": 2.717678100263852,
1464
+ "grad_norm": 0.49076753854751587,
1465
+ "learning_rate": 0.0002,
1466
+ "loss": 1.0386,
1467
+ "step": 2060
1468
+ },
1469
+ {
1470
+ "epoch": 2.7308707124010554,
1471
+ "grad_norm": 0.4736326336860657,
1472
+ "learning_rate": 0.0002,
1473
+ "loss": 0.9416,
1474
+ "step": 2070
1475
+ },
1476
+ {
1477
+ "epoch": 2.7440633245382586,
1478
+ "grad_norm": 0.5527601838111877,
1479
+ "learning_rate": 0.0002,
1480
+ "loss": 0.8424,
1481
+ "step": 2080
1482
+ },
1483
+ {
1484
+ "epoch": 2.757255936675462,
1485
+ "grad_norm": 0.7295718193054199,
1486
+ "learning_rate": 0.0002,
1487
+ "loss": 0.9149,
1488
+ "step": 2090
1489
+ },
1490
+ {
1491
+ "epoch": 2.7704485488126647,
1492
+ "grad_norm": 0.5437536835670471,
1493
+ "learning_rate": 0.0002,
1494
+ "loss": 0.9032,
1495
+ "step": 2100
1496
+ },
1497
+ {
1498
+ "epoch": 2.783641160949868,
1499
+ "grad_norm": 0.5997128486633301,
1500
+ "learning_rate": 0.0002,
1501
+ "loss": 0.8254,
1502
+ "step": 2110
1503
+ },
1504
+ {
1505
+ "epoch": 2.796833773087071,
1506
+ "grad_norm": 0.6498191356658936,
1507
+ "learning_rate": 0.0002,
1508
+ "loss": 0.976,
1509
+ "step": 2120
1510
+ },
1511
+ {
1512
+ "epoch": 2.8100263852242744,
1513
+ "grad_norm": 0.5237268805503845,
1514
+ "learning_rate": 0.0002,
1515
+ "loss": 0.9543,
1516
+ "step": 2130
1517
+ },
1518
+ {
1519
+ "epoch": 2.8232189973614776,
1520
+ "grad_norm": 0.6033027172088623,
1521
+ "learning_rate": 0.0002,
1522
+ "loss": 0.9302,
1523
+ "step": 2140
1524
+ },
1525
+ {
1526
+ "epoch": 2.836411609498681,
1527
+ "grad_norm": 0.6077138781547546,
1528
+ "learning_rate": 0.0002,
1529
+ "loss": 0.9625,
1530
+ "step": 2150
1531
+ },
1532
+ {
1533
+ "epoch": 2.849604221635884,
1534
+ "grad_norm": 0.4127797484397888,
1535
+ "learning_rate": 0.0002,
1536
+ "loss": 0.9347,
1537
+ "step": 2160
1538
+ },
1539
+ {
1540
+ "epoch": 2.862796833773087,
1541
+ "grad_norm": 0.8448635339736938,
1542
+ "learning_rate": 0.0002,
1543
+ "loss": 1.0459,
1544
+ "step": 2170
1545
+ },
1546
+ {
1547
+ "epoch": 2.87598944591029,
1548
+ "grad_norm": 0.5669729113578796,
1549
+ "learning_rate": 0.0002,
1550
+ "loss": 0.8185,
1551
+ "step": 2180
1552
+ },
1553
+ {
1554
+ "epoch": 2.8891820580474934,
1555
+ "grad_norm": 0.510231077671051,
1556
+ "learning_rate": 0.0002,
1557
+ "loss": 0.8555,
1558
+ "step": 2190
1559
+ },
1560
+ {
1561
+ "epoch": 2.9023746701846966,
1562
+ "grad_norm": 0.8072245121002197,
1563
+ "learning_rate": 0.0002,
1564
+ "loss": 0.9267,
1565
+ "step": 2200
1566
+ },
1567
+ {
1568
+ "epoch": 2.9155672823219,
1569
+ "grad_norm": 0.6055923104286194,
1570
+ "learning_rate": 0.0002,
1571
+ "loss": 0.9685,
1572
+ "step": 2210
1573
+ },
1574
+ {
1575
+ "epoch": 2.9287598944591027,
1576
+ "grad_norm": 0.7384416460990906,
1577
+ "learning_rate": 0.0002,
1578
+ "loss": 0.9157,
1579
+ "step": 2220
1580
+ },
1581
+ {
1582
+ "epoch": 2.941952506596306,
1583
+ "grad_norm": 0.4922751784324646,
1584
+ "learning_rate": 0.0002,
1585
+ "loss": 0.9712,
1586
+ "step": 2230
1587
+ },
1588
+ {
1589
+ "epoch": 2.955145118733509,
1590
+ "grad_norm": 0.6039906740188599,
1591
+ "learning_rate": 0.0002,
1592
+ "loss": 0.9487,
1593
+ "step": 2240
1594
+ },
1595
+ {
1596
+ "epoch": 2.9683377308707124,
1597
+ "grad_norm": 0.4751701354980469,
1598
+ "learning_rate": 0.0002,
1599
+ "loss": 0.9776,
1600
+ "step": 2250
1601
+ },
1602
+ {
1603
+ "epoch": 2.9815303430079156,
1604
+ "grad_norm": 0.5698353052139282,
1605
+ "learning_rate": 0.0002,
1606
+ "loss": 1.0619,
1607
+ "step": 2260
1608
+ },
1609
+ {
1610
+ "epoch": 2.994722955145119,
1611
+ "grad_norm": 0.893563449382782,
1612
+ "learning_rate": 0.0002,
1613
+ "loss": 1.1184,
1614
+ "step": 2270
1615
+ },
1616
+ {
1617
+ "epoch": 3.0,
1618
+ "eval_loss": 1.2046419382095337,
1619
+ "eval_runtime": 71.5992,
1620
+ "eval_samples_per_second": 6.02,
1621
+ "eval_steps_per_second": 0.754,
1622
+ "step": 2274
1623
+ },
1624
+ {
1625
+ "epoch": 3.007915567282322,
1626
+ "grad_norm": 0.41119325160980225,
1627
+ "learning_rate": 0.0002,
1628
+ "loss": 0.8269,
1629
+ "step": 2280
1630
+ },
1631
+ {
1632
+ "epoch": 3.021108179419525,
1633
+ "grad_norm": 0.8169420957565308,
1634
+ "learning_rate": 0.0002,
1635
+ "loss": 0.7856,
1636
+ "step": 2290
1637
+ },
1638
+ {
1639
+ "epoch": 3.034300791556728,
1640
+ "grad_norm": 0.6033818125724792,
1641
+ "learning_rate": 0.0002,
1642
+ "loss": 0.794,
1643
+ "step": 2300
1644
+ },
1645
+ {
1646
+ "epoch": 3.0474934036939314,
1647
+ "grad_norm": 0.9600058197975159,
1648
+ "learning_rate": 0.0002,
1649
+ "loss": 0.7607,
1650
+ "step": 2310
1651
+ },
1652
+ {
1653
+ "epoch": 3.0606860158311346,
1654
+ "grad_norm": 0.5859250426292419,
1655
+ "learning_rate": 0.0002,
1656
+ "loss": 0.8353,
1657
+ "step": 2320
1658
+ },
1659
+ {
1660
+ "epoch": 3.073878627968338,
1661
+ "grad_norm": 0.6758618950843811,
1662
+ "learning_rate": 0.0002,
1663
+ "loss": 0.7598,
1664
+ "step": 2330
1665
+ },
1666
+ {
1667
+ "epoch": 3.0870712401055407,
1668
+ "grad_norm": 0.8407140970230103,
1669
+ "learning_rate": 0.0002,
1670
+ "loss": 0.7631,
1671
+ "step": 2340
1672
+ },
1673
+ {
1674
+ "epoch": 3.100263852242744,
1675
+ "grad_norm": 0.767779529094696,
1676
+ "learning_rate": 0.0002,
1677
+ "loss": 0.7664,
1678
+ "step": 2350
1679
+ },
1680
+ {
1681
+ "epoch": 3.113456464379947,
1682
+ "grad_norm": 0.5572896599769592,
1683
+ "learning_rate": 0.0002,
1684
+ "loss": 0.7121,
1685
+ "step": 2360
1686
+ },
1687
+ {
1688
+ "epoch": 3.1266490765171504,
1689
+ "grad_norm": 0.5908368825912476,
1690
+ "learning_rate": 0.0002,
1691
+ "loss": 0.7419,
1692
+ "step": 2370
1693
+ },
1694
+ {
1695
+ "epoch": 3.1398416886543536,
1696
+ "grad_norm": 0.8047826290130615,
1697
+ "learning_rate": 0.0002,
1698
+ "loss": 0.8024,
1699
+ "step": 2380
1700
+ },
1701
+ {
1702
+ "epoch": 3.153034300791557,
1703
+ "grad_norm": 0.8041718006134033,
1704
+ "learning_rate": 0.0002,
1705
+ "loss": 0.8686,
1706
+ "step": 2390
1707
+ },
1708
+ {
1709
+ "epoch": 3.16622691292876,
1710
+ "grad_norm": 0.57078617811203,
1711
+ "learning_rate": 0.0002,
1712
+ "loss": 0.668,
1713
+ "step": 2400
1714
+ },
1715
+ {
1716
+ "epoch": 3.179419525065963,
1717
+ "grad_norm": 0.5125322937965393,
1718
+ "learning_rate": 0.0002,
1719
+ "loss": 0.7976,
1720
+ "step": 2410
1721
+ },
1722
+ {
1723
+ "epoch": 3.192612137203166,
1724
+ "grad_norm": 0.6356934309005737,
1725
+ "learning_rate": 0.0002,
1726
+ "loss": 0.741,
1727
+ "step": 2420
1728
+ },
1729
+ {
1730
+ "epoch": 3.2058047493403694,
1731
+ "grad_norm": 1.0129680633544922,
1732
+ "learning_rate": 0.0002,
1733
+ "loss": 0.687,
1734
+ "step": 2430
1735
+ },
1736
+ {
1737
+ "epoch": 3.2189973614775726,
1738
+ "grad_norm": 0.8104226589202881,
1739
+ "learning_rate": 0.0002,
1740
+ "loss": 0.8316,
1741
+ "step": 2440
1742
+ },
1743
+ {
1744
+ "epoch": 3.232189973614776,
1745
+ "grad_norm": 0.7276079058647156,
1746
+ "learning_rate": 0.0002,
1747
+ "loss": 0.8343,
1748
+ "step": 2450
1749
+ },
1750
+ {
1751
+ "epoch": 3.2453825857519787,
1752
+ "grad_norm": 0.9753884077072144,
1753
+ "learning_rate": 0.0002,
1754
+ "loss": 0.8183,
1755
+ "step": 2460
1756
+ },
1757
+ {
1758
+ "epoch": 3.258575197889182,
1759
+ "grad_norm": 0.9753183722496033,
1760
+ "learning_rate": 0.0002,
1761
+ "loss": 0.7776,
1762
+ "step": 2470
1763
+ },
1764
+ {
1765
+ "epoch": 3.271767810026385,
1766
+ "grad_norm": 0.6791225075721741,
1767
+ "learning_rate": 0.0002,
1768
+ "loss": 0.8815,
1769
+ "step": 2480
1770
+ },
1771
+ {
1772
+ "epoch": 3.2849604221635884,
1773
+ "grad_norm": 0.6797150373458862,
1774
+ "learning_rate": 0.0002,
1775
+ "loss": 0.7548,
1776
+ "step": 2490
1777
+ },
1778
+ {
1779
+ "epoch": 3.2981530343007917,
1780
+ "grad_norm": 0.8107194900512695,
1781
+ "learning_rate": 0.0002,
1782
+ "loss": 0.8395,
1783
+ "step": 2500
1784
+ },
1785
+ {
1786
+ "epoch": 3.311345646437995,
1787
+ "grad_norm": 0.5878375172615051,
1788
+ "learning_rate": 0.0002,
1789
+ "loss": 0.7869,
1790
+ "step": 2510
1791
+ },
1792
+ {
1793
+ "epoch": 3.324538258575198,
1794
+ "grad_norm": 0.5882975459098816,
1795
+ "learning_rate": 0.0002,
1796
+ "loss": 0.7992,
1797
+ "step": 2520
1798
+ },
1799
+ {
1800
+ "epoch": 3.337730870712401,
1801
+ "grad_norm": 0.6180013418197632,
1802
+ "learning_rate": 0.0002,
1803
+ "loss": 0.7472,
1804
+ "step": 2530
1805
+ },
1806
+ {
1807
+ "epoch": 3.350923482849604,
1808
+ "grad_norm": 1.0008151531219482,
1809
+ "learning_rate": 0.0002,
1810
+ "loss": 0.8033,
1811
+ "step": 2540
1812
+ },
1813
+ {
1814
+ "epoch": 3.3641160949868074,
1815
+ "grad_norm": 0.6404656767845154,
1816
+ "learning_rate": 0.0002,
1817
+ "loss": 0.8464,
1818
+ "step": 2550
1819
+ },
1820
+ {
1821
+ "epoch": 3.3773087071240107,
1822
+ "grad_norm": 0.8481354117393494,
1823
+ "learning_rate": 0.0002,
1824
+ "loss": 0.7533,
1825
+ "step": 2560
1826
+ },
1827
+ {
1828
+ "epoch": 3.390501319261214,
1829
+ "grad_norm": 0.8068035244941711,
1830
+ "learning_rate": 0.0002,
1831
+ "loss": 0.7852,
1832
+ "step": 2570
1833
+ },
1834
+ {
1835
+ "epoch": 3.4036939313984167,
1836
+ "grad_norm": 0.7477166056632996,
1837
+ "learning_rate": 0.0002,
1838
+ "loss": 0.8621,
1839
+ "step": 2580
1840
+ },
1841
+ {
1842
+ "epoch": 3.41688654353562,
1843
+ "grad_norm": 0.6202635765075684,
1844
+ "learning_rate": 0.0002,
1845
+ "loss": 0.8352,
1846
+ "step": 2590
1847
+ },
1848
+ {
1849
+ "epoch": 3.430079155672823,
1850
+ "grad_norm": 0.6981159448623657,
1851
+ "learning_rate": 0.0002,
1852
+ "loss": 0.7572,
1853
+ "step": 2600
1854
+ },
1855
+ {
1856
+ "epoch": 3.4432717678100264,
1857
+ "grad_norm": 0.6611084342002869,
1858
+ "learning_rate": 0.0002,
1859
+ "loss": 0.7846,
1860
+ "step": 2610
1861
+ },
1862
+ {
1863
+ "epoch": 3.4564643799472297,
1864
+ "grad_norm": 0.5727696418762207,
1865
+ "learning_rate": 0.0002,
1866
+ "loss": 0.7503,
1867
+ "step": 2620
1868
+ },
1869
+ {
1870
+ "epoch": 3.469656992084433,
1871
+ "grad_norm": 1.2354545593261719,
1872
+ "learning_rate": 0.0002,
1873
+ "loss": 0.8427,
1874
+ "step": 2630
1875
+ },
1876
+ {
1877
+ "epoch": 3.4828496042216357,
1878
+ "grad_norm": 0.6347638368606567,
1879
+ "learning_rate": 0.0002,
1880
+ "loss": 0.7747,
1881
+ "step": 2640
1882
+ },
1883
+ {
1884
+ "epoch": 3.496042216358839,
1885
+ "grad_norm": 0.6975704431533813,
1886
+ "learning_rate": 0.0002,
1887
+ "loss": 0.8426,
1888
+ "step": 2650
1889
+ },
1890
+ {
1891
+ "epoch": 3.509234828496042,
1892
+ "grad_norm": 0.6569573879241943,
1893
+ "learning_rate": 0.0002,
1894
+ "loss": 0.8773,
1895
+ "step": 2660
1896
+ },
1897
+ {
1898
+ "epoch": 3.5224274406332454,
1899
+ "grad_norm": 0.6979609131813049,
1900
+ "learning_rate": 0.0002,
1901
+ "loss": 0.7908,
1902
+ "step": 2670
1903
+ },
1904
+ {
1905
+ "epoch": 3.5356200527704487,
1906
+ "grad_norm": 0.6287988424301147,
1907
+ "learning_rate": 0.0002,
1908
+ "loss": 0.8254,
1909
+ "step": 2680
1910
+ },
1911
+ {
1912
+ "epoch": 3.5488126649076515,
1913
+ "grad_norm": 0.8682637214660645,
1914
+ "learning_rate": 0.0002,
1915
+ "loss": 0.7815,
1916
+ "step": 2690
1917
+ },
1918
+ {
1919
+ "epoch": 3.5620052770448547,
1920
+ "grad_norm": 0.7062831521034241,
1921
+ "learning_rate": 0.0002,
1922
+ "loss": 0.7566,
1923
+ "step": 2700
1924
+ },
1925
+ {
1926
+ "epoch": 3.575197889182058,
1927
+ "grad_norm": 1.0061452388763428,
1928
+ "learning_rate": 0.0002,
1929
+ "loss": 0.713,
1930
+ "step": 2710
1931
+ },
1932
+ {
1933
+ "epoch": 3.588390501319261,
1934
+ "grad_norm": 0.719097375869751,
1935
+ "learning_rate": 0.0002,
1936
+ "loss": 0.7738,
1937
+ "step": 2720
1938
+ },
1939
+ {
1940
+ "epoch": 3.6015831134564644,
1941
+ "grad_norm": 0.7583496570587158,
1942
+ "learning_rate": 0.0002,
1943
+ "loss": 0.8145,
1944
+ "step": 2730
1945
+ },
1946
+ {
1947
+ "epoch": 3.6147757255936677,
1948
+ "grad_norm": 0.7543531060218811,
1949
+ "learning_rate": 0.0002,
1950
+ "loss": 0.91,
1951
+ "step": 2740
1952
+ },
1953
+ {
1954
+ "epoch": 3.627968337730871,
1955
+ "grad_norm": 0.8873646855354309,
1956
+ "learning_rate": 0.0002,
1957
+ "loss": 0.8325,
1958
+ "step": 2750
1959
+ },
1960
+ {
1961
+ "epoch": 3.641160949868074,
1962
+ "grad_norm": 1.0657562017440796,
1963
+ "learning_rate": 0.0002,
1964
+ "loss": 0.7116,
1965
+ "step": 2760
1966
+ },
1967
+ {
1968
+ "epoch": 3.654353562005277,
1969
+ "grad_norm": 0.8641113638877869,
1970
+ "learning_rate": 0.0002,
1971
+ "loss": 0.8291,
1972
+ "step": 2770
1973
+ },
1974
+ {
1975
+ "epoch": 3.66754617414248,
1976
+ "grad_norm": 0.6620645523071289,
1977
+ "learning_rate": 0.0002,
1978
+ "loss": 0.8302,
1979
+ "step": 2780
1980
+ },
1981
+ {
1982
+ "epoch": 3.6807387862796834,
1983
+ "grad_norm": 0.6919541954994202,
1984
+ "learning_rate": 0.0002,
1985
+ "loss": 0.8261,
1986
+ "step": 2790
1987
+ },
1988
+ {
1989
+ "epoch": 3.6939313984168867,
1990
+ "grad_norm": 0.7305743098258972,
1991
+ "learning_rate": 0.0002,
1992
+ "loss": 0.8388,
1993
+ "step": 2800
1994
+ },
1995
+ {
1996
+ "epoch": 3.7071240105540895,
1997
+ "grad_norm": 0.7464777827262878,
1998
+ "learning_rate": 0.0002,
1999
+ "loss": 0.8053,
2000
+ "step": 2810
2001
+ },
2002
+ {
2003
+ "epoch": 3.7203166226912927,
2004
+ "grad_norm": 0.8067063093185425,
2005
+ "learning_rate": 0.0002,
2006
+ "loss": 0.8019,
2007
+ "step": 2820
2008
+ },
2009
+ {
2010
+ "epoch": 3.733509234828496,
2011
+ "grad_norm": 0.7789416313171387,
2012
+ "learning_rate": 0.0002,
2013
+ "loss": 0.8259,
2014
+ "step": 2830
2015
+ },
2016
+ {
2017
+ "epoch": 3.746701846965699,
2018
+ "grad_norm": 0.507529079914093,
2019
+ "learning_rate": 0.0002,
2020
+ "loss": 0.774,
2021
+ "step": 2840
2022
+ },
2023
+ {
2024
+ "epoch": 3.7598944591029024,
2025
+ "grad_norm": 0.6509260535240173,
2026
+ "learning_rate": 0.0002,
2027
+ "loss": 0.832,
2028
+ "step": 2850
2029
+ },
2030
+ {
2031
+ "epoch": 3.7730870712401057,
2032
+ "grad_norm": 0.9141367673873901,
2033
+ "learning_rate": 0.0002,
2034
+ "loss": 0.8257,
2035
+ "step": 2860
2036
+ },
2037
+ {
2038
+ "epoch": 3.786279683377309,
2039
+ "grad_norm": 0.7852635979652405,
2040
+ "learning_rate": 0.0002,
2041
+ "loss": 0.9436,
2042
+ "step": 2870
2043
+ },
2044
+ {
2045
+ "epoch": 3.7994722955145117,
2046
+ "grad_norm": 0.5340318083763123,
2047
+ "learning_rate": 0.0002,
2048
+ "loss": 0.8842,
2049
+ "step": 2880
2050
+ },
2051
+ {
2052
+ "epoch": 3.812664907651715,
2053
+ "grad_norm": 0.6246042847633362,
2054
+ "learning_rate": 0.0002,
2055
+ "loss": 0.7468,
2056
+ "step": 2890
2057
+ },
2058
+ {
2059
+ "epoch": 3.825857519788918,
2060
+ "grad_norm": 0.7064066529273987,
2061
+ "learning_rate": 0.0002,
2062
+ "loss": 0.8184,
2063
+ "step": 2900
2064
+ },
2065
+ {
2066
+ "epoch": 3.8390501319261214,
2067
+ "grad_norm": 0.6144065856933594,
2068
+ "learning_rate": 0.0002,
2069
+ "loss": 0.8515,
2070
+ "step": 2910
2071
+ },
2072
+ {
2073
+ "epoch": 3.8522427440633247,
2074
+ "grad_norm": 0.5268424153327942,
2075
+ "learning_rate": 0.0002,
2076
+ "loss": 0.7484,
2077
+ "step": 2920
2078
+ },
2079
+ {
2080
+ "epoch": 3.8654353562005275,
2081
+ "grad_norm": 0.9508116841316223,
2082
+ "learning_rate": 0.0002,
2083
+ "loss": 0.7594,
2084
+ "step": 2930
2085
+ },
2086
+ {
2087
+ "epoch": 3.8786279683377307,
2088
+ "grad_norm": 0.9133715629577637,
2089
+ "learning_rate": 0.0002,
2090
+ "loss": 0.8437,
2091
+ "step": 2940
2092
+ },
2093
+ {
2094
+ "epoch": 3.891820580474934,
2095
+ "grad_norm": 1.0144646167755127,
2096
+ "learning_rate": 0.0002,
2097
+ "loss": 0.8611,
2098
+ "step": 2950
2099
+ },
2100
+ {
2101
+ "epoch": 3.905013192612137,
2102
+ "grad_norm": 0.6397877931594849,
2103
+ "learning_rate": 0.0002,
2104
+ "loss": 0.8043,
2105
+ "step": 2960
2106
+ },
2107
+ {
2108
+ "epoch": 3.9182058047493404,
2109
+ "grad_norm": 0.734835147857666,
2110
+ "learning_rate": 0.0002,
2111
+ "loss": 0.8285,
2112
+ "step": 2970
2113
+ },
2114
+ {
2115
+ "epoch": 3.9313984168865437,
2116
+ "grad_norm": 0.784853994846344,
2117
+ "learning_rate": 0.0002,
2118
+ "loss": 0.7831,
2119
+ "step": 2980
2120
+ },
2121
+ {
2122
+ "epoch": 3.944591029023747,
2123
+ "grad_norm": 0.805831789970398,
2124
+ "learning_rate": 0.0002,
2125
+ "loss": 0.8148,
2126
+ "step": 2990
2127
+ },
2128
+ {
2129
+ "epoch": 3.9577836411609497,
2130
+ "grad_norm": 0.6299595236778259,
2131
+ "learning_rate": 0.0002,
2132
+ "loss": 0.8252,
2133
+ "step": 3000
2134
+ },
2135
+ {
2136
+ "epoch": 3.970976253298153,
2137
+ "grad_norm": 0.6264058351516724,
2138
+ "learning_rate": 0.0002,
2139
+ "loss": 0.8244,
2140
+ "step": 3010
2141
+ },
2142
+ {
2143
+ "epoch": 3.984168865435356,
2144
+ "grad_norm": 0.6419739723205566,
2145
+ "learning_rate": 0.0002,
2146
+ "loss": 0.8185,
2147
+ "step": 3020
2148
+ },
2149
+ {
2150
+ "epoch": 3.9973614775725594,
2151
+ "grad_norm": 0.7737036943435669,
2152
+ "learning_rate": 0.0002,
2153
+ "loss": 0.8174,
2154
+ "step": 3030
2155
+ },
2156
+ {
2157
+ "epoch": 4.0,
2158
+ "eval_loss": 1.2454297542572021,
2159
+ "eval_runtime": 71.8558,
2160
+ "eval_samples_per_second": 5.998,
2161
+ "eval_steps_per_second": 0.752,
2162
+ "step": 3032
2163
+ },
2164
+ {
2165
+ "epoch": 4.010554089709762,
2166
+ "grad_norm": 1.092727541923523,
2167
+ "learning_rate": 0.0002,
2168
+ "loss": 0.6716,
2169
+ "step": 3040
2170
+ },
2171
+ {
2172
+ "epoch": 4.0237467018469655,
2173
+ "grad_norm": 0.8087759613990784,
2174
+ "learning_rate": 0.0002,
2175
+ "loss": 0.596,
2176
+ "step": 3050
2177
+ },
2178
+ {
2179
+ "epoch": 4.036939313984169,
2180
+ "grad_norm": 0.8106053471565247,
2181
+ "learning_rate": 0.0002,
2182
+ "loss": 0.7055,
2183
+ "step": 3060
2184
+ },
2185
+ {
2186
+ "epoch": 4.050131926121372,
2187
+ "grad_norm": 0.8675326704978943,
2188
+ "learning_rate": 0.0002,
2189
+ "loss": 0.6846,
2190
+ "step": 3070
2191
+ },
2192
+ {
2193
+ "epoch": 4.063324538258575,
2194
+ "grad_norm": 0.9620490074157715,
2195
+ "learning_rate": 0.0002,
2196
+ "loss": 0.6064,
2197
+ "step": 3080
2198
+ },
2199
+ {
2200
+ "epoch": 4.076517150395778,
2201
+ "grad_norm": 0.8996296525001526,
2202
+ "learning_rate": 0.0002,
2203
+ "loss": 0.6047,
2204
+ "step": 3090
2205
+ },
2206
+ {
2207
+ "epoch": 4.089709762532982,
2208
+ "grad_norm": 0.8648998737335205,
2209
+ "learning_rate": 0.0002,
2210
+ "loss": 0.6111,
2211
+ "step": 3100
2212
+ },
2213
+ {
2214
+ "epoch": 4.102902374670185,
2215
+ "grad_norm": 1.0321335792541504,
2216
+ "learning_rate": 0.0002,
2217
+ "loss": 0.5853,
2218
+ "step": 3110
2219
+ },
2220
+ {
2221
+ "epoch": 4.116094986807388,
2222
+ "grad_norm": 0.7949225306510925,
2223
+ "learning_rate": 0.0002,
2224
+ "loss": 0.6161,
2225
+ "step": 3120
2226
+ },
2227
+ {
2228
+ "epoch": 4.129287598944591,
2229
+ "grad_norm": 0.9684646129608154,
2230
+ "learning_rate": 0.0002,
2231
+ "loss": 0.6354,
2232
+ "step": 3130
2233
+ },
2234
+ {
2235
+ "epoch": 4.142480211081795,
2236
+ "grad_norm": 0.8698066473007202,
2237
+ "learning_rate": 0.0002,
2238
+ "loss": 0.6198,
2239
+ "step": 3140
2240
+ },
2241
+ {
2242
+ "epoch": 4.155672823218997,
2243
+ "grad_norm": 0.7688450813293457,
2244
+ "learning_rate": 0.0002,
2245
+ "loss": 0.7185,
2246
+ "step": 3150
2247
+ },
2248
+ {
2249
+ "epoch": 4.1688654353562,
2250
+ "grad_norm": 0.9682092070579529,
2251
+ "learning_rate": 0.0002,
2252
+ "loss": 0.6053,
2253
+ "step": 3160
2254
+ },
2255
+ {
2256
+ "epoch": 4.1820580474934035,
2257
+ "grad_norm": 0.961561918258667,
2258
+ "learning_rate": 0.0002,
2259
+ "loss": 0.6827,
2260
+ "step": 3170
2261
+ },
2262
+ {
2263
+ "epoch": 4.195250659630607,
2264
+ "grad_norm": 1.3962990045547485,
2265
+ "learning_rate": 0.0002,
2266
+ "loss": 0.6403,
2267
+ "step": 3180
2268
+ },
2269
+ {
2270
+ "epoch": 4.20844327176781,
2271
+ "grad_norm": 0.9485045075416565,
2272
+ "learning_rate": 0.0002,
2273
+ "loss": 0.6319,
2274
+ "step": 3190
2275
+ },
2276
+ {
2277
+ "epoch": 4.221635883905013,
2278
+ "grad_norm": 0.7768281698226929,
2279
+ "learning_rate": 0.0002,
2280
+ "loss": 0.5908,
2281
+ "step": 3200
2282
+ },
2283
+ {
2284
+ "epoch": 4.2348284960422165,
2285
+ "grad_norm": 1.2685691118240356,
2286
+ "learning_rate": 0.0002,
2287
+ "loss": 0.6365,
2288
+ "step": 3210
2289
+ },
2290
+ {
2291
+ "epoch": 4.24802110817942,
2292
+ "grad_norm": 0.6876471638679504,
2293
+ "learning_rate": 0.0002,
2294
+ "loss": 0.6601,
2295
+ "step": 3220
2296
+ },
2297
+ {
2298
+ "epoch": 4.261213720316623,
2299
+ "grad_norm": 1.0074554681777954,
2300
+ "learning_rate": 0.0002,
2301
+ "loss": 0.6274,
2302
+ "step": 3230
2303
+ },
2304
+ {
2305
+ "epoch": 4.274406332453826,
2306
+ "grad_norm": 0.8094777464866638,
2307
+ "learning_rate": 0.0002,
2308
+ "loss": 0.6027,
2309
+ "step": 3240
2310
+ },
2311
+ {
2312
+ "epoch": 4.287598944591029,
2313
+ "grad_norm": 0.7906569242477417,
2314
+ "learning_rate": 0.0002,
2315
+ "loss": 0.643,
2316
+ "step": 3250
2317
+ },
2318
+ {
2319
+ "epoch": 4.300791556728232,
2320
+ "grad_norm": 0.840238630771637,
2321
+ "learning_rate": 0.0002,
2322
+ "loss": 0.5909,
2323
+ "step": 3260
2324
+ },
2325
+ {
2326
+ "epoch": 4.313984168865435,
2327
+ "grad_norm": 1.0119295120239258,
2328
+ "learning_rate": 0.0002,
2329
+ "loss": 0.5943,
2330
+ "step": 3270
2331
+ },
2332
+ {
2333
+ "epoch": 4.327176781002638,
2334
+ "grad_norm": 0.7943191528320312,
2335
+ "learning_rate": 0.0002,
2336
+ "loss": 0.5912,
2337
+ "step": 3280
2338
+ },
2339
+ {
2340
+ "epoch": 4.3403693931398415,
2341
+ "grad_norm": 0.7691723704338074,
2342
+ "learning_rate": 0.0002,
2343
+ "loss": 0.6235,
2344
+ "step": 3290
2345
+ },
2346
+ {
2347
+ "epoch": 4.353562005277045,
2348
+ "grad_norm": 0.7227770686149597,
2349
+ "learning_rate": 0.0002,
2350
+ "loss": 0.6173,
2351
+ "step": 3300
2352
+ },
2353
+ {
2354
+ "epoch": 4.366754617414248,
2355
+ "grad_norm": 0.8512253165245056,
2356
+ "learning_rate": 0.0002,
2357
+ "loss": 0.6047,
2358
+ "step": 3310
2359
+ },
2360
+ {
2361
+ "epoch": 4.379947229551451,
2362
+ "grad_norm": 0.7852529287338257,
2363
+ "learning_rate": 0.0002,
2364
+ "loss": 0.5849,
2365
+ "step": 3320
2366
+ },
2367
+ {
2368
+ "epoch": 4.3931398416886545,
2369
+ "grad_norm": 0.8888797163963318,
2370
+ "learning_rate": 0.0002,
2371
+ "loss": 0.6416,
2372
+ "step": 3330
2373
+ },
2374
+ {
2375
+ "epoch": 4.406332453825858,
2376
+ "grad_norm": 0.9522430896759033,
2377
+ "learning_rate": 0.0002,
2378
+ "loss": 0.6804,
2379
+ "step": 3340
2380
+ },
2381
+ {
2382
+ "epoch": 4.419525065963061,
2383
+ "grad_norm": 0.900276780128479,
2384
+ "learning_rate": 0.0002,
2385
+ "loss": 0.6345,
2386
+ "step": 3350
2387
+ },
2388
+ {
2389
+ "epoch": 4.432717678100264,
2390
+ "grad_norm": 1.181547999382019,
2391
+ "learning_rate": 0.0002,
2392
+ "loss": 0.7055,
2393
+ "step": 3360
2394
+ },
2395
+ {
2396
+ "epoch": 4.445910290237467,
2397
+ "grad_norm": 0.903142511844635,
2398
+ "learning_rate": 0.0002,
2399
+ "loss": 0.7073,
2400
+ "step": 3370
2401
+ },
2402
+ {
2403
+ "epoch": 4.45910290237467,
2404
+ "grad_norm": 0.8747565150260925,
2405
+ "learning_rate": 0.0002,
2406
+ "loss": 0.7235,
2407
+ "step": 3380
2408
+ },
2409
+ {
2410
+ "epoch": 4.472295514511873,
2411
+ "grad_norm": 0.7838051319122314,
2412
+ "learning_rate": 0.0002,
2413
+ "loss": 0.7071,
2414
+ "step": 3390
2415
+ },
2416
+ {
2417
+ "epoch": 4.485488126649076,
2418
+ "grad_norm": 0.8691313862800598,
2419
+ "learning_rate": 0.0002,
2420
+ "loss": 0.5932,
2421
+ "step": 3400
2422
+ },
2423
+ {
2424
+ "epoch": 4.4986807387862795,
2425
+ "grad_norm": 0.8493868708610535,
2426
+ "learning_rate": 0.0002,
2427
+ "loss": 0.7019,
2428
+ "step": 3410
2429
+ },
2430
+ {
2431
+ "epoch": 4.511873350923483,
2432
+ "grad_norm": 1.0104830265045166,
2433
+ "learning_rate": 0.0002,
2434
+ "loss": 0.5959,
2435
+ "step": 3420
2436
+ },
2437
+ {
2438
+ "epoch": 4.525065963060686,
2439
+ "grad_norm": 1.1716967821121216,
2440
+ "learning_rate": 0.0002,
2441
+ "loss": 0.6662,
2442
+ "step": 3430
2443
+ },
2444
+ {
2445
+ "epoch": 4.538258575197889,
2446
+ "grad_norm": 0.9122593998908997,
2447
+ "learning_rate": 0.0002,
2448
+ "loss": 0.6411,
2449
+ "step": 3440
2450
+ },
2451
+ {
2452
+ "epoch": 4.5514511873350925,
2453
+ "grad_norm": 0.829090416431427,
2454
+ "learning_rate": 0.0002,
2455
+ "loss": 0.7047,
2456
+ "step": 3450
2457
+ },
2458
+ {
2459
+ "epoch": 4.564643799472296,
2460
+ "grad_norm": 1.141662836074829,
2461
+ "learning_rate": 0.0002,
2462
+ "loss": 0.6001,
2463
+ "step": 3460
2464
+ },
2465
+ {
2466
+ "epoch": 4.577836411609499,
2467
+ "grad_norm": 0.8423182368278503,
2468
+ "learning_rate": 0.0002,
2469
+ "loss": 0.6612,
2470
+ "step": 3470
2471
+ },
2472
+ {
2473
+ "epoch": 4.591029023746702,
2474
+ "grad_norm": 0.8024184703826904,
2475
+ "learning_rate": 0.0002,
2476
+ "loss": 0.6797,
2477
+ "step": 3480
2478
+ },
2479
+ {
2480
+ "epoch": 4.6042216358839045,
2481
+ "grad_norm": 0.7703381776809692,
2482
+ "learning_rate": 0.0002,
2483
+ "loss": 0.7184,
2484
+ "step": 3490
2485
+ },
2486
+ {
2487
+ "epoch": 4.617414248021108,
2488
+ "grad_norm": 0.9883959293365479,
2489
+ "learning_rate": 0.0002,
2490
+ "loss": 0.7001,
2491
+ "step": 3500
2492
+ },
2493
+ {
2494
+ "epoch": 4.630606860158311,
2495
+ "grad_norm": 0.9554709196090698,
2496
+ "learning_rate": 0.0002,
2497
+ "loss": 0.6188,
2498
+ "step": 3510
2499
+ },
2500
+ {
2501
+ "epoch": 4.643799472295514,
2502
+ "grad_norm": 1.9949709177017212,
2503
+ "learning_rate": 0.0002,
2504
+ "loss": 0.7378,
2505
+ "step": 3520
2506
+ },
2507
+ {
2508
+ "epoch": 4.6569920844327175,
2509
+ "grad_norm": 0.7762255072593689,
2510
+ "learning_rate": 0.0002,
2511
+ "loss": 0.6678,
2512
+ "step": 3530
2513
+ },
2514
+ {
2515
+ "epoch": 4.670184696569921,
2516
+ "grad_norm": 0.9538425803184509,
2517
+ "learning_rate": 0.0002,
2518
+ "loss": 0.6298,
2519
+ "step": 3540
2520
+ },
2521
+ {
2522
+ "epoch": 4.683377308707124,
2523
+ "grad_norm": 1.0279661417007446,
2524
+ "learning_rate": 0.0002,
2525
+ "loss": 0.6352,
2526
+ "step": 3550
2527
+ },
2528
+ {
2529
+ "epoch": 4.696569920844327,
2530
+ "grad_norm": 0.7545472979545593,
2531
+ "learning_rate": 0.0002,
2532
+ "loss": 0.6641,
2533
+ "step": 3560
2534
+ },
2535
+ {
2536
+ "epoch": 4.7097625329815305,
2537
+ "grad_norm": 0.8919376730918884,
2538
+ "learning_rate": 0.0002,
2539
+ "loss": 0.6887,
2540
+ "step": 3570
2541
+ },
2542
+ {
2543
+ "epoch": 4.722955145118734,
2544
+ "grad_norm": 0.7621569633483887,
2545
+ "learning_rate": 0.0002,
2546
+ "loss": 0.6395,
2547
+ "step": 3580
2548
+ },
2549
+ {
2550
+ "epoch": 4.736147757255937,
2551
+ "grad_norm": 1.205320119857788,
2552
+ "learning_rate": 0.0002,
2553
+ "loss": 0.6928,
2554
+ "step": 3590
2555
+ },
2556
+ {
2557
+ "epoch": 4.74934036939314,
2558
+ "grad_norm": 1.0642725229263306,
2559
+ "learning_rate": 0.0002,
2560
+ "loss": 0.6612,
2561
+ "step": 3600
2562
+ },
2563
+ {
2564
+ "epoch": 4.762532981530343,
2565
+ "grad_norm": 0.9402666687965393,
2566
+ "learning_rate": 0.0002,
2567
+ "loss": 0.6541,
2568
+ "step": 3610
2569
+ },
2570
+ {
2571
+ "epoch": 4.775725593667546,
2572
+ "grad_norm": 1.254127025604248,
2573
+ "learning_rate": 0.0002,
2574
+ "loss": 0.6395,
2575
+ "step": 3620
2576
+ },
2577
+ {
2578
+ "epoch": 4.788918205804749,
2579
+ "grad_norm": 0.7609598636627197,
2580
+ "learning_rate": 0.0002,
2581
+ "loss": 0.692,
2582
+ "step": 3630
2583
+ },
2584
+ {
2585
+ "epoch": 4.802110817941952,
2586
+ "grad_norm": 0.8240329623222351,
2587
+ "learning_rate": 0.0002,
2588
+ "loss": 0.6578,
2589
+ "step": 3640
2590
+ },
2591
+ {
2592
+ "epoch": 4.8153034300791555,
2593
+ "grad_norm": 0.8356260657310486,
2594
+ "learning_rate": 0.0002,
2595
+ "loss": 0.7383,
2596
+ "step": 3650
2597
+ },
2598
+ {
2599
+ "epoch": 4.828496042216359,
2600
+ "grad_norm": 0.9130708575248718,
2601
+ "learning_rate": 0.0002,
2602
+ "loss": 0.6368,
2603
+ "step": 3660
2604
+ },
2605
+ {
2606
+ "epoch": 4.841688654353562,
2607
+ "grad_norm": 0.9384765028953552,
2608
+ "learning_rate": 0.0002,
2609
+ "loss": 0.7269,
2610
+ "step": 3670
2611
+ },
2612
+ {
2613
+ "epoch": 4.854881266490765,
2614
+ "grad_norm": 0.9829966425895691,
2615
+ "learning_rate": 0.0002,
2616
+ "loss": 0.6509,
2617
+ "step": 3680
2618
+ },
2619
+ {
2620
+ "epoch": 4.8680738786279685,
2621
+ "grad_norm": 1.0488632917404175,
2622
+ "learning_rate": 0.0002,
2623
+ "loss": 0.6311,
2624
+ "step": 3690
2625
+ },
2626
+ {
2627
+ "epoch": 4.881266490765172,
2628
+ "grad_norm": 1.2278969287872314,
2629
+ "learning_rate": 0.0002,
2630
+ "loss": 0.7005,
2631
+ "step": 3700
2632
+ },
2633
+ {
2634
+ "epoch": 4.894459102902375,
2635
+ "grad_norm": 0.8078970313072205,
2636
+ "learning_rate": 0.0002,
2637
+ "loss": 0.6869,
2638
+ "step": 3710
2639
+ },
2640
+ {
2641
+ "epoch": 4.907651715039578,
2642
+ "grad_norm": 0.8081700205802917,
2643
+ "learning_rate": 0.0002,
2644
+ "loss": 0.6588,
2645
+ "step": 3720
2646
+ },
2647
+ {
2648
+ "epoch": 4.9208443271767806,
2649
+ "grad_norm": 0.9204511046409607,
2650
+ "learning_rate": 0.0002,
2651
+ "loss": 0.7189,
2652
+ "step": 3730
2653
+ },
2654
+ {
2655
+ "epoch": 4.934036939313984,
2656
+ "grad_norm": 0.9326391220092773,
2657
+ "learning_rate": 0.0002,
2658
+ "loss": 0.6953,
2659
+ "step": 3740
2660
+ },
2661
+ {
2662
+ "epoch": 4.947229551451187,
2663
+ "grad_norm": 1.0089969635009766,
2664
+ "learning_rate": 0.0002,
2665
+ "loss": 0.68,
2666
+ "step": 3750
2667
+ },
2668
+ {
2669
+ "epoch": 4.96042216358839,
2670
+ "grad_norm": 0.7063466906547546,
2671
+ "learning_rate": 0.0002,
2672
+ "loss": 0.7031,
2673
+ "step": 3760
2674
+ },
2675
+ {
2676
+ "epoch": 4.9736147757255935,
2677
+ "grad_norm": 1.2603905200958252,
2678
+ "learning_rate": 0.0002,
2679
+ "loss": 0.6568,
2680
+ "step": 3770
2681
+ },
2682
+ {
2683
+ "epoch": 4.986807387862797,
2684
+ "grad_norm": 0.8418653607368469,
2685
+ "learning_rate": 0.0002,
2686
+ "loss": 0.7134,
2687
+ "step": 3780
2688
+ },
2689
+ {
2690
+ "epoch": 5.0,
2691
+ "grad_norm": 0.9537181854248047,
2692
+ "learning_rate": 0.0002,
2693
+ "loss": 0.6683,
2694
+ "step": 3790
2695
+ },
2696
+ {
2697
+ "epoch": 5.0,
2698
+ "eval_loss": 1.3319307565689087,
2699
+ "eval_runtime": 71.7836,
2700
+ "eval_samples_per_second": 6.004,
2701
+ "eval_steps_per_second": 0.752,
2702
+ "step": 3790
2703
+ }
2704
+ ],
2705
+ "logging_steps": 10,
2706
+ "max_steps": 6064,
2707
+ "num_input_tokens_seen": 0,
2708
+ "num_train_epochs": 8,
2709
+ "save_steps": 200,
2710
+ "stateful_callbacks": {
2711
+ "TrainerControl": {
2712
+ "args": {
2713
+ "should_epoch_stop": false,
2714
+ "should_evaluate": false,
2715
+ "should_log": false,
2716
+ "should_save": true,
2717
+ "should_training_stop": false
2718
+ },
2719
+ "attributes": {}
2720
+ }
2721
+ },
2722
+ "total_flos": 1.7539271384629248e+17,
2723
+ "train_batch_size": 1,
2724
+ "trial_name": null,
2725
+ "trial_params": null
2726
+ }
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-3790/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e04722e246164eebe6b4f70dd50fe946c936a2bd25edd75bcedcfd4c7ff9474e
3
+ size 5624
Meta-Llama-3-8B-Instruct_int4_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-4548/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_mmlu-routerbench-0shot-full-by-task_lr-0.0002_e-8_seq-512_lora-a-32-d-0.05-r-64_bs-1_gas-2_tf32-True_tunedata-portion-p-0.5-num-4904-sd-42/checkpoint-4548/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
+ }