lzc0525 commited on
Commit
2c695b2
·
verified ·
1 Parent(s): 5dc8e42

Upload folder using huggingface_hub

Browse files
Files changed (42) hide show
  1. .gitattributes +4 -0
  2. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/README.md +59 -0
  3. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/all_results.json +24 -0
  4. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/config.json +40 -0
  5. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/eval_results.json +18 -0
  6. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/generation_config.json +12 -0
  7. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/model-00001-of-00002.safetensors +3 -0
  8. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/model-00002-of-00002.safetensors +3 -0
  9. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/model.safetensors.index.json +262 -0
  10. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/special_tokens_map.json +17 -0
  11. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/tokenizer.json +3 -0
  12. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/tokenizer_config.json +2063 -0
  13. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/train_results.json +9 -0
  14. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/trainer_state.json +1317 -0
  15. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/training_args.bin +3 -0
  16. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/README.md +59 -0
  17. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/all_results.json +9 -0
  18. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/config.json +40 -0
  19. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/generation_config.json +12 -0
  20. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/model-00001-of-00002.safetensors +3 -0
  21. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/model-00002-of-00002.safetensors +3 -0
  22. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/model.safetensors.index.json +262 -0
  23. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/special_tokens_map.json +17 -0
  24. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/tokenizer.json +3 -0
  25. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/tokenizer_config.json +2063 -0
  26. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/train_results.json +9 -0
  27. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/trainer_state.json +0 -0
  28. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/training_args.bin +3 -0
  29. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/README.md +59 -0
  30. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/all_results.json +9 -0
  31. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/config.json +40 -0
  32. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/generation_config.json +12 -0
  33. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/model-00001-of-00002.safetensors +3 -0
  34. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/model-00002-of-00002.safetensors +3 -0
  35. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/model.safetensors.index.json +262 -0
  36. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/raw_datasets.json +3 -0
  37. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/special_tokens_map.json +17 -0
  38. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/tokenizer.json +3 -0
  39. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/tokenizer_config.json +2063 -0
  40. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/train_results.json +9 -0
  41. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/trainer_state.json +1392 -0
  42. Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/raw_datasets.json filter=lfs diff=lfs merge=lfs -text
39
+ Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: /home/v-liuzichuan/huggingface/Llama-3.2-3B-Instruct
4
+ tags:
5
+ - alignment-handbook
6
+ - generated_from_trainer
7
+ datasets:
8
+ - /home/v-liuzichuan/huggingface/princeton-nlp/llama3-math
9
+ model-index:
10
+ - name: Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1
18
+
19
+ This model is a fine-tuned version of [/home/v-liuzichuan/huggingface/Llama-3.2-3B-Instruct](https://huggingface.co//home/v-liuzichuan/huggingface/Llama-3.2-3B-Instruct) on the /home/v-liuzichuan/huggingface/princeton-nlp/llama3-math dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-07
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - gradient_accumulation_steps: 64
44
+ - total_train_batch_size: 128
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 1
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.45.2
57
+ - Pytorch 2.5.1+cu121
58
+ - Datasets 3.5.0
59
+ - Tokenizers 0.20.3
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/all_results.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9880609304240429,
3
+ "eval_logits/chosen": -0.006348939146846533,
4
+ "eval_logits/rejected": 0.15363818407058716,
5
+ "eval_logps/chosen": -152.83180236816406,
6
+ "eval_logps/ref_chosen": -143.584228515625,
7
+ "eval_logps/ref_rejected": -180.65379333496094,
8
+ "eval_logps/rejected": -193.19842529296875,
9
+ "eval_loss": 2200.785888671875,
10
+ "eval_rewards/accuracies": 0.7675926089286804,
11
+ "eval_rewards/chosen": -0.09247560054063797,
12
+ "eval_rewards/margins": 0.03297054395079613,
13
+ "eval_rewards/rejected": -0.125446155667305,
14
+ "eval_runtime": 144.1905,
15
+ "eval_samples": 1080,
16
+ "eval_samples_per_second": 7.49,
17
+ "eval_steps_per_second": 1.873,
18
+ "total_flos": 0.0,
19
+ "train_loss": 2318.3018196614585,
20
+ "train_runtime": 5362.5076,
21
+ "train_samples": 9715,
22
+ "train_samples_per_second": 1.812,
23
+ "train_steps_per_second": 0.014
24
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/v-liuzichuan/huggingface/Llama-3.2-3B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 24,
23
+ "num_hidden_layers": 28,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.45.2",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/eval_results.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9880609304240429,
3
+ "eval_logits/chosen": -0.006348939146846533,
4
+ "eval_logits/rejected": 0.15363818407058716,
5
+ "eval_logps/chosen": -152.83180236816406,
6
+ "eval_logps/ref_chosen": -143.584228515625,
7
+ "eval_logps/ref_rejected": -180.65379333496094,
8
+ "eval_logps/rejected": -193.19842529296875,
9
+ "eval_loss": 2200.785888671875,
10
+ "eval_rewards/accuracies": 0.7675926089286804,
11
+ "eval_rewards/chosen": -0.09247560054063797,
12
+ "eval_rewards/margins": 0.03297054395079613,
13
+ "eval_rewards/rejected": -0.125446155667305,
14
+ "eval_runtime": 144.1905,
15
+ "eval_samples": 1080,
16
+ "eval_samples_per_second": 7.49,
17
+ "eval_steps_per_second": 1.873
18
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.45.2"
12
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:406950142942bd6ecc5e4d0189e5536f9c55b4d0327a287472bba05b6d39951e
3
+ size 4965799096
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b36468d396c14af5406e75ba9946c39ed91227034dfee3da077dcf3eacdc9ae
3
+ size 2247734992
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7213504512
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.norm.weight": "model-00002-of-00002.safetensors"
261
+ }
262
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/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
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/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": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
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": "<|eom_id|>",
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": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
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": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
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": 2048,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9880609304240429,
3
+ "total_flos": 0.0,
4
+ "train_loss": 2318.3018196614585,
5
+ "train_runtime": 5362.5076,
6
+ "train_samples": 9715,
7
+ "train_samples_per_second": 1.812,
8
+ "train_steps_per_second": 0.014
9
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/trainer_state.json ADDED
@@ -0,0 +1,1317 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9880609304240429,
5
+ "eval_steps": 500,
6
+ "global_step": 75,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.013174145738987238,
13
+ "grad_norm": 6860.466796875,
14
+ "learning_rate": 6.25e-08,
15
+ "logits/chosen": 0.141204833984375,
16
+ "logits/rejected": 0.33030927181243896,
17
+ "logps/chosen": -145.53533935546875,
18
+ "logps/ref_chosen": -145.53533935546875,
19
+ "logps/ref_rejected": -193.32150268554688,
20
+ "logps/rejected": -193.32150268554688,
21
+ "loss": 2500.0,
22
+ "rewards/accuracies": 0.0,
23
+ "rewards/chosen": 0.0,
24
+ "rewards/margins": 0.0,
25
+ "rewards/rejected": 0.0,
26
+ "step": 1
27
+ },
28
+ {
29
+ "epoch": 0.026348291477974475,
30
+ "grad_norm": 6303.73779296875,
31
+ "learning_rate": 1.25e-07,
32
+ "logits/chosen": 0.13193297386169434,
33
+ "logits/rejected": 0.2929544448852539,
34
+ "logps/chosen": -140.2626953125,
35
+ "logps/ref_chosen": -140.2626953125,
36
+ "logps/ref_rejected": -176.88131713867188,
37
+ "logps/rejected": -176.88131713867188,
38
+ "loss": 2500.0,
39
+ "rewards/accuracies": 0.0,
40
+ "rewards/chosen": 0.0,
41
+ "rewards/margins": 0.0,
42
+ "rewards/rejected": 0.0,
43
+ "step": 2
44
+ },
45
+ {
46
+ "epoch": 0.03952243721696171,
47
+ "grad_norm": 7013.66455078125,
48
+ "learning_rate": 1.875e-07,
49
+ "logits/chosen": 0.13777679204940796,
50
+ "logits/rejected": 0.3124394416809082,
51
+ "logps/chosen": -140.7003173828125,
52
+ "logps/ref_chosen": -140.56329345703125,
53
+ "logps/ref_rejected": -178.77528381347656,
54
+ "logps/rejected": -179.00807189941406,
55
+ "loss": 2490.6772,
56
+ "rewards/accuracies": 0.59375,
57
+ "rewards/chosen": -0.001370340003632009,
58
+ "rewards/margins": 0.0009573930292390287,
59
+ "rewards/rejected": -0.0023277332074940205,
60
+ "step": 3
61
+ },
62
+ {
63
+ "epoch": 0.05269658295594895,
64
+ "grad_norm": 6542.68701171875,
65
+ "learning_rate": 2.5e-07,
66
+ "logits/chosen": 0.11986075341701508,
67
+ "logits/rejected": 0.3138517737388611,
68
+ "logps/chosen": -142.2206268310547,
69
+ "logps/ref_chosen": -142.1716766357422,
70
+ "logps/ref_rejected": -182.4105682373047,
71
+ "logps/rejected": -182.5343017578125,
72
+ "loss": 2492.9197,
73
+ "rewards/accuracies": 0.5859375,
74
+ "rewards/chosen": -0.0004894107696600258,
75
+ "rewards/margins": 0.0007477980107069016,
76
+ "rewards/rejected": -0.0012372087221592665,
77
+ "step": 4
78
+ },
79
+ {
80
+ "epoch": 0.06587072869493618,
81
+ "grad_norm": 6226.75830078125,
82
+ "learning_rate": 3.1249999999999997e-07,
83
+ "logits/chosen": 0.1316731721162796,
84
+ "logits/rejected": 0.27220460772514343,
85
+ "logps/chosen": -136.12843322753906,
86
+ "logps/ref_chosen": -136.04742431640625,
87
+ "logps/ref_rejected": -174.37258911132812,
88
+ "logps/rejected": -174.43295288085938,
89
+ "loss": 2502.3987,
90
+ "rewards/accuracies": 0.5234375,
91
+ "rewards/chosen": -0.0008100616978481412,
92
+ "rewards/margins": -0.00020654620311688632,
93
+ "rewards/rejected": -0.0006035154801793396,
94
+ "step": 5
95
+ },
96
+ {
97
+ "epoch": 0.07904487443392343,
98
+ "grad_norm": 6592.1669921875,
99
+ "learning_rate": 3.75e-07,
100
+ "logits/chosen": 0.014960660599172115,
101
+ "logits/rejected": 0.2215287983417511,
102
+ "logps/chosen": -141.27008056640625,
103
+ "logps/ref_chosen": -141.18539428710938,
104
+ "logps/ref_rejected": -184.99798583984375,
105
+ "logps/rejected": -185.0793914794922,
106
+ "loss": 2500.5635,
107
+ "rewards/accuracies": 0.453125,
108
+ "rewards/chosen": -0.0008468800224363804,
109
+ "rewards/margins": -3.290064341854304e-05,
110
+ "rewards/rejected": -0.0008139795390889049,
111
+ "step": 6
112
+ },
113
+ {
114
+ "epoch": 0.09221902017291066,
115
+ "grad_norm": 6696.421875,
116
+ "learning_rate": 4.375e-07,
117
+ "logits/chosen": 0.18217767775058746,
118
+ "logits/rejected": 0.29594191908836365,
119
+ "logps/chosen": -137.65072631835938,
120
+ "logps/ref_chosen": -137.64540100097656,
121
+ "logps/ref_rejected": -162.30291748046875,
122
+ "logps/rejected": -162.27566528320312,
123
+ "loss": 2503.5322,
124
+ "rewards/accuracies": 0.484375,
125
+ "rewards/chosen": -5.3269868658389896e-05,
126
+ "rewards/margins": -0.00032598141115158796,
127
+ "rewards/rejected": 0.00027271150611341,
128
+ "step": 7
129
+ },
130
+ {
131
+ "epoch": 0.1053931659118979,
132
+ "grad_norm": 6849.87255859375,
133
+ "learning_rate": 5e-07,
134
+ "logits/chosen": 0.14773835241794586,
135
+ "logits/rejected": 0.27819374203681946,
136
+ "logps/chosen": -142.74822998046875,
137
+ "logps/ref_chosen": -142.64285278320312,
138
+ "logps/ref_rejected": -179.400390625,
139
+ "logps/rejected": -179.61361694335938,
140
+ "loss": 2489.5378,
141
+ "rewards/accuracies": 0.609375,
142
+ "rewards/chosen": -0.0010537999914959073,
143
+ "rewards/margins": 0.0010784172918647528,
144
+ "rewards/rejected": -0.002132217399775982,
145
+ "step": 8
146
+ },
147
+ {
148
+ "epoch": 0.11856731165088513,
149
+ "grad_norm": 6715.9052734375,
150
+ "learning_rate": 4.997252228714278e-07,
151
+ "logits/chosen": 0.16841058433055878,
152
+ "logits/rejected": 0.25743114948272705,
153
+ "logps/chosen": -143.73524475097656,
154
+ "logps/ref_chosen": -143.59718322753906,
155
+ "logps/ref_rejected": -167.90943908691406,
156
+ "logps/rejected": -168.07098388671875,
157
+ "loss": 2497.9673,
158
+ "rewards/accuracies": 0.5703125,
159
+ "rewards/chosen": -0.001380585483275354,
160
+ "rewards/margins": 0.0002349048008909449,
161
+ "rewards/rejected": -0.0016154901823028922,
162
+ "step": 9
163
+ },
164
+ {
165
+ "epoch": 0.13174145738987236,
166
+ "grad_norm": 7364.2939453125,
167
+ "learning_rate": 4.989014955054745e-07,
168
+ "logits/chosen": 0.06786679476499557,
169
+ "logits/rejected": 0.271741658449173,
170
+ "logps/chosen": -136.30813598632812,
171
+ "logps/ref_chosen": -136.13136291503906,
172
+ "logps/ref_rejected": -167.5884246826172,
173
+ "logps/rejected": -167.917724609375,
174
+ "loss": 2485.0818,
175
+ "rewards/accuracies": 0.59375,
176
+ "rewards/chosen": -0.0017676865682005882,
177
+ "rewards/margins": 0.001525329309515655,
178
+ "rewards/rejected": -0.003293015994131565,
179
+ "step": 10
180
+ },
181
+ {
182
+ "epoch": 0.14491560312885962,
183
+ "grad_norm": 6181.556640625,
184
+ "learning_rate": 4.975306286336627e-07,
185
+ "logits/chosen": 0.13534238934516907,
186
+ "logits/rejected": 0.2919628918170929,
187
+ "logps/chosen": -140.97483825683594,
188
+ "logps/ref_chosen": -140.63983154296875,
189
+ "logps/ref_rejected": -187.97640991210938,
190
+ "logps/rejected": -188.3951416015625,
191
+ "loss": 2491.9521,
192
+ "rewards/accuracies": 0.578125,
193
+ "rewards/chosen": -0.0033500813879072666,
194
+ "rewards/margins": 0.0008371174335479736,
195
+ "rewards/rejected": -0.00418719882145524,
196
+ "step": 11
197
+ },
198
+ {
199
+ "epoch": 0.15808974886784685,
200
+ "grad_norm": 6728.86962890625,
201
+ "learning_rate": 4.956156357188939e-07,
202
+ "logits/chosen": 0.15034745633602142,
203
+ "logits/rejected": 0.2988182306289673,
204
+ "logps/chosen": -138.34246826171875,
205
+ "logps/ref_chosen": -137.91943359375,
206
+ "logps/ref_rejected": -173.40560913085938,
207
+ "logps/rejected": -174.0308837890625,
208
+ "loss": 2480.1863,
209
+ "rewards/accuracies": 0.640625,
210
+ "rewards/chosen": -0.004230341874063015,
211
+ "rewards/margins": 0.002022407716140151,
212
+ "rewards/rejected": -0.006252749357372522,
213
+ "step": 12
214
+ },
215
+ {
216
+ "epoch": 0.17126389460683408,
217
+ "grad_norm": 6973.720703125,
218
+ "learning_rate": 4.931607263312032e-07,
219
+ "logits/chosen": 0.20189328491687775,
220
+ "logits/rejected": 0.3522319495677948,
221
+ "logps/chosen": -140.02114868164062,
222
+ "logps/ref_chosen": -139.3595428466797,
223
+ "logps/ref_rejected": -178.2056121826172,
224
+ "logps/rejected": -179.11842346191406,
225
+ "loss": 2475.3787,
226
+ "rewards/accuracies": 0.6171875,
227
+ "rewards/chosen": -0.00661615002900362,
228
+ "rewards/margins": 0.0025120466016232967,
229
+ "rewards/rejected": -0.00912819616496563,
230
+ "step": 13
231
+ },
232
+ {
233
+ "epoch": 0.1844380403458213,
234
+ "grad_norm": 7222.79541015625,
235
+ "learning_rate": 4.9017129689421e-07,
236
+ "logits/chosen": 0.09214643388986588,
237
+ "logits/rejected": 0.28671640157699585,
238
+ "logps/chosen": -141.103271484375,
239
+ "logps/ref_chosen": -140.22817993164062,
240
+ "logps/ref_rejected": -174.04420471191406,
241
+ "logps/rejected": -174.9939727783203,
242
+ "loss": 2492.9717,
243
+ "rewards/accuracies": 0.53125,
244
+ "rewards/chosen": -0.008750887587666512,
245
+ "rewards/margins": 0.0007466625538654625,
246
+ "rewards/rejected": -0.009497551247477531,
247
+ "step": 14
248
+ },
249
+ {
250
+ "epoch": 0.19761218608480857,
251
+ "grad_norm": 9396.513671875,
252
+ "learning_rate": 4.866539188226085e-07,
253
+ "logits/chosen": 0.14158909022808075,
254
+ "logits/rejected": 0.22743283212184906,
255
+ "logps/chosen": -141.16696166992188,
256
+ "logps/ref_chosen": -140.21017456054688,
257
+ "logps/ref_rejected": -165.01068115234375,
258
+ "logps/rejected": -166.10667419433594,
259
+ "loss": 2486.5557,
260
+ "rewards/accuracies": 0.5859375,
261
+ "rewards/chosen": -0.009568018838763237,
262
+ "rewards/margins": 0.0013918390031903982,
263
+ "rewards/rejected": -0.010959859006106853,
264
+ "step": 15
265
+ },
266
+ {
267
+ "epoch": 0.2107863318237958,
268
+ "grad_norm": 6558.8779296875,
269
+ "learning_rate": 4.826163240767716e-07,
270
+ "logits/chosen": 0.1439928561449051,
271
+ "logits/rejected": 0.20027083158493042,
272
+ "logps/chosen": -135.67388916015625,
273
+ "logps/ref_chosen": -134.51571655273438,
274
+ "logps/ref_rejected": -160.91802978515625,
275
+ "logps/rejected": -162.40234375,
276
+ "loss": 2468.094,
277
+ "rewards/accuracies": 0.6796875,
278
+ "rewards/chosen": -0.011581514962017536,
279
+ "rewards/margins": 0.0032616225071251392,
280
+ "rewards/rejected": -0.014843138866126537,
281
+ "step": 16
282
+ },
283
+ {
284
+ "epoch": 0.22396047756278303,
285
+ "grad_norm": 9624.171875,
286
+ "learning_rate": 4.780673881662242e-07,
287
+ "logits/chosen": 0.09058184921741486,
288
+ "logits/rejected": 0.30712011456489563,
289
+ "logps/chosen": -138.65167236328125,
290
+ "logps/ref_chosen": -137.29457092285156,
291
+ "logps/ref_rejected": -186.57139587402344,
292
+ "logps/rejected": -188.1879425048828,
293
+ "loss": 2475.0437,
294
+ "rewards/accuracies": 0.6484375,
295
+ "rewards/chosen": -0.013570962473750114,
296
+ "rewards/margins": 0.0025946293026208878,
297
+ "rewards/rejected": -0.016165591776371002,
298
+ "step": 17
299
+ },
300
+ {
301
+ "epoch": 0.23713462330177026,
302
+ "grad_norm": 7499.15478515625,
303
+ "learning_rate": 4.730171106393466e-07,
304
+ "logits/chosen": 0.13107196986675262,
305
+ "logits/rejected": 0.23367160558700562,
306
+ "logps/chosen": -137.4244842529297,
307
+ "logps/ref_chosen": -135.82603454589844,
308
+ "logps/ref_rejected": -162.28997802734375,
309
+ "logps/rejected": -164.30157470703125,
310
+ "loss": 2459.6831,
311
+ "rewards/accuracies": 0.640625,
312
+ "rewards/chosen": -0.015984630212187767,
313
+ "rewards/margins": 0.004131443798542023,
314
+ "rewards/rejected": -0.02011607214808464,
315
+ "step": 18
316
+ },
317
+ {
318
+ "epoch": 0.2503087690407575,
319
+ "grad_norm": 6299.62109375,
320
+ "learning_rate": 4.6747659310219757e-07,
321
+ "logits/chosen": 0.17090073227882385,
322
+ "logits/rejected": 0.30368080735206604,
323
+ "logps/chosen": -144.9495849609375,
324
+ "logps/ref_chosen": -143.41900634765625,
325
+ "logps/ref_rejected": -173.9239501953125,
326
+ "logps/rejected": -176.06329345703125,
327
+ "loss": 2440.637,
328
+ "rewards/accuracies": 0.71875,
329
+ "rewards/chosen": -0.015305725857615471,
330
+ "rewards/margins": 0.006087546236813068,
331
+ "rewards/rejected": -0.021393269300460815,
332
+ "step": 19
333
+ },
334
+ {
335
+ "epoch": 0.2634829147797447,
336
+ "grad_norm": 7396.08349609375,
337
+ "learning_rate": 4.6145801481477433e-07,
338
+ "logits/chosen": 0.16462361812591553,
339
+ "logits/rejected": 0.30562156438827515,
340
+ "logps/chosen": -146.265625,
341
+ "logps/ref_chosen": -144.12081909179688,
342
+ "logps/ref_rejected": -185.55020141601562,
343
+ "logps/rejected": -188.32659912109375,
344
+ "loss": 2438.6282,
345
+ "rewards/accuracies": 0.7265625,
346
+ "rewards/chosen": -0.02144799381494522,
347
+ "rewards/margins": 0.006316186860203743,
348
+ "rewards/rejected": -0.027764180675148964,
349
+ "step": 20
350
+ },
351
+ {
352
+ "epoch": 0.276657060518732,
353
+ "grad_norm": 5270.61865234375,
354
+ "learning_rate": 4.549746059183561e-07,
355
+ "logits/chosen": 0.15787144005298615,
356
+ "logits/rejected": 0.27715587615966797,
357
+ "logps/chosen": -139.85423278808594,
358
+ "logps/ref_chosen": -137.74465942382812,
359
+ "logps/ref_rejected": -166.4859619140625,
360
+ "logps/rejected": -169.4452667236328,
361
+ "loss": 2417.2112,
362
+ "rewards/accuracies": 0.75,
363
+ "rewards/chosen": -0.0210958831012249,
364
+ "rewards/margins": 0.008497259579598904,
365
+ "rewards/rejected": -0.029593143612146378,
366
+ "step": 21
367
+ },
368
+ {
369
+ "epoch": 0.28983120625771924,
370
+ "grad_norm": 7718.4482421875,
371
+ "learning_rate": 4.480406183527823e-07,
372
+ "logits/chosen": 0.07220113277435303,
373
+ "logits/rejected": 0.29546162486076355,
374
+ "logps/chosen": -143.28038024902344,
375
+ "logps/ref_chosen": -140.8328094482422,
376
+ "logps/ref_rejected": -200.5518798828125,
377
+ "logps/rejected": -203.9213104248047,
378
+ "loss": 2410.8091,
379
+ "rewards/accuracies": 0.75,
380
+ "rewards/chosen": -0.02447575330734253,
381
+ "rewards/margins": 0.009218500927090645,
382
+ "rewards/rejected": -0.033694252371788025,
383
+ "step": 22
384
+ },
385
+ {
386
+ "epoch": 0.3030053519967065,
387
+ "grad_norm": 6451.75341796875,
388
+ "learning_rate": 4.4067129452759546e-07,
389
+ "logits/chosen": 0.07104746997356415,
390
+ "logits/rejected": 0.2862705588340759,
391
+ "logps/chosen": -138.75106811523438,
392
+ "logps/ref_chosen": -136.00917053222656,
393
+ "logps/ref_rejected": -180.5914306640625,
394
+ "logps/rejected": -184.22340393066406,
395
+ "loss": 2414.3352,
396
+ "rewards/accuracies": 0.75,
397
+ "rewards/chosen": -0.02741893380880356,
398
+ "rewards/margins": 0.008900967426598072,
399
+ "rewards/rejected": -0.036319900304079056,
400
+ "step": 23
401
+ },
402
+ {
403
+ "epoch": 0.3161794977356937,
404
+ "grad_norm": 5537.490234375,
405
+ "learning_rate": 4.3288283381591725e-07,
406
+ "logits/chosen": 0.12691445648670197,
407
+ "logits/rejected": 0.2488580346107483,
408
+ "logps/chosen": -146.79885864257812,
409
+ "logps/ref_chosen": -143.82127380371094,
410
+ "logps/ref_rejected": -182.13327026367188,
411
+ "logps/rejected": -186.1513671875,
412
+ "loss": 2399.553,
413
+ "rewards/accuracies": 0.734375,
414
+ "rewards/chosen": -0.02977580577135086,
415
+ "rewards/margins": 0.010404943488538265,
416
+ "rewards/rejected": -0.0401807501912117,
417
+ "step": 24
418
+ },
419
+ {
420
+ "epoch": 0.32935364347468093,
421
+ "grad_norm": 6902.609375,
422
+ "learning_rate": 4.246923569447104e-07,
423
+ "logits/chosen": 0.19381573796272278,
424
+ "logits/rejected": 0.31139570474624634,
425
+ "logps/chosen": -144.62013244628906,
426
+ "logps/ref_chosen": -141.2464141845703,
427
+ "logps/ref_rejected": -168.5917510986328,
428
+ "logps/rejected": -172.9250030517578,
429
+ "loss": 2407.001,
430
+ "rewards/accuracies": 0.7109375,
431
+ "rewards/chosen": -0.03373728320002556,
432
+ "rewards/margins": 0.009595153853297234,
433
+ "rewards/rejected": -0.04333243519067764,
434
+ "step": 25
435
+ },
436
+ {
437
+ "epoch": 0.34252778921366817,
438
+ "grad_norm": 6792.0068359375,
439
+ "learning_rate": 4.161178683597054e-07,
440
+ "logits/chosen": 0.14972905814647675,
441
+ "logits/rejected": 0.267787367105484,
442
+ "logps/chosen": -148.2871551513672,
443
+ "logps/ref_chosen": -144.67782592773438,
444
+ "logps/ref_rejected": -183.55374145507812,
445
+ "logps/rejected": -188.48240661621094,
446
+ "loss": 2372.5386,
447
+ "rewards/accuracies": 0.796875,
448
+ "rewards/chosen": -0.03609343245625496,
449
+ "rewards/margins": 0.013193339109420776,
450
+ "rewards/rejected": -0.049286771565675735,
451
+ "step": 26
452
+ },
453
+ {
454
+ "epoch": 0.3557019349526554,
455
+ "grad_norm": 7997.36669921875,
456
+ "learning_rate": 4.0717821664772124e-07,
457
+ "logits/chosen": 0.11141426116228104,
458
+ "logits/rejected": 0.28967005014419556,
459
+ "logps/chosen": -142.55812072753906,
460
+ "logps/ref_chosen": -138.5041046142578,
461
+ "logps/ref_rejected": -177.208251953125,
462
+ "logps/rejected": -182.5889892578125,
463
+ "loss": 2372.2795,
464
+ "rewards/accuracies": 0.734375,
465
+ "rewards/chosen": -0.04054022952914238,
466
+ "rewards/margins": 0.013267194852232933,
467
+ "rewards/rejected": -0.053807422518730164,
468
+ "step": 27
469
+ },
470
+ {
471
+ "epoch": 0.3688760806916426,
472
+ "grad_norm": 7562.548828125,
473
+ "learning_rate": 3.978930531033806e-07,
474
+ "logits/chosen": 0.09050436317920685,
475
+ "logits/rejected": 0.2789982855319977,
476
+ "logps/chosen": -142.0299072265625,
477
+ "logps/ref_chosen": -137.58804321289062,
478
+ "logps/ref_rejected": -182.34164428710938,
479
+ "logps/rejected": -188.1849822998047,
480
+ "loss": 2365.6448,
481
+ "rewards/accuracies": 0.7578125,
482
+ "rewards/chosen": -0.04441874474287033,
483
+ "rewards/margins": 0.014014637097716331,
484
+ "rewards/rejected": -0.058433376252651215,
485
+ "step": 28
486
+ },
487
+ {
488
+ "epoch": 0.3820502264306299,
489
+ "grad_norm": 10295.1181640625,
490
+ "learning_rate": 3.882827885312998e-07,
491
+ "logits/chosen": 0.13718749582767487,
492
+ "logits/rejected": 0.2508697807788849,
493
+ "logps/chosen": -144.1764373779297,
494
+ "logps/ref_chosen": -139.355712890625,
495
+ "logps/ref_rejected": -166.58685302734375,
496
+ "logps/rejected": -172.87887573242188,
497
+ "loss": 2359.4316,
498
+ "rewards/accuracies": 0.796875,
499
+ "rewards/chosen": -0.048207301646471024,
500
+ "rewards/margins": 0.014712938107550144,
501
+ "rewards/rejected": -0.0629202350974083,
502
+ "step": 29
503
+ },
504
+ {
505
+ "epoch": 0.39522437216961714,
506
+ "grad_norm": 6830.68994140625,
507
+ "learning_rate": 3.7836854837871044e-07,
508
+ "logits/chosen": 0.14999902248382568,
509
+ "logits/rejected": 0.27044931054115295,
510
+ "logps/chosen": -144.25474548339844,
511
+ "logps/ref_chosen": -138.8655548095703,
512
+ "logps/ref_rejected": -169.93161010742188,
513
+ "logps/rejected": -176.71615600585938,
514
+ "loss": 2366.7632,
515
+ "rewards/accuracies": 0.7109375,
516
+ "rewards/chosen": -0.05389188230037689,
517
+ "rewards/margins": 0.013953596353530884,
518
+ "rewards/rejected": -0.06784547120332718,
519
+ "step": 30
520
+ },
521
+ {
522
+ "epoch": 0.4083985179086044,
523
+ "grad_norm": 8562.919921875,
524
+ "learning_rate": 3.681721262971413e-07,
525
+ "logits/chosen": 0.1571384221315384,
526
+ "logits/rejected": 0.3112070560455322,
527
+ "logps/chosen": -144.13421630859375,
528
+ "logps/ref_chosen": -138.506103515625,
529
+ "logps/ref_rejected": -160.6241455078125,
530
+ "logps/rejected": -167.71922302246094,
531
+ "loss": 2360.6272,
532
+ "rewards/accuracies": 0.7265625,
533
+ "rewards/chosen": -0.056280914694070816,
534
+ "rewards/margins": 0.014669710770249367,
535
+ "rewards/rejected": -0.07095062732696533,
536
+ "step": 31
537
+ },
538
+ {
539
+ "epoch": 0.4215726636475916,
540
+ "grad_norm": 7112.58642578125,
541
+ "learning_rate": 3.577159362352426e-07,
542
+ "logits/chosen": 0.16715647280216217,
543
+ "logits/rejected": 0.32336658239364624,
544
+ "logps/chosen": -144.36634826660156,
545
+ "logps/ref_chosen": -138.49879455566406,
546
+ "logps/ref_rejected": -174.4591827392578,
547
+ "logps/rejected": -181.9716033935547,
548
+ "loss": 2344.2522,
549
+ "rewards/accuracies": 0.7421875,
550
+ "rewards/chosen": -0.05867544189095497,
551
+ "rewards/margins": 0.01644859090447426,
552
+ "rewards/rejected": -0.07512403279542923,
553
+ "step": 32
554
+ },
555
+ {
556
+ "epoch": 0.43474680938657884,
557
+ "grad_norm": 6419.78125,
558
+ "learning_rate": 3.470229631680624e-07,
559
+ "logits/chosen": 0.12648124992847443,
560
+ "logits/rejected": 0.25772759318351746,
561
+ "logps/chosen": -146.20086669921875,
562
+ "logps/ref_chosen": -140.21722412109375,
563
+ "logps/ref_rejected": -169.49217224121094,
564
+ "logps/rejected": -177.2689666748047,
565
+ "loss": 2331.8401,
566
+ "rewards/accuracies": 0.75,
567
+ "rewards/chosen": -0.059836432337760925,
568
+ "rewards/margins": 0.017931492999196053,
569
+ "rewards/rejected": -0.07776791602373123,
570
+ "step": 33
571
+ },
572
+ {
573
+ "epoch": 0.44792095512556607,
574
+ "grad_norm": 6666.31298828125,
575
+ "learning_rate": 3.361167125710832e-07,
576
+ "logits/chosen": 0.11497840285301208,
577
+ "logits/rejected": 0.32681411504745483,
578
+ "logps/chosen": -148.2799072265625,
579
+ "logps/ref_chosen": -142.15771484375,
580
+ "logps/ref_rejected": -182.51876831054688,
581
+ "logps/rejected": -190.4166717529297,
582
+ "loss": 2333.2249,
583
+ "rewards/accuracies": 0.7421875,
584
+ "rewards/chosen": -0.061221737414598465,
585
+ "rewards/margins": 0.017757374793291092,
586
+ "rewards/rejected": -0.07897911965847015,
587
+ "step": 34
588
+ },
589
+ {
590
+ "epoch": 0.4610951008645533,
591
+ "grad_norm": 8634.4833984375,
592
+ "learning_rate": 3.2502115875008516e-07,
593
+ "logits/chosen": 0.19959449768066406,
594
+ "logits/rejected": 0.3128213584423065,
595
+ "logps/chosen": -143.249267578125,
596
+ "logps/ref_chosen": -136.8671875,
597
+ "logps/ref_rejected": -161.7582550048828,
598
+ "logps/rejected": -170.11978149414062,
599
+ "loss": 2314.9158,
600
+ "rewards/accuracies": 0.7265625,
601
+ "rewards/chosen": -0.06382085382938385,
602
+ "rewards/margins": 0.01979430392384529,
603
+ "rewards/rejected": -0.08361515402793884,
604
+ "step": 35
605
+ },
606
+ {
607
+ "epoch": 0.47426924660354053,
608
+ "grad_norm": 7203.060546875,
609
+ "learning_rate": 3.137606921404191e-07,
610
+ "logits/chosen": 0.22031764686107635,
611
+ "logits/rejected": 0.35867929458618164,
612
+ "logps/chosen": -147.1063690185547,
613
+ "logps/ref_chosen": -139.9434814453125,
614
+ "logps/ref_rejected": -171.1022186279297,
615
+ "logps/rejected": -180.0121307373047,
616
+ "loss": 2337.103,
617
+ "rewards/accuracies": 0.7421875,
618
+ "rewards/chosen": -0.07162884622812271,
619
+ "rewards/margins": 0.017470190301537514,
620
+ "rewards/rejected": -0.08909902721643448,
621
+ "step": 36
622
+ },
623
+ {
624
+ "epoch": 0.4874433923425278,
625
+ "grad_norm": 9438.7119140625,
626
+ "learning_rate": 3.0236006569153616e-07,
627
+ "logits/chosen": 0.1601647287607193,
628
+ "logits/rejected": 0.3246475160121918,
629
+ "logps/chosen": -149.15200805664062,
630
+ "logps/ref_chosen": -142.24777221679688,
631
+ "logps/ref_rejected": -186.27542114257812,
632
+ "logps/rejected": -195.56056213378906,
633
+ "loss": 2276.2998,
634
+ "rewards/accuracies": 0.78125,
635
+ "rewards/chosen": -0.06904245913028717,
636
+ "rewards/margins": 0.023809153586626053,
637
+ "rewards/rejected": -0.09285160899162292,
638
+ "step": 37
639
+ },
640
+ {
641
+ "epoch": 0.500617538081515,
642
+ "grad_norm": 8125.13232421875,
643
+ "learning_rate": 2.9084434045463254e-07,
644
+ "logits/chosen": 0.18701249361038208,
645
+ "logits/rejected": 0.29296407103538513,
646
+ "logps/chosen": -151.26107788085938,
647
+ "logps/ref_chosen": -143.4994354248047,
648
+ "logps/ref_rejected": -169.76812744140625,
649
+ "logps/rejected": -179.5215606689453,
650
+ "loss": 2316.1897,
651
+ "rewards/accuracies": 0.765625,
652
+ "rewards/chosen": -0.07761640101671219,
653
+ "rewards/margins": 0.019917910918593407,
654
+ "rewards/rejected": -0.09753430634737015,
655
+ "step": 38
656
+ },
657
+ {
658
+ "epoch": 0.5137916838205022,
659
+ "grad_norm": 7210.390625,
660
+ "learning_rate": 2.7923883049302066e-07,
661
+ "logits/chosen": 0.20329824090003967,
662
+ "logits/rejected": 0.3062314987182617,
663
+ "logps/chosen": -149.1944580078125,
664
+ "logps/ref_chosen": -142.20091247558594,
665
+ "logps/ref_rejected": -176.95993041992188,
666
+ "logps/rejected": -186.2585906982422,
667
+ "loss": 2284.1282,
668
+ "rewards/accuracies": 0.78125,
669
+ "rewards/chosen": -0.06993547081947327,
670
+ "rewards/margins": 0.023050837218761444,
671
+ "rewards/rejected": -0.09298631548881531,
672
+ "step": 39
673
+ },
674
+ {
675
+ "epoch": 0.5269658295594895,
676
+ "grad_norm": 7052.74951171875,
677
+ "learning_rate": 2.6756904723632324e-07,
678
+ "logits/chosen": 0.2308526635169983,
679
+ "logits/rejected": 0.3400764465332031,
680
+ "logps/chosen": -145.32469177246094,
681
+ "logps/ref_chosen": -137.6454620361328,
682
+ "logps/ref_rejected": -168.80984497070312,
683
+ "logps/rejected": -178.9228057861328,
684
+ "loss": 2273.1941,
685
+ "rewards/accuracies": 0.7578125,
686
+ "rewards/chosen": -0.07679218798875809,
687
+ "rewards/margins": 0.024337470531463623,
688
+ "rewards/rejected": -0.10112965852022171,
689
+ "step": 40
690
+ },
691
+ {
692
+ "epoch": 0.5401399752984768,
693
+ "grad_norm": 6497.931640625,
694
+ "learning_rate": 2.5586064340081516e-07,
695
+ "logits/chosen": 0.20711341500282288,
696
+ "logits/rejected": 0.32196125388145447,
697
+ "logps/chosen": -152.06080627441406,
698
+ "logps/ref_chosen": -144.18096923828125,
699
+ "logps/ref_rejected": -175.95211791992188,
700
+ "logps/rejected": -185.96385192871094,
701
+ "loss": 2300.8403,
702
+ "rewards/accuracies": 0.7578125,
703
+ "rewards/chosen": -0.07879841327667236,
704
+ "rewards/margins": 0.0213189497590065,
705
+ "rewards/rejected": -0.10011736303567886,
706
+ "step": 41
707
+ },
708
+ {
709
+ "epoch": 0.553314121037464,
710
+ "grad_norm": 6679.0595703125,
711
+ "learning_rate": 2.4413935659918487e-07,
712
+ "logits/chosen": 0.18452338874340057,
713
+ "logits/rejected": 0.387422651052475,
714
+ "logps/chosen": -145.51397705078125,
715
+ "logps/ref_chosen": -138.06454467773438,
716
+ "logps/ref_rejected": -179.8441162109375,
717
+ "logps/rejected": -189.7871856689453,
718
+ "loss": 2267.5906,
719
+ "rewards/accuracies": 0.7578125,
720
+ "rewards/chosen": -0.07449443638324738,
721
+ "rewards/margins": 0.02493644505739212,
722
+ "rewards/rejected": -0.09943088889122009,
723
+ "step": 42
724
+ },
725
+ {
726
+ "epoch": 0.5664882667764513,
727
+ "grad_norm": 5415.99658203125,
728
+ "learning_rate": 2.3243095276367684e-07,
729
+ "logits/chosen": 0.2290109246969223,
730
+ "logits/rejected": 0.35180214047431946,
731
+ "logps/chosen": -149.4269256591797,
732
+ "logps/ref_chosen": -141.347900390625,
733
+ "logps/ref_rejected": -171.0642547607422,
734
+ "logps/rejected": -181.90652465820312,
735
+ "loss": 2242.7625,
736
+ "rewards/accuracies": 0.8125,
737
+ "rewards/chosen": -0.08079031854867935,
738
+ "rewards/margins": 0.027632439509034157,
739
+ "rewards/rejected": -0.10842276364564896,
740
+ "step": 43
741
+ },
742
+ {
743
+ "epoch": 0.5796624125154385,
744
+ "grad_norm": 7586.189453125,
745
+ "learning_rate": 2.2076116950697937e-07,
746
+ "logits/chosen": 0.10840879380702972,
747
+ "logits/rejected": 0.35155922174453735,
748
+ "logps/chosen": -149.24771118164062,
749
+ "logps/ref_chosen": -141.38162231445312,
750
+ "logps/ref_rejected": -187.5796356201172,
751
+ "logps/rejected": -198.4950408935547,
752
+ "loss": 2216.2781,
753
+ "rewards/accuracies": 0.8203125,
754
+ "rewards/chosen": -0.07866107672452927,
755
+ "rewards/margins": 0.030493203550577164,
756
+ "rewards/rejected": -0.10915428400039673,
757
+ "step": 44
758
+ },
759
+ {
760
+ "epoch": 0.5928365582544257,
761
+ "grad_norm": 9534.2294921875,
762
+ "learning_rate": 2.091556595453674e-07,
763
+ "logits/chosen": 0.27076855301856995,
764
+ "logits/rejected": 0.4277436137199402,
765
+ "logps/chosen": -151.55093383789062,
766
+ "logps/ref_chosen": -143.77825927734375,
767
+ "logps/ref_rejected": -179.0214385986328,
768
+ "logps/rejected": -189.74734497070312,
769
+ "loss": 2224.4258,
770
+ "rewards/accuracies": 0.859375,
771
+ "rewards/chosen": -0.07772687077522278,
772
+ "rewards/margins": 0.029532309621572495,
773
+ "rewards/rejected": -0.10725918412208557,
774
+ "step": 45
775
+ },
776
+ {
777
+ "epoch": 0.606010703993413,
778
+ "grad_norm": 7174.7802734375,
779
+ "learning_rate": 1.9763993430846392e-07,
780
+ "logits/chosen": 0.1256578415632248,
781
+ "logits/rejected": 0.3058658838272095,
782
+ "logps/chosen": -146.8641815185547,
783
+ "logps/ref_chosen": -138.49636840820312,
784
+ "logps/ref_rejected": -175.60797119140625,
785
+ "logps/rejected": -186.2463836669922,
786
+ "loss": 2294.2419,
787
+ "rewards/accuracies": 0.7109375,
788
+ "rewards/chosen": -0.08367808163166046,
789
+ "rewards/margins": 0.022705810144543648,
790
+ "rewards/rejected": -0.10638388246297836,
791
+ "step": 46
792
+ },
793
+ {
794
+ "epoch": 0.6191848497324002,
795
+ "grad_norm": 7637.0185546875,
796
+ "learning_rate": 1.862393078595809e-07,
797
+ "logits/chosen": 0.19172614812850952,
798
+ "logits/rejected": 0.3001164197921753,
799
+ "logps/chosen": -152.0642852783203,
800
+ "logps/ref_chosen": -143.7464141845703,
801
+ "logps/ref_rejected": -169.4178924560547,
802
+ "logps/rejected": -181.17225646972656,
803
+ "loss": 2180.1541,
804
+ "rewards/accuracies": 0.8359375,
805
+ "rewards/chosen": -0.08317889273166656,
806
+ "rewards/margins": 0.03436458110809326,
807
+ "rewards/rejected": -0.11754348129034042,
808
+ "step": 47
809
+ },
810
+ {
811
+ "epoch": 0.6323589954713874,
812
+ "grad_norm": 6842.74609375,
813
+ "learning_rate": 1.7497884124991485e-07,
814
+ "logits/chosen": 0.08567388355731964,
815
+ "logits/rejected": 0.31849536299705505,
816
+ "logps/chosen": -151.8147735595703,
817
+ "logps/ref_chosen": -143.42369079589844,
818
+ "logps/ref_rejected": -192.09017944335938,
819
+ "logps/rejected": -203.51661682128906,
820
+ "loss": 2217.6252,
821
+ "rewards/accuracies": 0.8125,
822
+ "rewards/chosen": -0.08391077816486359,
823
+ "rewards/margins": 0.03035370446741581,
824
+ "rewards/rejected": -0.11426447331905365,
825
+ "step": 48
826
+ },
827
+ {
828
+ "epoch": 0.6455331412103746,
829
+ "grad_norm": 7464.0966796875,
830
+ "learning_rate": 1.6388328742891678e-07,
831
+ "logits/chosen": 0.14193353056907654,
832
+ "logits/rejected": 0.29211774468421936,
833
+ "logps/chosen": -147.90036010742188,
834
+ "logps/ref_chosen": -139.34225463867188,
835
+ "logps/ref_rejected": -173.71649169921875,
836
+ "logps/rejected": -185.2205352783203,
837
+ "loss": 2228.885,
838
+ "rewards/accuracies": 0.7734375,
839
+ "rewards/chosen": -0.08558091521263123,
840
+ "rewards/margins": 0.029459496960043907,
841
+ "rewards/rejected": -0.11504041403532028,
842
+ "step": 49
843
+ },
844
+ {
845
+ "epoch": 0.6587072869493619,
846
+ "grad_norm": 8806.134765625,
847
+ "learning_rate": 1.5297703683193753e-07,
848
+ "logits/chosen": 0.16522561013698578,
849
+ "logits/rejected": 0.3208205997943878,
850
+ "logps/chosen": -150.81781005859375,
851
+ "logps/ref_chosen": -142.66964721679688,
852
+ "logps/ref_rejected": -179.97023010253906,
853
+ "logps/rejected": -191.62022399902344,
854
+ "loss": 2178.3289,
855
+ "rewards/accuracies": 0.828125,
856
+ "rewards/chosen": -0.08148160576820374,
857
+ "rewards/margins": 0.035018205642700195,
858
+ "rewards/rejected": -0.11649981141090393,
859
+ "step": 50
860
+ },
861
+ {
862
+ "epoch": 0.6718814326883491,
863
+ "grad_norm": 5882.73486328125,
864
+ "learning_rate": 1.422840637647574e-07,
865
+ "logits/chosen": 0.12343470007181168,
866
+ "logits/rejected": 0.21680085361003876,
867
+ "logps/chosen": -154.97280883789062,
868
+ "logps/ref_chosen": -147.04750061035156,
869
+ "logps/ref_rejected": -182.6226043701172,
870
+ "logps/rejected": -193.77963256835938,
871
+ "loss": 2203.8274,
872
+ "rewards/accuracies": 0.8046875,
873
+ "rewards/chosen": -0.0792531818151474,
874
+ "rewards/margins": 0.03231706842780113,
875
+ "rewards/rejected": -0.11157024651765823,
876
+ "step": 51
877
+ },
878
+ {
879
+ "epoch": 0.6850555784273363,
880
+ "grad_norm": 6423.96044921875,
881
+ "learning_rate": 1.3182787370285865e-07,
882
+ "logits/chosen": 0.20253154635429382,
883
+ "logits/rejected": 0.351491242647171,
884
+ "logps/chosen": -153.34129333496094,
885
+ "logps/ref_chosen": -145.28207397460938,
886
+ "logps/ref_rejected": -186.92506408691406,
887
+ "logps/rejected": -198.43634033203125,
888
+ "loss": 2184.8164,
889
+ "rewards/accuracies": 0.8046875,
890
+ "rewards/chosen": -0.08059230446815491,
891
+ "rewards/margins": 0.03452064096927643,
892
+ "rewards/rejected": -0.11511294543743134,
893
+ "step": 52
894
+ },
895
+ {
896
+ "epoch": 0.6982297241663236,
897
+ "grad_norm": 7110.8720703125,
898
+ "learning_rate": 1.2163145162128946e-07,
899
+ "logits/chosen": 0.17684641480445862,
900
+ "logits/rejected": 0.2714047133922577,
901
+ "logps/chosen": -154.22564697265625,
902
+ "logps/ref_chosen": -144.9042205810547,
903
+ "logps/ref_rejected": -181.88597106933594,
904
+ "logps/rejected": -193.96234130859375,
905
+ "loss": 2248.8911,
906
+ "rewards/accuracies": 0.765625,
907
+ "rewards/chosen": -0.0932142436504364,
908
+ "rewards/margins": 0.0275496207177639,
909
+ "rewards/rejected": -0.12076384574174881,
910
+ "step": 53
911
+ },
912
+ {
913
+ "epoch": 0.7114038699053108,
914
+ "grad_norm": 8480.2412109375,
915
+ "learning_rate": 1.1171721146870014e-07,
916
+ "logits/chosen": 0.1637565791606903,
917
+ "logits/rejected": 0.34545600414276123,
918
+ "logps/chosen": -147.90777587890625,
919
+ "logps/ref_chosen": -139.37796020507812,
920
+ "logps/ref_rejected": -178.37158203125,
921
+ "logps/rejected": -190.43238830566406,
922
+ "loss": 2175.6248,
923
+ "rewards/accuracies": 0.828125,
924
+ "rewards/chosen": -0.085298091173172,
925
+ "rewards/margins": 0.0353100560605526,
926
+ "rewards/rejected": -0.12060815095901489,
927
+ "step": 54
928
+ },
929
+ {
930
+ "epoch": 0.724578015644298,
931
+ "grad_norm": 6994.4423828125,
932
+ "learning_rate": 1.0210694689661939e-07,
933
+ "logits/chosen": 0.1886930912733078,
934
+ "logits/rejected": 0.311793714761734,
935
+ "logps/chosen": -147.7918701171875,
936
+ "logps/ref_chosen": -139.57748413085938,
937
+ "logps/ref_rejected": -163.42202758789062,
938
+ "logps/rejected": -175.12420654296875,
939
+ "loss": 2178.6426,
940
+ "rewards/accuracies": 0.8125,
941
+ "rewards/chosen": -0.08214367181062698,
942
+ "rewards/margins": 0.03487822040915489,
943
+ "rewards/rejected": -0.11702188849449158,
944
+ "step": 55
945
+ },
946
+ {
947
+ "epoch": 0.7377521613832853,
948
+ "grad_norm": 5469.5498046875,
949
+ "learning_rate": 9.282178335227883e-08,
950
+ "logits/chosen": 0.13419488072395325,
951
+ "logits/rejected": 0.32886138558387756,
952
+ "logps/chosen": -153.0216064453125,
953
+ "logps/ref_chosen": -143.66351318359375,
954
+ "logps/ref_rejected": -189.92372131347656,
955
+ "logps/rejected": -202.5775909423828,
956
+ "loss": 2202.1431,
957
+ "rewards/accuracies": 0.78125,
958
+ "rewards/chosen": -0.09358088672161102,
959
+ "rewards/margins": 0.0329577773809433,
960
+ "rewards/rejected": -0.12653866410255432,
961
+ "step": 56
962
+ },
963
+ {
964
+ "epoch": 0.7509263071222725,
965
+ "grad_norm": 10984.908203125,
966
+ "learning_rate": 8.388213164029459e-08,
967
+ "logits/chosen": 0.21511928737163544,
968
+ "logits/rejected": 0.34719422459602356,
969
+ "logps/chosen": -151.35519409179688,
970
+ "logps/ref_chosen": -142.55517578125,
971
+ "logps/ref_rejected": -175.55435180664062,
972
+ "logps/rejected": -187.24032592773438,
973
+ "loss": 2239.1248,
974
+ "rewards/accuracies": 0.7421875,
975
+ "rewards/chosen": -0.08800003677606583,
976
+ "rewards/margins": 0.028859596699476242,
977
+ "rewards/rejected": -0.11685963720083237,
978
+ "step": 57
979
+ },
980
+ {
981
+ "epoch": 0.7641004528612598,
982
+ "grad_norm": 8758.0439453125,
983
+ "learning_rate": 7.530764305528958e-08,
984
+ "logits/chosen": 0.20229403674602509,
985
+ "logits/rejected": 0.33734947443008423,
986
+ "logps/chosen": -151.44970703125,
987
+ "logps/ref_chosen": -142.6311492919922,
988
+ "logps/ref_rejected": -175.78897094726562,
989
+ "logps/rejected": -187.89028930664062,
990
+ "loss": 2198.1309,
991
+ "rewards/accuracies": 0.7734375,
992
+ "rewards/chosen": -0.08818576484918594,
993
+ "rewards/margins": 0.03282759338617325,
994
+ "rewards/rejected": -0.12101335823535919,
995
+ "step": 58
996
+ },
997
+ {
998
+ "epoch": 0.7772745986002471,
999
+ "grad_norm": 7517.16748046875,
1000
+ "learning_rate": 6.711716618408281e-08,
1001
+ "logits/chosen": 0.16748952865600586,
1002
+ "logits/rejected": 0.3588869273662567,
1003
+ "logps/chosen": -153.1207275390625,
1004
+ "logps/ref_chosen": -144.38674926757812,
1005
+ "logps/ref_rejected": -184.999267578125,
1006
+ "logps/rejected": -197.11062622070312,
1007
+ "loss": 2194.5862,
1008
+ "rewards/accuracies": 0.7734375,
1009
+ "rewards/chosen": -0.08733989298343658,
1010
+ "rewards/margins": 0.033773742616176605,
1011
+ "rewards/rejected": -0.12111362814903259,
1012
+ "step": 59
1013
+ },
1014
+ {
1015
+ "epoch": 0.7904487443392343,
1016
+ "grad_norm": 6131.287109375,
1017
+ "learning_rate": 5.932870547240454e-08,
1018
+ "logits/chosen": 0.2141285240650177,
1019
+ "logits/rejected": 0.3435683250427246,
1020
+ "logps/chosen": -152.48385620117188,
1021
+ "logps/ref_chosen": -143.2462158203125,
1022
+ "logps/ref_rejected": -177.8916778564453,
1023
+ "logps/rejected": -190.52423095703125,
1024
+ "loss": 2187.7061,
1025
+ "rewards/accuracies": 0.8046875,
1026
+ "rewards/chosen": -0.09237637370824814,
1027
+ "rewards/margins": 0.033949077129364014,
1028
+ "rewards/rejected": -0.12632544338703156,
1029
+ "step": 60
1030
+ },
1031
+ {
1032
+ "epoch": 0.8036228900782215,
1033
+ "grad_norm": 8281.1650390625,
1034
+ "learning_rate": 5.1959381647217665e-08,
1035
+ "logits/chosen": 0.1745128035545349,
1036
+ "logits/rejected": 0.3122703731060028,
1037
+ "logps/chosen": -152.68939208984375,
1038
+ "logps/ref_chosen": -143.92420959472656,
1039
+ "logps/ref_rejected": -176.6068115234375,
1040
+ "logps/rejected": -188.49099731445312,
1041
+ "loss": 2219.0474,
1042
+ "rewards/accuracies": 0.734375,
1043
+ "rewards/chosen": -0.08765168488025665,
1044
+ "rewards/margins": 0.031190264970064163,
1045
+ "rewards/rejected": -0.11884195357561111,
1046
+ "step": 61
1047
+ },
1048
+ {
1049
+ "epoch": 0.8167970358172087,
1050
+ "grad_norm": 5113.0146484375,
1051
+ "learning_rate": 4.502539408164385e-08,
1052
+ "logits/chosen": 0.13161124289035797,
1053
+ "logits/rejected": 0.2597178816795349,
1054
+ "logps/chosen": -149.14198303222656,
1055
+ "logps/ref_chosen": -140.12322998046875,
1056
+ "logps/ref_rejected": -171.29669189453125,
1057
+ "logps/rejected": -183.97909545898438,
1058
+ "loss": 2163.1401,
1059
+ "rewards/accuracies": 0.8125,
1060
+ "rewards/chosen": -0.09018754214048386,
1061
+ "rewards/margins": 0.03663650527596474,
1062
+ "rewards/rejected": -0.1268240511417389,
1063
+ "step": 62
1064
+ },
1065
+ {
1066
+ "epoch": 0.829971181556196,
1067
+ "grad_norm": 7166.9453125,
1068
+ "learning_rate": 3.854198518522564e-08,
1069
+ "logits/chosen": 0.22974729537963867,
1070
+ "logits/rejected": 0.36869755387306213,
1071
+ "logps/chosen": -145.85195922851562,
1072
+ "logps/ref_chosen": -136.71630859375,
1073
+ "logps/ref_rejected": -171.1470947265625,
1074
+ "logps/rejected": -183.384765625,
1075
+ "loss": 2217.2756,
1076
+ "rewards/accuracies": 0.71875,
1077
+ "rewards/chosen": -0.09135645627975464,
1078
+ "rewards/margins": 0.031020279973745346,
1079
+ "rewards/rejected": -0.12237672507762909,
1080
+ "step": 63
1081
+ },
1082
+ {
1083
+ "epoch": 0.8431453272951832,
1084
+ "grad_norm": 7681.93994140625,
1085
+ "learning_rate": 3.2523406897802444e-08,
1086
+ "logits/chosen": 0.23416659235954285,
1087
+ "logits/rejected": 0.36190101504325867,
1088
+ "logps/chosen": -154.23883056640625,
1089
+ "logps/ref_chosen": -144.72784423828125,
1090
+ "logps/ref_rejected": -181.54769897460938,
1091
+ "logps/rejected": -194.52224731445312,
1092
+ "loss": 2186.8882,
1093
+ "rewards/accuracies": 0.75,
1094
+ "rewards/chosen": -0.09511007368564606,
1095
+ "rewards/margins": 0.03463532403111458,
1096
+ "rewards/rejected": -0.12974540889263153,
1097
+ "step": 64
1098
+ },
1099
+ {
1100
+ "epoch": 0.8563194730341704,
1101
+ "grad_norm": 7177.78369140625,
1102
+ "learning_rate": 2.6982889360653376e-08,
1103
+ "logits/chosen": 0.17723366618156433,
1104
+ "logits/rejected": 0.3242289125919342,
1105
+ "logps/chosen": -151.72543334960938,
1106
+ "logps/ref_chosen": -142.64617919921875,
1107
+ "logps/ref_rejected": -174.40614318847656,
1108
+ "logps/rejected": -186.78662109375,
1109
+ "loss": 2196.0581,
1110
+ "rewards/accuracies": 0.796875,
1111
+ "rewards/chosen": -0.09079259634017944,
1112
+ "rewards/margins": 0.033012229949235916,
1113
+ "rewards/rejected": -0.12380482256412506,
1114
+ "step": 65
1115
+ },
1116
+ {
1117
+ "epoch": 0.8694936187731577,
1118
+ "grad_norm": 8175.220703125,
1119
+ "learning_rate": 2.1932611833775843e-08,
1120
+ "logits/chosen": 0.08193757385015488,
1121
+ "logits/rejected": 0.26095396280288696,
1122
+ "logps/chosen": -147.0934295654297,
1123
+ "logps/ref_chosen": -138.63568115234375,
1124
+ "logps/ref_rejected": -182.35244750976562,
1125
+ "logps/rejected": -194.43313598632812,
1126
+ "loss": 2168.0254,
1127
+ "rewards/accuracies": 0.796875,
1128
+ "rewards/chosen": -0.08457762002944946,
1129
+ "rewards/margins": 0.03622942045331001,
1130
+ "rewards/rejected": -0.12080704420804977,
1131
+ "step": 66
1132
+ },
1133
+ {
1134
+ "epoch": 0.8826677645121449,
1135
+ "grad_norm": 7215.3154296875,
1136
+ "learning_rate": 1.738367592322837e-08,
1137
+ "logits/chosen": 0.1766711324453354,
1138
+ "logits/rejected": 0.3498009741306305,
1139
+ "logps/chosen": -150.53700256347656,
1140
+ "logps/ref_chosen": -141.5865478515625,
1141
+ "logps/ref_rejected": -185.27081298828125,
1142
+ "logps/rejected": -198.028564453125,
1143
+ "loss": 2155.2078,
1144
+ "rewards/accuracies": 0.8125,
1145
+ "rewards/chosen": -0.0895046666264534,
1146
+ "rewards/margins": 0.03807291388511658,
1147
+ "rewards/rejected": -0.12757760286331177,
1148
+ "step": 67
1149
+ },
1150
+ {
1151
+ "epoch": 0.8958419102511321,
1152
+ "grad_norm": 8997.7958984375,
1153
+ "learning_rate": 1.3346081177391472e-08,
1154
+ "logits/chosen": 0.14675183594226837,
1155
+ "logits/rejected": 0.3305708169937134,
1156
+ "logps/chosen": -148.1304931640625,
1157
+ "logps/ref_chosen": -139.1151580810547,
1158
+ "logps/ref_rejected": -176.0420684814453,
1159
+ "logps/rejected": -188.79638671875,
1160
+ "loss": 2163.0139,
1161
+ "rewards/accuracies": 0.796875,
1162
+ "rewards/chosen": -0.09015330672264099,
1163
+ "rewards/margins": 0.03738997504115105,
1164
+ "rewards/rejected": -0.12754328548908234,
1165
+ "step": 68
1166
+ },
1167
+ {
1168
+ "epoch": 0.9090160559901194,
1169
+ "grad_norm": 6634.298828125,
1170
+ "learning_rate": 9.828703105789981e-09,
1171
+ "logits/chosen": 0.11062157154083252,
1172
+ "logits/rejected": 0.26717525720596313,
1173
+ "logps/chosen": -157.52674865722656,
1174
+ "logps/ref_chosen": -148.0703125,
1175
+ "logps/ref_rejected": -185.28785705566406,
1176
+ "logps/rejected": -197.8096923828125,
1177
+ "loss": 2219.3191,
1178
+ "rewards/accuracies": 0.765625,
1179
+ "rewards/chosen": -0.09456441551446915,
1180
+ "rewards/margins": 0.030653683468699455,
1181
+ "rewards/rejected": -0.12521810829639435,
1182
+ "step": 69
1183
+ },
1184
+ {
1185
+ "epoch": 0.9221902017291066,
1186
+ "grad_norm": 6588.52099609375,
1187
+ "learning_rate": 6.839273668796747e-09,
1188
+ "logits/chosen": 0.20371803641319275,
1189
+ "logits/rejected": 0.38707682490348816,
1190
+ "logps/chosen": -150.7587127685547,
1191
+ "logps/ref_chosen": -142.1817169189453,
1192
+ "logps/ref_rejected": -183.52871704101562,
1193
+ "logps/rejected": -195.626953125,
1194
+ "loss": 2180.2317,
1195
+ "rewards/accuracies": 0.7734375,
1196
+ "rewards/chosen": -0.08577002584934235,
1197
+ "rewards/margins": 0.03521224111318588,
1198
+ "rewards/rejected": -0.12098225951194763,
1199
+ "step": 70
1200
+ },
1201
+ {
1202
+ "epoch": 0.9353643474680938,
1203
+ "grad_norm": 7922.1845703125,
1204
+ "learning_rate": 4.384364281105973e-09,
1205
+ "logits/chosen": 0.14600388705730438,
1206
+ "logits/rejected": 0.3577485978603363,
1207
+ "logps/chosen": -151.2028045654297,
1208
+ "logps/ref_chosen": -142.00233459472656,
1209
+ "logps/ref_rejected": -188.67965698242188,
1210
+ "logps/rejected": -201.70025634765625,
1211
+ "loss": 2152.5889,
1212
+ "rewards/accuracies": 0.7890625,
1213
+ "rewards/chosen": -0.09200464934110641,
1214
+ "rewards/margins": 0.038201265037059784,
1215
+ "rewards/rejected": -0.1302059143781662,
1216
+ "step": 71
1217
+ },
1218
+ {
1219
+ "epoch": 0.9485384932070811,
1220
+ "grad_norm": 6042.76123046875,
1221
+ "learning_rate": 2.469371366337264e-09,
1222
+ "logits/chosen": 0.18784670531749725,
1223
+ "logits/rejected": 0.33177098631858826,
1224
+ "logps/chosen": -151.64651489257812,
1225
+ "logps/ref_chosen": -142.16261291503906,
1226
+ "logps/ref_rejected": -195.17788696289062,
1227
+ "logps/rejected": -207.6988983154297,
1228
+ "loss": 2222.146,
1229
+ "rewards/accuracies": 0.7578125,
1230
+ "rewards/chosen": -0.09483905881643295,
1231
+ "rewards/margins": 0.030371030792593956,
1232
+ "rewards/rejected": -0.12521009147167206,
1233
+ "step": 72
1234
+ },
1235
+ {
1236
+ "epoch": 0.9617126389460683,
1237
+ "grad_norm": 5766.6953125,
1238
+ "learning_rate": 1.0985044945254762e-09,
1239
+ "logits/chosen": 0.13510531187057495,
1240
+ "logits/rejected": 0.3228178024291992,
1241
+ "logps/chosen": -149.89263916015625,
1242
+ "logps/ref_chosen": -140.62818908691406,
1243
+ "logps/ref_rejected": -181.2576141357422,
1244
+ "logps/rejected": -194.0572509765625,
1245
+ "loss": 2178.6985,
1246
+ "rewards/accuracies": 0.796875,
1247
+ "rewards/chosen": -0.09264436364173889,
1248
+ "rewards/margins": 0.035351961851119995,
1249
+ "rewards/rejected": -0.12799634039402008,
1250
+ "step": 73
1251
+ },
1252
+ {
1253
+ "epoch": 0.9748867846850556,
1254
+ "grad_norm": 8777.2763671875,
1255
+ "learning_rate": 2.7477712857215675e-10,
1256
+ "logits/chosen": 0.14389634132385254,
1257
+ "logits/rejected": 0.3162282109260559,
1258
+ "logps/chosen": -151.93350219726562,
1259
+ "logps/ref_chosen": -143.0329132080078,
1260
+ "logps/ref_rejected": -187.8455810546875,
1261
+ "logps/rejected": -200.83340454101562,
1262
+ "loss": 2124.8625,
1263
+ "rewards/accuracies": 0.8515625,
1264
+ "rewards/chosen": -0.08900578320026398,
1265
+ "rewards/margins": 0.040872570127248764,
1266
+ "rewards/rejected": -0.12987834215164185,
1267
+ "step": 74
1268
+ },
1269
+ {
1270
+ "epoch": 0.9880609304240429,
1271
+ "grad_norm": 6027.6533203125,
1272
+ "learning_rate": 0.0,
1273
+ "logits/chosen": 0.14975285530090332,
1274
+ "logits/rejected": 0.2791685461997986,
1275
+ "logps/chosen": -151.98268127441406,
1276
+ "logps/ref_chosen": -142.6675262451172,
1277
+ "logps/ref_rejected": -172.9785614013672,
1278
+ "logps/rejected": -185.24148559570312,
1279
+ "loss": 2232.3572,
1280
+ "rewards/accuracies": 0.7421875,
1281
+ "rewards/chosen": -0.09315158426761627,
1282
+ "rewards/margins": 0.029477719217538834,
1283
+ "rewards/rejected": -0.12262929230928421,
1284
+ "step": 75
1285
+ },
1286
+ {
1287
+ "epoch": 0.9880609304240429,
1288
+ "step": 75,
1289
+ "total_flos": 0.0,
1290
+ "train_loss": 2318.3018196614585,
1291
+ "train_runtime": 5362.5076,
1292
+ "train_samples_per_second": 1.812,
1293
+ "train_steps_per_second": 0.014
1294
+ }
1295
+ ],
1296
+ "logging_steps": 1,
1297
+ "max_steps": 75,
1298
+ "num_input_tokens_seen": 0,
1299
+ "num_train_epochs": 1,
1300
+ "save_steps": 64,
1301
+ "stateful_callbacks": {
1302
+ "TrainerControl": {
1303
+ "args": {
1304
+ "should_epoch_stop": false,
1305
+ "should_evaluate": false,
1306
+ "should_log": false,
1307
+ "should_save": true,
1308
+ "should_training_stop": true
1309
+ },
1310
+ "attributes": {}
1311
+ }
1312
+ },
1313
+ "total_flos": 0.0,
1314
+ "train_batch_size": 2,
1315
+ "trial_name": null,
1316
+ "trial_params": null
1317
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea31e2520a407dfedcf990d30d6e5ea37a809e00c66520b0daccabcc98bad11
3
+ size 7352
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: /home/v-liuzichuan/huggingface/Llama-3.2-3B-Instruct
4
+ tags:
5
+ - alignment-handbook
6
+ - generated_from_trainer
7
+ datasets:
8
+ - /home/v-liuzichuan/huggingface/princeton-nlp/llama3-math
9
+ model-index:
10
+ - name: Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3
18
+
19
+ This model is a fine-tuned version of [/home/v-liuzichuan/huggingface/Llama-3.2-3B-Instruct](https://huggingface.co//home/v-liuzichuan/huggingface/Llama-3.2-3B-Instruct) on the /home/v-liuzichuan/huggingface/princeton-nlp/llama3-math dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-07
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - gradient_accumulation_steps: 64
44
+ - total_train_batch_size: 128
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 1
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.45.2
57
+ - Pytorch 2.5.1+cu121
58
+ - Datasets 3.5.0
59
+ - Tokenizers 0.20.3
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9969120977149523,
3
+ "total_flos": 0.0,
4
+ "train_loss": 1752.3481854006056,
5
+ "train_runtime": 13961.4025,
6
+ "train_samples": 29145,
7
+ "train_samples_per_second": 2.088,
8
+ "train_steps_per_second": 0.016
9
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/v-liuzichuan/huggingface/Llama-3.2-3B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 24,
23
+ "num_hidden_layers": 28,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.45.2",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.45.2"
12
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fa267e0c272699d33e3c070b9c97b3382601e63c6fd0f4084897b51d094a0ec
3
+ size 4965799096
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a1e6860342e9724eb4d182ffb3d8ad250457cc1f6e46b3627215784440328b0
3
+ size 2247734992
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7213504512
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.norm.weight": "model-00002-of-00002.safetensors"
261
+ }
262
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/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
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/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": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
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": "<|eom_id|>",
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": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
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": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
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": 2048,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9969120977149523,
3
+ "total_flos": 0.0,
4
+ "train_loss": 1752.3481854006056,
5
+ "train_runtime": 13961.4025,
6
+ "train_samples": 29145,
7
+ "train_samples_per_second": 2.088,
8
+ "train_steps_per_second": 0.016
9
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk1_epoch3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72f9eefd5644f3e7b04a1fb2cb27d27728da16ee4e5ab23ebbe27b18bb9e5302
3
+ size 7352
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: /home/v-liuzichuan/huggingface/Llama-3.2-3B-Instruct
4
+ tags:
5
+ - alignment-handbook
6
+ - generated_from_trainer
7
+ datasets:
8
+ - /home/v-liuzichuan/huggingface/princeton-nlp/llama3-math
9
+ model-index:
10
+ - name: '2'
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # 2
18
+
19
+ This model is a fine-tuned version of [/home/v-liuzichuan/huggingface/Llama-3.2-3B-Instruct](https://huggingface.co//home/v-liuzichuan/huggingface/Llama-3.2-3B-Instruct) on the /home/v-liuzichuan/huggingface/princeton-nlp/llama3-math dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-07
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - gradient_accumulation_steps: 64
44
+ - total_train_batch_size: 128
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 1
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.45.2
57
+ - Pytorch 2.5.1+cu121
58
+ - Datasets 3.5.0
59
+ - Tokenizers 0.20.3
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9880609304240429,
3
+ "total_flos": 0.0,
4
+ "train_loss": 1284.6718611653646,
5
+ "train_runtime": 5197.2653,
6
+ "train_samples": 9715,
7
+ "train_samples_per_second": 1.869,
8
+ "train_steps_per_second": 0.014
9
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/v-liuzichuan/dpo/outputs_ipo//temp_path",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 24,
23
+ "num_hidden_layers": 28,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.45.2",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.45.2"
12
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a9abeae06bf7f918b6ca8011797790ab30a4c85410abb0e841a0a31df227c3c
3
+ size 4965799096
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b654f33377137c4ff410e5ff4844fbf6db90b7013eda592e5d8992e1e3214774
3
+ size 2247734992
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7213504512
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.norm.weight": "model-00002-of-00002.safetensors"
261
+ }
262
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/raw_datasets.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d89ef369c3a210b3f0617ba98bcbe2181b12d114b10eaf1ca89f1b55c7000130
3
+ size 14697198
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/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
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/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": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
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": "<|eom_id|>",
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": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
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": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
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": 2048,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9880609304240429,
3
+ "total_flos": 0.0,
4
+ "train_loss": 1284.6718611653646,
5
+ "train_runtime": 5197.2653,
6
+ "train_samples": 9715,
7
+ "train_samples_per_second": 1.869,
8
+ "train_steps_per_second": 0.014
9
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/trainer_state.json ADDED
@@ -0,0 +1,1392 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9880609304240429,
5
+ "eval_steps": 500,
6
+ "global_step": 75,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.013174145738987238,
13
+ "grad_norm": 23949.7109375,
14
+ "learning_rate": 6.25e-08,
15
+ "logits/chosen": -0.8008705973625183,
16
+ "logits/rejected": -0.8651990294456482,
17
+ "logps/chosen": -250.500244140625,
18
+ "logps/ref_chosen": -254.47015380859375,
19
+ "logps/ref_rejected": -418.95074462890625,
20
+ "logps/rejected": -411.23785400390625,
21
+ "loss": 1468.7465,
22
+ "rewards/accuracies": 0.3046875,
23
+ "rewards/chosen": 0.03969910740852356,
24
+ "rewards/margins": -0.03742925450205803,
25
+ "rewards/rejected": 0.0771283507347107,
26
+ "sft_loss": 0.9547704458236694,
27
+ "step": 1
28
+ },
29
+ {
30
+ "epoch": 0.026348291477974475,
31
+ "grad_norm": 42517.4296875,
32
+ "learning_rate": 1.25e-07,
33
+ "logits/chosen": -0.8648843765258789,
34
+ "logits/rejected": -0.8835014700889587,
35
+ "logps/chosen": -271.94342041015625,
36
+ "logps/ref_chosen": -276.519775390625,
37
+ "logps/ref_rejected": -435.0823669433594,
38
+ "logps/rejected": -427.2591857910156,
39
+ "loss": 1440.641,
40
+ "rewards/accuracies": 0.34375,
41
+ "rewards/chosen": 0.045763421803712845,
42
+ "rewards/margins": -0.03246838226914406,
43
+ "rewards/rejected": 0.0782318040728569,
44
+ "sft_loss": 0.9081498980522156,
45
+ "step": 2
46
+ },
47
+ {
48
+ "epoch": 0.03952243721696171,
49
+ "grad_norm": 45039.2109375,
50
+ "learning_rate": 1.875e-07,
51
+ "logits/chosen": -0.7890776991844177,
52
+ "logits/rejected": -0.8727779984474182,
53
+ "logps/chosen": -253.0457763671875,
54
+ "logps/ref_chosen": -257.1988220214844,
55
+ "logps/ref_rejected": -393.6779479980469,
56
+ "logps/rejected": -387.13726806640625,
57
+ "loss": 1390.0684,
58
+ "rewards/accuracies": 0.34375,
59
+ "rewards/chosen": 0.04153094068169594,
60
+ "rewards/margins": -0.023875586688518524,
61
+ "rewards/rejected": 0.06540653109550476,
62
+ "sft_loss": 0.8998649716377258,
63
+ "step": 3
64
+ },
65
+ {
66
+ "epoch": 0.05269658295594895,
67
+ "grad_norm": 40517.47265625,
68
+ "learning_rate": 2.5e-07,
69
+ "logits/chosen": -0.7816249132156372,
70
+ "logits/rejected": -0.8107084035873413,
71
+ "logps/chosen": -260.0189208984375,
72
+ "logps/ref_chosen": -264.57086181640625,
73
+ "logps/ref_rejected": -404.1727600097656,
74
+ "logps/rejected": -396.4281005859375,
75
+ "loss": 1439.671,
76
+ "rewards/accuracies": 0.3046875,
77
+ "rewards/chosen": 0.04551965743303299,
78
+ "rewards/margins": -0.03192698955535889,
79
+ "rewards/rejected": 0.07744664698839188,
80
+ "sft_loss": 0.9242280721664429,
81
+ "step": 4
82
+ },
83
+ {
84
+ "epoch": 0.06587072869493618,
85
+ "grad_norm": 40508.13671875,
86
+ "learning_rate": 3.1249999999999997e-07,
87
+ "logits/chosen": -0.7920335531234741,
88
+ "logits/rejected": -0.8334716558456421,
89
+ "logps/chosen": -257.8485107421875,
90
+ "logps/ref_chosen": -261.6973571777344,
91
+ "logps/ref_rejected": -415.48101806640625,
92
+ "logps/rejected": -408.35888671875,
93
+ "loss": 1439.3862,
94
+ "rewards/accuracies": 0.2578125,
95
+ "rewards/chosen": 0.03848864510655403,
96
+ "rewards/margins": -0.0327322855591774,
97
+ "rewards/rejected": 0.07122092694044113,
98
+ "sft_loss": 0.9617606401443481,
99
+ "step": 5
100
+ },
101
+ {
102
+ "epoch": 0.07904487443392343,
103
+ "grad_norm": 67280.8203125,
104
+ "learning_rate": 3.75e-07,
105
+ "logits/chosen": -0.8593892455101013,
106
+ "logits/rejected": -0.9203681349754333,
107
+ "logps/chosen": -250.87802124023438,
108
+ "logps/ref_chosen": -254.50120544433594,
109
+ "logps/ref_rejected": -415.44366455078125,
110
+ "logps/rejected": -408.802734375,
111
+ "loss": 1426.8674,
112
+ "rewards/accuracies": 0.34375,
113
+ "rewards/chosen": 0.03623175993561745,
114
+ "rewards/margins": -0.030177462846040726,
115
+ "rewards/rejected": 0.06640923023223877,
116
+ "sft_loss": 0.8602447509765625,
117
+ "step": 6
118
+ },
119
+ {
120
+ "epoch": 0.09221902017291066,
121
+ "grad_norm": 36309.33984375,
122
+ "learning_rate": 4.375e-07,
123
+ "logits/chosen": -0.8027951121330261,
124
+ "logits/rejected": -0.8602517247200012,
125
+ "logps/chosen": -253.07276916503906,
126
+ "logps/ref_chosen": -256.30010986328125,
127
+ "logps/ref_rejected": -417.3987731933594,
128
+ "logps/rejected": -413.0194396972656,
129
+ "loss": 1319.4021,
130
+ "rewards/accuracies": 0.4375,
131
+ "rewards/chosen": 0.03227325156331062,
132
+ "rewards/margins": -0.011520068161189556,
133
+ "rewards/rejected": 0.043793320655822754,
134
+ "sft_loss": 0.9406993985176086,
135
+ "step": 7
136
+ },
137
+ {
138
+ "epoch": 0.1053931659118979,
139
+ "grad_norm": 58247.61328125,
140
+ "learning_rate": 5e-07,
141
+ "logits/chosen": -0.8113671541213989,
142
+ "logits/rejected": -0.8746984004974365,
143
+ "logps/chosen": -261.3500061035156,
144
+ "logps/ref_chosen": -262.356201171875,
145
+ "logps/ref_rejected": -429.6075439453125,
146
+ "logps/rejected": -429.34735107421875,
147
+ "loss": 1226.9708,
148
+ "rewards/accuracies": 0.484375,
149
+ "rewards/chosen": 0.010061981156468391,
150
+ "rewards/margins": 0.007459938060492277,
151
+ "rewards/rejected": 0.002602042630314827,
152
+ "sft_loss": 0.925779402256012,
153
+ "step": 8
154
+ },
155
+ {
156
+ "epoch": 0.11856731165088513,
157
+ "grad_norm": 35830.9296875,
158
+ "learning_rate": 4.997252228714278e-07,
159
+ "logits/chosen": -0.7887070178985596,
160
+ "logits/rejected": -0.8501583933830261,
161
+ "logps/chosen": -247.213623046875,
162
+ "logps/ref_chosen": -246.46566772460938,
163
+ "logps/ref_rejected": -401.689208984375,
164
+ "logps/rejected": -405.4938659667969,
165
+ "loss": 1137.1165,
166
+ "rewards/accuracies": 0.609375,
167
+ "rewards/chosen": -0.007479269523173571,
168
+ "rewards/margins": 0.030567554756999016,
169
+ "rewards/rejected": -0.03804682567715645,
170
+ "sft_loss": 0.9024340510368347,
171
+ "step": 9
172
+ },
173
+ {
174
+ "epoch": 0.13174145738987236,
175
+ "grad_norm": 49081.078125,
176
+ "learning_rate": 4.989014955054745e-07,
177
+ "logits/chosen": -0.7538288831710815,
178
+ "logits/rejected": -0.8280922174453735,
179
+ "logps/chosen": -260.5111389160156,
180
+ "logps/ref_chosen": -255.78009033203125,
181
+ "logps/ref_rejected": -355.2666015625,
182
+ "logps/rejected": -364.0128173828125,
183
+ "loss": 1120.6088,
184
+ "rewards/accuracies": 0.6640625,
185
+ "rewards/chosen": -0.047310683876276016,
186
+ "rewards/margins": 0.04015128314495087,
187
+ "rewards/rejected": -0.08746197074651718,
188
+ "sft_loss": 0.9213616847991943,
189
+ "step": 10
190
+ },
191
+ {
192
+ "epoch": 0.14491560312885962,
193
+ "grad_norm": 27151.37109375,
194
+ "learning_rate": 4.975306286336627e-07,
195
+ "logits/chosen": -0.8138033747673035,
196
+ "logits/rejected": -0.8641115427017212,
197
+ "logps/chosen": -279.50128173828125,
198
+ "logps/ref_chosen": -268.767578125,
199
+ "logps/ref_rejected": -417.3045654296875,
200
+ "logps/rejected": -440.1104431152344,
201
+ "loss": 1080.8665,
202
+ "rewards/accuracies": 0.6953125,
203
+ "rewards/chosen": -0.10733672231435776,
204
+ "rewards/margins": 0.12072216719388962,
205
+ "rewards/rejected": -0.22805888950824738,
206
+ "sft_loss": 0.9601907730102539,
207
+ "step": 11
208
+ },
209
+ {
210
+ "epoch": 0.15808974886784685,
211
+ "grad_norm": 35450.01953125,
212
+ "learning_rate": 4.956156357188939e-07,
213
+ "logits/chosen": -0.7551673650741577,
214
+ "logits/rejected": -0.8324231505393982,
215
+ "logps/chosen": -274.9906921386719,
216
+ "logps/ref_chosen": -261.2640380859375,
217
+ "logps/ref_rejected": -356.03948974609375,
218
+ "logps/rejected": -378.89349365234375,
219
+ "loss": 1123.4912,
220
+ "rewards/accuracies": 0.6484375,
221
+ "rewards/chosen": -0.1372665911912918,
222
+ "rewards/margins": 0.09127368032932281,
223
+ "rewards/rejected": -0.22854028642177582,
224
+ "sft_loss": 1.0183186531066895,
225
+ "step": 12
226
+ },
227
+ {
228
+ "epoch": 0.17126389460683408,
229
+ "grad_norm": 31516.70703125,
230
+ "learning_rate": 4.931607263312032e-07,
231
+ "logits/chosen": -0.7455427050590515,
232
+ "logits/rejected": -0.816511332988739,
233
+ "logps/chosen": -289.495361328125,
234
+ "logps/ref_chosen": -272.1609191894531,
235
+ "logps/ref_rejected": -417.3423767089844,
236
+ "logps/rejected": -454.0290222167969,
237
+ "loss": 1218.0366,
238
+ "rewards/accuracies": 0.6796875,
239
+ "rewards/chosen": -0.17334474623203278,
240
+ "rewards/margins": 0.19352208077907562,
241
+ "rewards/rejected": -0.366866797208786,
242
+ "sft_loss": 1.0172396898269653,
243
+ "step": 13
244
+ },
245
+ {
246
+ "epoch": 0.1844380403458213,
247
+ "grad_norm": 22413.31640625,
248
+ "learning_rate": 4.9017129689421e-07,
249
+ "logits/chosen": -0.8126018643379211,
250
+ "logits/rejected": -0.8541157245635986,
251
+ "logps/chosen": -272.24163818359375,
252
+ "logps/ref_chosen": -254.89801025390625,
253
+ "logps/ref_rejected": -403.5438537597656,
254
+ "logps/rejected": -441.9024963378906,
255
+ "loss": 1253.6353,
256
+ "rewards/accuracies": 0.765625,
257
+ "rewards/chosen": -0.17343664169311523,
258
+ "rewards/margins": 0.21014949679374695,
259
+ "rewards/rejected": -0.38358616828918457,
260
+ "sft_loss": 0.9973514080047607,
261
+ "step": 14
262
+ },
263
+ {
264
+ "epoch": 0.19761218608480857,
265
+ "grad_norm": 299858.125,
266
+ "learning_rate": 4.866539188226085e-07,
267
+ "logits/chosen": -0.821877658367157,
268
+ "logits/rejected": -0.8447117805480957,
269
+ "logps/chosen": -270.3739318847656,
270
+ "logps/ref_chosen": -250.36923217773438,
271
+ "logps/ref_rejected": -402.3016662597656,
272
+ "logps/rejected": -448.3406982421875,
273
+ "loss": 2166.4175,
274
+ "rewards/accuracies": 0.6640625,
275
+ "rewards/chosen": -0.2000468224287033,
276
+ "rewards/margins": 0.2603432536125183,
277
+ "rewards/rejected": -0.4603900611400604,
278
+ "sft_loss": 0.9630093574523926,
279
+ "step": 15
280
+ },
281
+ {
282
+ "epoch": 0.2107863318237958,
283
+ "grad_norm": 20275.111328125,
284
+ "learning_rate": 4.826163240767716e-07,
285
+ "logits/chosen": -0.7847133874893188,
286
+ "logits/rejected": -0.8517911434173584,
287
+ "logps/chosen": -274.80609130859375,
288
+ "logps/ref_chosen": -253.88784790039062,
289
+ "logps/ref_rejected": -363.81549072265625,
290
+ "logps/rejected": -404.54119873046875,
291
+ "loss": 1400.3004,
292
+ "rewards/accuracies": 0.703125,
293
+ "rewards/chosen": -0.2091825008392334,
294
+ "rewards/margins": 0.198074609041214,
295
+ "rewards/rejected": -0.4072571396827698,
296
+ "sft_loss": 0.9957829713821411,
297
+ "step": 16
298
+ },
299
+ {
300
+ "epoch": 0.22396047756278303,
301
+ "grad_norm": 144756.109375,
302
+ "learning_rate": 4.780673881662242e-07,
303
+ "logits/chosen": -0.7692462801933289,
304
+ "logits/rejected": -0.750064492225647,
305
+ "logps/chosen": -312.2320861816406,
306
+ "logps/ref_chosen": -280.298095703125,
307
+ "logps/ref_rejected": -426.6932373046875,
308
+ "logps/rejected": -485.9967041015625,
309
+ "loss": 2140.3831,
310
+ "rewards/accuracies": 0.7421875,
311
+ "rewards/chosen": -0.3193399906158447,
312
+ "rewards/margins": 0.27369457483291626,
313
+ "rewards/rejected": -0.5930346250534058,
314
+ "sft_loss": 1.019205093383789,
315
+ "step": 17
316
+ },
317
+ {
318
+ "epoch": 0.23713462330177026,
319
+ "grad_norm": 147186.65625,
320
+ "learning_rate": 4.730171106393466e-07,
321
+ "logits/chosen": -0.8014205694198608,
322
+ "logits/rejected": -0.8366638422012329,
323
+ "logps/chosen": -272.2122497558594,
324
+ "logps/ref_chosen": -245.93484497070312,
325
+ "logps/ref_rejected": -355.2913818359375,
326
+ "logps/rejected": -402.57916259765625,
327
+ "loss": 1260.5695,
328
+ "rewards/accuracies": 0.6796875,
329
+ "rewards/chosen": -0.26277416944503784,
330
+ "rewards/margins": 0.21010375022888184,
331
+ "rewards/rejected": -0.4728779196739197,
332
+ "sft_loss": 1.0054181814193726,
333
+ "step": 18
334
+ },
335
+ {
336
+ "epoch": 0.2503087690407575,
337
+ "grad_norm": 9353.1171875,
338
+ "learning_rate": 4.6747659310219757e-07,
339
+ "logits/chosen": -0.7688182592391968,
340
+ "logits/rejected": -0.8143107891082764,
341
+ "logps/chosen": -313.2867126464844,
342
+ "logps/ref_chosen": -282.3853759765625,
343
+ "logps/ref_rejected": -423.46612548828125,
344
+ "logps/rejected": -485.9477844238281,
345
+ "loss": 2975.3206,
346
+ "rewards/accuracies": 0.703125,
347
+ "rewards/chosen": -0.3090134561061859,
348
+ "rewards/margins": 0.3158027231693268,
349
+ "rewards/rejected": -0.6248162388801575,
350
+ "sft_loss": 1.0559428930282593,
351
+ "step": 19
352
+ },
353
+ {
354
+ "epoch": 0.2634829147797447,
355
+ "grad_norm": 71948.1328125,
356
+ "learning_rate": 4.6145801481477433e-07,
357
+ "logits/chosen": -0.7672979831695557,
358
+ "logits/rejected": -0.8246533274650574,
359
+ "logps/chosen": -278.12701416015625,
360
+ "logps/ref_chosen": -250.12939453125,
361
+ "logps/ref_rejected": -400.04193115234375,
362
+ "logps/rejected": -459.34783935546875,
363
+ "loss": 1524.6759,
364
+ "rewards/accuracies": 0.75,
365
+ "rewards/chosen": -0.2799761891365051,
366
+ "rewards/margins": 0.31308287382125854,
367
+ "rewards/rejected": -0.5930590629577637,
368
+ "sft_loss": 0.995878279209137,
369
+ "step": 20
370
+ },
371
+ {
372
+ "epoch": 0.276657060518732,
373
+ "grad_norm": 19010.67578125,
374
+ "learning_rate": 4.549746059183561e-07,
375
+ "logits/chosen": -0.7679699063301086,
376
+ "logits/rejected": -0.7934538125991821,
377
+ "logps/chosen": -290.7159729003906,
378
+ "logps/ref_chosen": -260.5438232421875,
379
+ "logps/ref_rejected": -394.02606201171875,
380
+ "logps/rejected": -455.3935546875,
381
+ "loss": 2176.1531,
382
+ "rewards/accuracies": 0.765625,
383
+ "rewards/chosen": -0.3017215132713318,
384
+ "rewards/margins": 0.31195297837257385,
385
+ "rewards/rejected": -0.6136744618415833,
386
+ "sft_loss": 1.0407434701919556,
387
+ "step": 21
388
+ },
389
+ {
390
+ "epoch": 0.28983120625771924,
391
+ "grad_norm": 74092.6953125,
392
+ "learning_rate": 4.480406183527823e-07,
393
+ "logits/chosen": -0.8038030862808228,
394
+ "logits/rejected": -0.828942060470581,
395
+ "logps/chosen": -294.260009765625,
396
+ "logps/ref_chosen": -264.4549560546875,
397
+ "logps/ref_rejected": -426.1365661621094,
398
+ "logps/rejected": -491.14739990234375,
399
+ "loss": 2098.3057,
400
+ "rewards/accuracies": 0.7109375,
401
+ "rewards/chosen": -0.29805096983909607,
402
+ "rewards/margins": 0.3520573675632477,
403
+ "rewards/rejected": -0.6501083970069885,
404
+ "sft_loss": 1.0383522510528564,
405
+ "step": 22
406
+ },
407
+ {
408
+ "epoch": 0.3030053519967065,
409
+ "grad_norm": 23798.248046875,
410
+ "learning_rate": 4.4067129452759546e-07,
411
+ "logits/chosen": -0.8293471932411194,
412
+ "logits/rejected": -0.8665866851806641,
413
+ "logps/chosen": -276.66107177734375,
414
+ "logps/ref_chosen": -248.43484497070312,
415
+ "logps/ref_rejected": -354.51226806640625,
416
+ "logps/rejected": -406.6967468261719,
417
+ "loss": 1895.6882,
418
+ "rewards/accuracies": 0.75,
419
+ "rewards/chosen": -0.2822622060775757,
420
+ "rewards/margins": 0.2395820915699005,
421
+ "rewards/rejected": -0.5218443274497986,
422
+ "sft_loss": 1.0060269832611084,
423
+ "step": 23
424
+ },
425
+ {
426
+ "epoch": 0.3161794977356937,
427
+ "grad_norm": 85321.9296875,
428
+ "learning_rate": 4.3288283381591725e-07,
429
+ "logits/chosen": -0.8108458518981934,
430
+ "logits/rejected": -0.8491148352622986,
431
+ "logps/chosen": -268.555419921875,
432
+ "logps/ref_chosen": -241.54579162597656,
433
+ "logps/ref_rejected": -381.7640686035156,
434
+ "logps/rejected": -436.7099914550781,
435
+ "loss": 2128.0498,
436
+ "rewards/accuracies": 0.75,
437
+ "rewards/chosen": -0.27009618282318115,
438
+ "rewards/margins": 0.27936306595802307,
439
+ "rewards/rejected": -0.5494592189788818,
440
+ "sft_loss": 0.9779033660888672,
441
+ "step": 24
442
+ },
443
+ {
444
+ "epoch": 0.32935364347468093,
445
+ "grad_norm": 26374.453125,
446
+ "learning_rate": 4.246923569447104e-07,
447
+ "logits/chosen": -0.7603333592414856,
448
+ "logits/rejected": -0.7976529002189636,
449
+ "logps/chosen": -289.4198913574219,
450
+ "logps/ref_chosen": -263.8042297363281,
451
+ "logps/ref_rejected": -432.7107238769531,
452
+ "logps/rejected": -491.9762878417969,
453
+ "loss": 2442.6104,
454
+ "rewards/accuracies": 0.671875,
455
+ "rewards/chosen": -0.2561565637588501,
456
+ "rewards/margins": 0.3364991247653961,
457
+ "rewards/rejected": -0.5926557183265686,
458
+ "sft_loss": 1.008938193321228,
459
+ "step": 25
460
+ },
461
+ {
462
+ "epoch": 0.34252778921366817,
463
+ "grad_norm": 18185.58203125,
464
+ "learning_rate": 4.161178683597054e-07,
465
+ "logits/chosen": -0.7645914554595947,
466
+ "logits/rejected": -0.7908961176872253,
467
+ "logps/chosen": -283.41595458984375,
468
+ "logps/ref_chosen": -258.4693603515625,
469
+ "logps/ref_rejected": -396.6169128417969,
470
+ "logps/rejected": -451.3160400390625,
471
+ "loss": 1601.3,
472
+ "rewards/accuracies": 0.6875,
473
+ "rewards/chosen": -0.2494659125804901,
474
+ "rewards/margins": 0.29752564430236816,
475
+ "rewards/rejected": -0.5469915866851807,
476
+ "sft_loss": 1.0247998237609863,
477
+ "step": 26
478
+ },
479
+ {
480
+ "epoch": 0.3557019349526554,
481
+ "grad_norm": 70844.5859375,
482
+ "learning_rate": 4.0717821664772124e-07,
483
+ "logits/chosen": -0.8039371967315674,
484
+ "logits/rejected": -0.8496546149253845,
485
+ "logps/chosen": -265.72076416015625,
486
+ "logps/ref_chosen": -243.9918670654297,
487
+ "logps/ref_rejected": -415.019775390625,
488
+ "logps/rejected": -469.927490234375,
489
+ "loss": 1508.8497,
490
+ "rewards/accuracies": 0.78125,
491
+ "rewards/chosen": -0.21728886663913727,
492
+ "rewards/margins": 0.3317885100841522,
493
+ "rewards/rejected": -0.5490773320198059,
494
+ "sft_loss": 0.9742772579193115,
495
+ "step": 27
496
+ },
497
+ {
498
+ "epoch": 0.3688760806916426,
499
+ "grad_norm": 17698.689453125,
500
+ "learning_rate": 3.978930531033806e-07,
501
+ "logits/chosen": -0.8012359142303467,
502
+ "logits/rejected": -0.8333377242088318,
503
+ "logps/chosen": -286.1438903808594,
504
+ "logps/ref_chosen": -262.3642578125,
505
+ "logps/ref_rejected": -404.7378845214844,
506
+ "logps/rejected": -453.0112609863281,
507
+ "loss": 1529.8362,
508
+ "rewards/accuracies": 0.703125,
509
+ "rewards/chosen": -0.2377963364124298,
510
+ "rewards/margins": 0.24493779242038727,
511
+ "rewards/rejected": -0.48273414373397827,
512
+ "sft_loss": 1.0474350452423096,
513
+ "step": 28
514
+ },
515
+ {
516
+ "epoch": 0.3820502264306299,
517
+ "grad_norm": 31423.068359375,
518
+ "learning_rate": 3.882827885312998e-07,
519
+ "logits/chosen": -0.8194433450698853,
520
+ "logits/rejected": -0.8658930659294128,
521
+ "logps/chosen": -269.17816162109375,
522
+ "logps/ref_chosen": -248.24476623535156,
523
+ "logps/ref_rejected": -385.9969787597656,
524
+ "logps/rejected": -430.42547607421875,
525
+ "loss": 1514.3403,
526
+ "rewards/accuracies": 0.6953125,
527
+ "rewards/chosen": -0.20933374762535095,
528
+ "rewards/margins": 0.2349512279033661,
529
+ "rewards/rejected": -0.44428494572639465,
530
+ "sft_loss": 0.9792473316192627,
531
+ "step": 29
532
+ },
533
+ {
534
+ "epoch": 0.39522437216961714,
535
+ "grad_norm": 21664.841796875,
536
+ "learning_rate": 3.7836854837871044e-07,
537
+ "logits/chosen": -0.7560093998908997,
538
+ "logits/rejected": -0.8075149655342102,
539
+ "logps/chosen": -274.10748291015625,
540
+ "logps/ref_chosen": -252.64498901367188,
541
+ "logps/ref_rejected": -389.426025390625,
542
+ "logps/rejected": -431.0108642578125,
543
+ "loss": 1284.9393,
544
+ "rewards/accuracies": 0.7109375,
545
+ "rewards/chosen": -0.21462516486644745,
546
+ "rewards/margins": 0.20122365653514862,
547
+ "rewards/rejected": -0.4158487915992737,
548
+ "sft_loss": 0.9510519504547119,
549
+ "step": 30
550
+ },
551
+ {
552
+ "epoch": 0.4083985179086044,
553
+ "grad_norm": 34951.4765625,
554
+ "learning_rate": 3.681721262971413e-07,
555
+ "logits/chosen": -0.8185158371925354,
556
+ "logits/rejected": -0.8208706378936768,
557
+ "logps/chosen": -256.5106506347656,
558
+ "logps/ref_chosen": -238.3830108642578,
559
+ "logps/ref_rejected": -404.7466735839844,
560
+ "logps/rejected": -448.7279052734375,
561
+ "loss": 1711.1511,
562
+ "rewards/accuracies": 0.7265625,
563
+ "rewards/chosen": -0.18127650022506714,
564
+ "rewards/margins": 0.2585355341434479,
565
+ "rewards/rejected": -0.4398120641708374,
566
+ "sft_loss": 0.9598148465156555,
567
+ "step": 31
568
+ },
569
+ {
570
+ "epoch": 0.4215726636475916,
571
+ "grad_norm": 22634.892578125,
572
+ "learning_rate": 3.577159362352426e-07,
573
+ "logits/chosen": -0.8045048713684082,
574
+ "logits/rejected": -0.871455192565918,
575
+ "logps/chosen": -298.8917236328125,
576
+ "logps/ref_chosen": -275.08062744140625,
577
+ "logps/ref_rejected": -439.5594787597656,
578
+ "logps/rejected": -486.42987060546875,
579
+ "loss": 1073.0205,
580
+ "rewards/accuracies": 0.75,
581
+ "rewards/chosen": -0.23811063170433044,
582
+ "rewards/margins": 0.2305929809808731,
583
+ "rewards/rejected": -0.46870362758636475,
584
+ "sft_loss": 1.066259741783142,
585
+ "step": 32
586
+ },
587
+ {
588
+ "epoch": 0.43474680938657884,
589
+ "grad_norm": 17340.03515625,
590
+ "learning_rate": 3.470229631680624e-07,
591
+ "logits/chosen": -0.8264797329902649,
592
+ "logits/rejected": -0.8613673448562622,
593
+ "logps/chosen": -272.50433349609375,
594
+ "logps/ref_chosen": -253.18777465820312,
595
+ "logps/ref_rejected": -413.8665771484375,
596
+ "logps/rejected": -456.3052978515625,
597
+ "loss": 1156.1897,
598
+ "rewards/accuracies": 0.796875,
599
+ "rewards/chosen": -0.19316571950912476,
600
+ "rewards/margins": 0.23122143745422363,
601
+ "rewards/rejected": -0.4243871867656708,
602
+ "sft_loss": 0.9994233846664429,
603
+ "step": 33
604
+ },
605
+ {
606
+ "epoch": 0.44792095512556607,
607
+ "grad_norm": 18645.935546875,
608
+ "learning_rate": 3.361167125710832e-07,
609
+ "logits/chosen": -0.7793031334877014,
610
+ "logits/rejected": -0.8169309496879578,
611
+ "logps/chosen": -277.7130126953125,
612
+ "logps/ref_chosen": -257.9416809082031,
613
+ "logps/ref_rejected": -420.4779357910156,
614
+ "logps/rejected": -463.8733215332031,
615
+ "loss": 1071.5037,
616
+ "rewards/accuracies": 0.7109375,
617
+ "rewards/chosen": -0.197713240981102,
618
+ "rewards/margins": 0.23624077439308167,
619
+ "rewards/rejected": -0.43395400047302246,
620
+ "sft_loss": 1.0031678676605225,
621
+ "step": 34
622
+ },
623
+ {
624
+ "epoch": 0.4610951008645533,
625
+ "grad_norm": 19952.755859375,
626
+ "learning_rate": 3.2502115875008516e-07,
627
+ "logits/chosen": -0.8148825764656067,
628
+ "logits/rejected": -0.8491742610931396,
629
+ "logps/chosen": -299.02423095703125,
630
+ "logps/ref_chosen": -274.88323974609375,
631
+ "logps/ref_rejected": -371.6654968261719,
632
+ "logps/rejected": -408.4618835449219,
633
+ "loss": 1289.3344,
634
+ "rewards/accuracies": 0.6640625,
635
+ "rewards/chosen": -0.24141037464141846,
636
+ "rewards/margins": 0.12655334174633026,
637
+ "rewards/rejected": -0.3679637014865875,
638
+ "sft_loss": 1.0052714347839355,
639
+ "step": 35
640
+ },
641
+ {
642
+ "epoch": 0.47426924660354053,
643
+ "grad_norm": 27593.88671875,
644
+ "learning_rate": 3.137606921404191e-07,
645
+ "logits/chosen": -0.7783984541893005,
646
+ "logits/rejected": -0.8010607957839966,
647
+ "logps/chosen": -279.0986022949219,
648
+ "logps/ref_chosen": -259.29522705078125,
649
+ "logps/ref_rejected": -394.7854919433594,
650
+ "logps/rejected": -431.82940673828125,
651
+ "loss": 1168.3469,
652
+ "rewards/accuracies": 0.765625,
653
+ "rewards/chosen": -0.19803372025489807,
654
+ "rewards/margins": 0.17240510880947113,
655
+ "rewards/rejected": -0.3704387843608856,
656
+ "sft_loss": 0.929314136505127,
657
+ "step": 36
658
+ },
659
+ {
660
+ "epoch": 0.4874433923425278,
661
+ "grad_norm": 24689.4375,
662
+ "learning_rate": 3.0236006569153616e-07,
663
+ "logits/chosen": -0.7673581838607788,
664
+ "logits/rejected": -0.7947245836257935,
665
+ "logps/chosen": -277.85296630859375,
666
+ "logps/ref_chosen": -257.4971923828125,
667
+ "logps/ref_rejected": -428.3898620605469,
668
+ "logps/rejected": -473.2132873535156,
669
+ "loss": 1577.0131,
670
+ "rewards/accuracies": 0.6953125,
671
+ "rewards/chosen": -0.20355747640132904,
672
+ "rewards/margins": 0.24467676877975464,
673
+ "rewards/rejected": -0.4482342600822449,
674
+ "sft_loss": 0.982255220413208,
675
+ "step": 37
676
+ },
677
+ {
678
+ "epoch": 0.500617538081515,
679
+ "grad_norm": 22088.283203125,
680
+ "learning_rate": 2.9084434045463254e-07,
681
+ "logits/chosen": -0.7526673674583435,
682
+ "logits/rejected": -0.8011683821678162,
683
+ "logps/chosen": -264.4170837402344,
684
+ "logps/ref_chosen": -247.0706024169922,
685
+ "logps/ref_rejected": -412.8132019042969,
686
+ "logps/rejected": -449.17218017578125,
687
+ "loss": 959.661,
688
+ "rewards/accuracies": 0.75,
689
+ "rewards/chosen": -0.173464834690094,
690
+ "rewards/margins": 0.19012488424777985,
691
+ "rewards/rejected": -0.36358973383903503,
692
+ "sft_loss": 0.8840616345405579,
693
+ "step": 38
694
+ },
695
+ {
696
+ "epoch": 0.5137916838205022,
697
+ "grad_norm": 23851.294921875,
698
+ "learning_rate": 2.7923883049302066e-07,
699
+ "logits/chosen": -0.7483999729156494,
700
+ "logits/rejected": -0.7759736776351929,
701
+ "logps/chosen": -267.4944763183594,
702
+ "logps/ref_chosen": -248.76388549804688,
703
+ "logps/ref_rejected": -392.1750183105469,
704
+ "logps/rejected": -427.758056640625,
705
+ "loss": 1144.1176,
706
+ "rewards/accuracies": 0.7109375,
707
+ "rewards/chosen": -0.1873060017824173,
708
+ "rewards/margins": 0.16852441430091858,
709
+ "rewards/rejected": -0.35583043098449707,
710
+ "sft_loss": 1.0190958976745605,
711
+ "step": 39
712
+ },
713
+ {
714
+ "epoch": 0.5269658295594895,
715
+ "grad_norm": 52302.57421875,
716
+ "learning_rate": 2.6756904723632324e-07,
717
+ "logits/chosen": -0.8017964959144592,
718
+ "logits/rejected": -0.8624761700630188,
719
+ "logps/chosen": -280.15875244140625,
720
+ "logps/ref_chosen": -259.4993896484375,
721
+ "logps/ref_rejected": -399.8374938964844,
722
+ "logps/rejected": -438.02447509765625,
723
+ "loss": 1198.8533,
724
+ "rewards/accuracies": 0.65625,
725
+ "rewards/chosen": -0.20659363269805908,
726
+ "rewards/margins": 0.17527592182159424,
727
+ "rewards/rejected": -0.3818695843219757,
728
+ "sft_loss": 0.9950222373008728,
729
+ "step": 40
730
+ },
731
+ {
732
+ "epoch": 0.5401399752984768,
733
+ "grad_norm": 32214.91796875,
734
+ "learning_rate": 2.5586064340081516e-07,
735
+ "logits/chosen": -0.775903046131134,
736
+ "logits/rejected": -0.8436408042907715,
737
+ "logps/chosen": -277.5977783203125,
738
+ "logps/ref_chosen": -257.62872314453125,
739
+ "logps/ref_rejected": -416.6236267089844,
740
+ "logps/rejected": -455.8535461425781,
741
+ "loss": 932.2411,
742
+ "rewards/accuracies": 0.765625,
743
+ "rewards/chosen": -0.19969075918197632,
744
+ "rewards/margins": 0.19260822236537933,
745
+ "rewards/rejected": -0.39229899644851685,
746
+ "sft_loss": 0.9193465709686279,
747
+ "step": 41
748
+ },
749
+ {
750
+ "epoch": 0.553314121037464,
751
+ "grad_norm": 18867.783203125,
752
+ "learning_rate": 2.4413935659918487e-07,
753
+ "logits/chosen": -0.7325506210327148,
754
+ "logits/rejected": -0.7629200220108032,
755
+ "logps/chosen": -278.38702392578125,
756
+ "logps/ref_chosen": -258.0796813964844,
757
+ "logps/ref_rejected": -403.37554931640625,
758
+ "logps/rejected": -441.0909729003906,
759
+ "loss": 1111.9651,
760
+ "rewards/accuracies": 0.71875,
761
+ "rewards/chosen": -0.20307336747646332,
762
+ "rewards/margins": 0.17408138513565063,
763
+ "rewards/rejected": -0.37715476751327515,
764
+ "sft_loss": 0.9346740245819092,
765
+ "step": 42
766
+ },
767
+ {
768
+ "epoch": 0.5664882667764513,
769
+ "grad_norm": 34268.01953125,
770
+ "learning_rate": 2.3243095276367684e-07,
771
+ "logits/chosen": -0.8410815000534058,
772
+ "logits/rejected": -0.8493119478225708,
773
+ "logps/chosen": -283.8769226074219,
774
+ "logps/ref_chosen": -263.16790771484375,
775
+ "logps/ref_rejected": -372.30419921875,
776
+ "logps/rejected": -405.7116394042969,
777
+ "loss": 1075.1367,
778
+ "rewards/accuracies": 0.671875,
779
+ "rewards/chosen": -0.20709021389484406,
780
+ "rewards/margins": 0.1269841194152832,
781
+ "rewards/rejected": -0.3340742886066437,
782
+ "sft_loss": 1.0096700191497803,
783
+ "step": 43
784
+ },
785
+ {
786
+ "epoch": 0.5796624125154385,
787
+ "grad_norm": 23751.416015625,
788
+ "learning_rate": 2.2076116950697937e-07,
789
+ "logits/chosen": -0.7676877379417419,
790
+ "logits/rejected": -0.7860767841339111,
791
+ "logps/chosen": -282.58770751953125,
792
+ "logps/ref_chosen": -260.87664794921875,
793
+ "logps/ref_rejected": -419.5744934082031,
794
+ "logps/rejected": -458.99755859375,
795
+ "loss": 1179.9371,
796
+ "rewards/accuracies": 0.71875,
797
+ "rewards/chosen": -0.2171107530593872,
798
+ "rewards/margins": 0.17712023854255676,
799
+ "rewards/rejected": -0.39423099160194397,
800
+ "sft_loss": 0.9293317794799805,
801
+ "step": 44
802
+ },
803
+ {
804
+ "epoch": 0.5928365582544257,
805
+ "grad_norm": 20057.634765625,
806
+ "learning_rate": 2.091556595453674e-07,
807
+ "logits/chosen": -0.810949981212616,
808
+ "logits/rejected": -0.807197630405426,
809
+ "logps/chosen": -303.0293884277344,
810
+ "logps/ref_chosen": -280.1766052246094,
811
+ "logps/ref_rejected": -414.77728271484375,
812
+ "logps/rejected": -454.41998291015625,
813
+ "loss": 1392.2808,
814
+ "rewards/accuracies": 0.65625,
815
+ "rewards/chosen": -0.22852776944637299,
816
+ "rewards/margins": 0.16789919137954712,
817
+ "rewards/rejected": -0.3964269459247589,
818
+ "sft_loss": 1.008779764175415,
819
+ "step": 45
820
+ },
821
+ {
822
+ "epoch": 0.606010703993413,
823
+ "grad_norm": 93258.9765625,
824
+ "learning_rate": 1.9763993430846392e-07,
825
+ "logits/chosen": -0.7731283903121948,
826
+ "logits/rejected": -0.8497406244277954,
827
+ "logps/chosen": -274.9454345703125,
828
+ "logps/ref_chosen": -256.38720703125,
829
+ "logps/ref_rejected": -440.72515869140625,
830
+ "logps/rejected": -478.4444580078125,
831
+ "loss": 1066.626,
832
+ "rewards/accuracies": 0.75,
833
+ "rewards/chosen": -0.18558244407176971,
834
+ "rewards/margins": 0.19161023199558258,
835
+ "rewards/rejected": -0.3771926760673523,
836
+ "sft_loss": 1.0101566314697266,
837
+ "step": 46
838
+ },
839
+ {
840
+ "epoch": 0.6191848497324002,
841
+ "grad_norm": 25284.322265625,
842
+ "learning_rate": 1.862393078595809e-07,
843
+ "logits/chosen": -0.8175167441368103,
844
+ "logits/rejected": -0.8652117252349854,
845
+ "logps/chosen": -296.01422119140625,
846
+ "logps/ref_chosen": -273.3941650390625,
847
+ "logps/ref_rejected": -390.37255859375,
848
+ "logps/rejected": -426.4823913574219,
849
+ "loss": 1059.3556,
850
+ "rewards/accuracies": 0.71875,
851
+ "rewards/chosen": -0.22620078921318054,
852
+ "rewards/margins": 0.13489758968353271,
853
+ "rewards/rejected": -0.36109837889671326,
854
+ "sft_loss": 0.9877309203147888,
855
+ "step": 47
856
+ },
857
+ {
858
+ "epoch": 0.6323589954713874,
859
+ "grad_norm": 22755.78515625,
860
+ "learning_rate": 1.7497884124991485e-07,
861
+ "logits/chosen": -0.8109832406044006,
862
+ "logits/rejected": -0.8523979783058167,
863
+ "logps/chosen": -274.8309020996094,
864
+ "logps/ref_chosen": -256.0462951660156,
865
+ "logps/ref_rejected": -433.33880615234375,
866
+ "logps/rejected": -471.33514404296875,
867
+ "loss": 1024.0135,
868
+ "rewards/accuracies": 0.7578125,
869
+ "rewards/chosen": -0.18784590065479279,
870
+ "rewards/margins": 0.19211755692958832,
871
+ "rewards/rejected": -0.3799634277820587,
872
+ "sft_loss": 0.9346714019775391,
873
+ "step": 48
874
+ },
875
+ {
876
+ "epoch": 0.6455331412103746,
877
+ "grad_norm": 48471.87890625,
878
+ "learning_rate": 1.6388328742891678e-07,
879
+ "logits/chosen": -0.7700808048248291,
880
+ "logits/rejected": -0.8283007144927979,
881
+ "logps/chosen": -276.7380065917969,
882
+ "logps/ref_chosen": -258.337158203125,
883
+ "logps/ref_rejected": -402.8912658691406,
884
+ "logps/rejected": -438.73443603515625,
885
+ "loss": 1057.601,
886
+ "rewards/accuracies": 0.75,
887
+ "rewards/chosen": -0.1840084046125412,
888
+ "rewards/margins": 0.17442339658737183,
889
+ "rewards/rejected": -0.3584318161010742,
890
+ "sft_loss": 1.0198752880096436,
891
+ "step": 49
892
+ },
893
+ {
894
+ "epoch": 0.6587072869493619,
895
+ "grad_norm": 20364.625,
896
+ "learning_rate": 1.5297703683193753e-07,
897
+ "logits/chosen": -0.8074498176574707,
898
+ "logits/rejected": -0.8775460720062256,
899
+ "logps/chosen": -264.13189697265625,
900
+ "logps/ref_chosen": -246.30377197265625,
901
+ "logps/ref_rejected": -357.4236145019531,
902
+ "logps/rejected": -387.9647216796875,
903
+ "loss": 918.1786,
904
+ "rewards/accuracies": 0.734375,
905
+ "rewards/chosen": -0.17828112840652466,
906
+ "rewards/margins": 0.12712979316711426,
907
+ "rewards/rejected": -0.30541089177131653,
908
+ "sft_loss": 0.9230359196662903,
909
+ "step": 50
910
+ },
911
+ {
912
+ "epoch": 0.6718814326883491,
913
+ "grad_norm": 29058.451171875,
914
+ "learning_rate": 1.422840637647574e-07,
915
+ "logits/chosen": -0.7510178685188293,
916
+ "logits/rejected": -0.771770715713501,
917
+ "logps/chosen": -258.41845703125,
918
+ "logps/ref_chosen": -242.3370361328125,
919
+ "logps/ref_rejected": -373.0410461425781,
920
+ "logps/rejected": -403.00408935546875,
921
+ "loss": 951.6824,
922
+ "rewards/accuracies": 0.7109375,
923
+ "rewards/chosen": -0.16081435978412628,
924
+ "rewards/margins": 0.13881637156009674,
925
+ "rewards/rejected": -0.299630731344223,
926
+ "sft_loss": 0.9331162571907043,
927
+ "step": 51
928
+ },
929
+ {
930
+ "epoch": 0.6850555784273363,
931
+ "grad_norm": 23650.7265625,
932
+ "learning_rate": 1.3182787370285865e-07,
933
+ "logits/chosen": -0.7598443031311035,
934
+ "logits/rejected": -0.7725738286972046,
935
+ "logps/chosen": -281.2547607421875,
936
+ "logps/ref_chosen": -261.9949645996094,
937
+ "logps/ref_rejected": -411.95611572265625,
938
+ "logps/rejected": -449.1616516113281,
939
+ "loss": 980.0952,
940
+ "rewards/accuracies": 0.75,
941
+ "rewards/chosen": -0.19259795546531677,
942
+ "rewards/margins": 0.179457426071167,
943
+ "rewards/rejected": -0.3720553517341614,
944
+ "sft_loss": 0.9306559562683105,
945
+ "step": 52
946
+ },
947
+ {
948
+ "epoch": 0.6982297241663236,
949
+ "grad_norm": 49730.3984375,
950
+ "learning_rate": 1.2163145162128946e-07,
951
+ "logits/chosen": -0.8213989734649658,
952
+ "logits/rejected": -0.8896348476409912,
953
+ "logps/chosen": -287.832763671875,
954
+ "logps/ref_chosen": -268.6963806152344,
955
+ "logps/ref_rejected": -425.7789001464844,
956
+ "logps/rejected": -463.97308349609375,
957
+ "loss": 1025.2494,
958
+ "rewards/accuracies": 0.765625,
959
+ "rewards/chosen": -0.1913636326789856,
960
+ "rewards/margins": 0.19057826697826385,
961
+ "rewards/rejected": -0.38194188475608826,
962
+ "sft_loss": 0.9831621646881104,
963
+ "step": 53
964
+ },
965
+ {
966
+ "epoch": 0.7114038699053108,
967
+ "grad_norm": 39849.76171875,
968
+ "learning_rate": 1.1171721146870014e-07,
969
+ "logits/chosen": -0.7456237077713013,
970
+ "logits/rejected": -0.8003172278404236,
971
+ "logps/chosen": -271.5772399902344,
972
+ "logps/ref_chosen": -251.62240600585938,
973
+ "logps/ref_rejected": -423.13226318359375,
974
+ "logps/rejected": -464.643310546875,
975
+ "loss": 1263.4849,
976
+ "rewards/accuracies": 0.703125,
977
+ "rewards/chosen": -0.19954846799373627,
978
+ "rewards/margins": 0.21556226909160614,
979
+ "rewards/rejected": -0.4151107370853424,
980
+ "sft_loss": 0.9654486179351807,
981
+ "step": 54
982
+ },
983
+ {
984
+ "epoch": 0.724578015644298,
985
+ "grad_norm": 16490.654296875,
986
+ "learning_rate": 1.0210694689661939e-07,
987
+ "logits/chosen": -0.8203299045562744,
988
+ "logits/rejected": -0.8787042498588562,
989
+ "logps/chosen": -270.5526428222656,
990
+ "logps/ref_chosen": -251.76651000976562,
991
+ "logps/ref_rejected": -390.6857604980469,
992
+ "logps/rejected": -425.12744140625,
993
+ "loss": 909.9653,
994
+ "rewards/accuracies": 0.71875,
995
+ "rewards/chosen": -0.18786153197288513,
996
+ "rewards/margins": 0.1565551608800888,
997
+ "rewards/rejected": -0.34441667795181274,
998
+ "sft_loss": 0.9638007879257202,
999
+ "step": 55
1000
+ },
1001
+ {
1002
+ "epoch": 0.7377521613832853,
1003
+ "grad_norm": 21740.568359375,
1004
+ "learning_rate": 9.282178335227883e-08,
1005
+ "logits/chosen": -0.7758232951164246,
1006
+ "logits/rejected": -0.8312428593635559,
1007
+ "logps/chosen": -293.42498779296875,
1008
+ "logps/ref_chosen": -272.2457580566406,
1009
+ "logps/ref_rejected": -409.26513671875,
1010
+ "logps/rejected": -448.3246154785156,
1011
+ "loss": 1011.9142,
1012
+ "rewards/accuracies": 0.7421875,
1013
+ "rewards/chosen": -0.21179243922233582,
1014
+ "rewards/margins": 0.1788019835948944,
1015
+ "rewards/rejected": -0.3905944228172302,
1016
+ "sft_loss": 0.9946072697639465,
1017
+ "step": 56
1018
+ },
1019
+ {
1020
+ "epoch": 0.7509263071222725,
1021
+ "grad_norm": 17951.88671875,
1022
+ "learning_rate": 8.388213164029459e-08,
1023
+ "logits/chosen": -0.7660011053085327,
1024
+ "logits/rejected": -0.8385521173477173,
1025
+ "logps/chosen": -278.1667175292969,
1026
+ "logps/ref_chosen": -258.1634521484375,
1027
+ "logps/ref_rejected": -446.6335754394531,
1028
+ "logps/rejected": -487.20623779296875,
1029
+ "loss": 921.0497,
1030
+ "rewards/accuracies": 0.78125,
1031
+ "rewards/chosen": -0.20003226399421692,
1032
+ "rewards/margins": 0.2056940495967865,
1033
+ "rewards/rejected": -0.4057263135910034,
1034
+ "sft_loss": 0.9664478898048401,
1035
+ "step": 57
1036
+ },
1037
+ {
1038
+ "epoch": 0.7641004528612598,
1039
+ "grad_norm": 34123.95703125,
1040
+ "learning_rate": 7.530764305528958e-08,
1041
+ "logits/chosen": -0.768264651298523,
1042
+ "logits/rejected": -0.8065668344497681,
1043
+ "logps/chosen": -280.6827392578125,
1044
+ "logps/ref_chosen": -261.5390625,
1045
+ "logps/ref_rejected": -408.1822509765625,
1046
+ "logps/rejected": -444.2044677734375,
1047
+ "loss": 973.7516,
1048
+ "rewards/accuracies": 0.7890625,
1049
+ "rewards/chosen": -0.19143663346767426,
1050
+ "rewards/margins": 0.16878540813922882,
1051
+ "rewards/rejected": -0.3602220416069031,
1052
+ "sft_loss": 1.0135674476623535,
1053
+ "step": 58
1054
+ },
1055
+ {
1056
+ "epoch": 0.7772745986002471,
1057
+ "grad_norm": 25089.880859375,
1058
+ "learning_rate": 6.711716618408281e-08,
1059
+ "logits/chosen": -0.7621768712997437,
1060
+ "logits/rejected": -0.8304345607757568,
1061
+ "logps/chosen": -285.82183837890625,
1062
+ "logps/ref_chosen": -266.89788818359375,
1063
+ "logps/ref_rejected": -408.42626953125,
1064
+ "logps/rejected": -443.7984313964844,
1065
+ "loss": 913.3936,
1066
+ "rewards/accuracies": 0.7890625,
1067
+ "rewards/chosen": -0.18923944234848022,
1068
+ "rewards/margins": 0.16448232531547546,
1069
+ "rewards/rejected": -0.3537217378616333,
1070
+ "sft_loss": 1.0188053846359253,
1071
+ "step": 59
1072
+ },
1073
+ {
1074
+ "epoch": 0.7904487443392343,
1075
+ "grad_norm": 24835.27734375,
1076
+ "learning_rate": 5.932870547240454e-08,
1077
+ "logits/chosen": -0.7458328008651733,
1078
+ "logits/rejected": -0.8268925547599792,
1079
+ "logps/chosen": -265.254638671875,
1080
+ "logps/ref_chosen": -247.4517822265625,
1081
+ "logps/ref_rejected": -384.67694091796875,
1082
+ "logps/rejected": -417.5419006347656,
1083
+ "loss": 1069.0216,
1084
+ "rewards/accuracies": 0.7265625,
1085
+ "rewards/chosen": -0.1780286729335785,
1086
+ "rewards/margins": 0.15062083303928375,
1087
+ "rewards/rejected": -0.32864949107170105,
1088
+ "sft_loss": 0.9329981803894043,
1089
+ "step": 60
1090
+ },
1091
+ {
1092
+ "epoch": 0.8036228900782215,
1093
+ "grad_norm": 39707.6328125,
1094
+ "learning_rate": 5.1959381647217665e-08,
1095
+ "logits/chosen": -0.7766802906990051,
1096
+ "logits/rejected": -0.8296952247619629,
1097
+ "logps/chosen": -284.8126525878906,
1098
+ "logps/ref_chosen": -264.2602233886719,
1099
+ "logps/ref_rejected": -395.50848388671875,
1100
+ "logps/rejected": -432.6766357421875,
1101
+ "loss": 982.9723,
1102
+ "rewards/accuracies": 0.7578125,
1103
+ "rewards/chosen": -0.20552387833595276,
1104
+ "rewards/margins": 0.1661575585603714,
1105
+ "rewards/rejected": -0.37168145179748535,
1106
+ "sft_loss": 0.9369614720344543,
1107
+ "step": 61
1108
+ },
1109
+ {
1110
+ "epoch": 0.8167970358172087,
1111
+ "grad_norm": 19872.701171875,
1112
+ "learning_rate": 4.502539408164385e-08,
1113
+ "logits/chosen": -0.8309569358825684,
1114
+ "logits/rejected": -0.8575015068054199,
1115
+ "logps/chosen": -276.09942626953125,
1116
+ "logps/ref_chosen": -255.97093200683594,
1117
+ "logps/ref_rejected": -447.40618896484375,
1118
+ "logps/rejected": -489.0849609375,
1119
+ "loss": 1000.5587,
1120
+ "rewards/accuracies": 0.78125,
1121
+ "rewards/chosen": -0.20128466188907623,
1122
+ "rewards/margins": 0.2155027985572815,
1123
+ "rewards/rejected": -0.4167875051498413,
1124
+ "sft_loss": 1.0023167133331299,
1125
+ "step": 62
1126
+ },
1127
+ {
1128
+ "epoch": 0.829971181556196,
1129
+ "grad_norm": 16652.455078125,
1130
+ "learning_rate": 3.854198518522564e-08,
1131
+ "logits/chosen": -0.7885565757751465,
1132
+ "logits/rejected": -0.8515602350234985,
1133
+ "logps/chosen": -285.7626953125,
1134
+ "logps/ref_chosen": -264.84906005859375,
1135
+ "logps/ref_rejected": -413.2689514160156,
1136
+ "logps/rejected": -451.171875,
1137
+ "loss": 1036.8346,
1138
+ "rewards/accuracies": 0.7109375,
1139
+ "rewards/chosen": -0.20913614332675934,
1140
+ "rewards/margins": 0.16989250481128693,
1141
+ "rewards/rejected": -0.3790286183357239,
1142
+ "sft_loss": 0.9977405071258545,
1143
+ "step": 63
1144
+ },
1145
+ {
1146
+ "epoch": 0.8431453272951832,
1147
+ "grad_norm": 95463.9609375,
1148
+ "learning_rate": 3.2523406897802444e-08,
1149
+ "logits/chosen": -0.7598262429237366,
1150
+ "logits/rejected": -0.8194103240966797,
1151
+ "logps/chosen": -297.930908203125,
1152
+ "logps/ref_chosen": -274.2559814453125,
1153
+ "logps/ref_rejected": -412.460693359375,
1154
+ "logps/rejected": -450.8624267578125,
1155
+ "loss": 1036.7638,
1156
+ "rewards/accuracies": 0.6953125,
1157
+ "rewards/chosen": -0.23674927651882172,
1158
+ "rewards/margins": 0.14726848900318146,
1159
+ "rewards/rejected": -0.3840177655220032,
1160
+ "sft_loss": 0.9848403930664062,
1161
+ "step": 64
1162
+ },
1163
+ {
1164
+ "epoch": 0.8563194730341704,
1165
+ "grad_norm": 26849.763671875,
1166
+ "learning_rate": 2.6982889360653376e-08,
1167
+ "logits/chosen": -0.7949633002281189,
1168
+ "logits/rejected": -0.854800820350647,
1169
+ "logps/chosen": -282.3885803222656,
1170
+ "logps/ref_chosen": -259.443115234375,
1171
+ "logps/ref_rejected": -437.60064697265625,
1172
+ "logps/rejected": -481.81732177734375,
1173
+ "loss": 1209.8678,
1174
+ "rewards/accuracies": 0.7421875,
1175
+ "rewards/chosen": -0.22945457696914673,
1176
+ "rewards/margins": 0.21271246671676636,
1177
+ "rewards/rejected": -0.4421670436859131,
1178
+ "sft_loss": 0.9634147882461548,
1179
+ "step": 65
1180
+ },
1181
+ {
1182
+ "epoch": 0.8694936187731577,
1183
+ "grad_norm": 24465.966796875,
1184
+ "learning_rate": 2.1932611833775843e-08,
1185
+ "logits/chosen": -0.8066317439079285,
1186
+ "logits/rejected": -0.8882776498794556,
1187
+ "logps/chosen": -263.16009521484375,
1188
+ "logps/ref_chosen": -244.51507568359375,
1189
+ "logps/ref_rejected": -397.60516357421875,
1190
+ "logps/rejected": -433.0977478027344,
1191
+ "loss": 996.5597,
1192
+ "rewards/accuracies": 0.78125,
1193
+ "rewards/chosen": -0.18644998967647552,
1194
+ "rewards/margins": 0.168475940823555,
1195
+ "rewards/rejected": -0.3549259305000305,
1196
+ "sft_loss": 0.9470033049583435,
1197
+ "step": 66
1198
+ },
1199
+ {
1200
+ "epoch": 0.8826677645121449,
1201
+ "grad_norm": 23544.0078125,
1202
+ "learning_rate": 1.738367592322837e-08,
1203
+ "logits/chosen": -0.8149206042289734,
1204
+ "logits/rejected": -0.8741443753242493,
1205
+ "logps/chosen": -278.1585388183594,
1206
+ "logps/ref_chosen": -258.00384521484375,
1207
+ "logps/ref_rejected": -426.8297119140625,
1208
+ "logps/rejected": -466.4974365234375,
1209
+ "loss": 974.3707,
1210
+ "rewards/accuracies": 0.7421875,
1211
+ "rewards/chosen": -0.20154669880867004,
1212
+ "rewards/margins": 0.1951308250427246,
1213
+ "rewards/rejected": -0.39667749404907227,
1214
+ "sft_loss": 0.9784504175186157,
1215
+ "step": 67
1216
+ },
1217
+ {
1218
+ "epoch": 0.8958419102511321,
1219
+ "grad_norm": 37581.44140625,
1220
+ "learning_rate": 1.3346081177391472e-08,
1221
+ "logits/chosen": -0.8311805129051208,
1222
+ "logits/rejected": -0.8835955858230591,
1223
+ "logps/chosen": -267.4219665527344,
1224
+ "logps/ref_chosen": -248.99069213867188,
1225
+ "logps/ref_rejected": -397.907470703125,
1226
+ "logps/rejected": -434.26910400390625,
1227
+ "loss": 938.5573,
1228
+ "rewards/accuracies": 0.765625,
1229
+ "rewards/chosen": -0.1843128651380539,
1230
+ "rewards/margins": 0.1793033629655838,
1231
+ "rewards/rejected": -0.3636162281036377,
1232
+ "sft_loss": 0.9809505343437195,
1233
+ "step": 68
1234
+ },
1235
+ {
1236
+ "epoch": 0.9090160559901194,
1237
+ "grad_norm": 17509.748046875,
1238
+ "learning_rate": 9.828703105789981e-09,
1239
+ "logits/chosen": -0.8134777545928955,
1240
+ "logits/rejected": -0.8525556325912476,
1241
+ "logps/chosen": -267.26904296875,
1242
+ "logps/ref_chosen": -247.39364624023438,
1243
+ "logps/ref_rejected": -421.5614013671875,
1244
+ "logps/rejected": -461.3177185058594,
1245
+ "loss": 997.8082,
1246
+ "rewards/accuracies": 0.734375,
1247
+ "rewards/chosen": -0.19875425100326538,
1248
+ "rewards/margins": 0.198808491230011,
1249
+ "rewards/rejected": -0.39756274223327637,
1250
+ "sft_loss": 0.9484153985977173,
1251
+ "step": 69
1252
+ },
1253
+ {
1254
+ "epoch": 0.9221902017291066,
1255
+ "grad_norm": 29303.15625,
1256
+ "learning_rate": 6.839273668796747e-09,
1257
+ "logits/chosen": -0.7265700697898865,
1258
+ "logits/rejected": -0.752987265586853,
1259
+ "logps/chosen": -293.7417297363281,
1260
+ "logps/ref_chosen": -269.7939758300781,
1261
+ "logps/ref_rejected": -410.67901611328125,
1262
+ "logps/rejected": -452.1363525390625,
1263
+ "loss": 1046.5741,
1264
+ "rewards/accuracies": 0.7265625,
1265
+ "rewards/chosen": -0.23947753012180328,
1266
+ "rewards/margins": 0.1750955581665039,
1267
+ "rewards/rejected": -0.414573073387146,
1268
+ "sft_loss": 0.9382635354995728,
1269
+ "step": 70
1270
+ },
1271
+ {
1272
+ "epoch": 0.9353643474680938,
1273
+ "grad_norm": 130671.40625,
1274
+ "learning_rate": 4.384364281105973e-09,
1275
+ "logits/chosen": -0.7530699968338013,
1276
+ "logits/rejected": -0.823380708694458,
1277
+ "logps/chosen": -284.096923828125,
1278
+ "logps/ref_chosen": -263.344970703125,
1279
+ "logps/ref_rejected": -426.18939208984375,
1280
+ "logps/rejected": -464.8126525878906,
1281
+ "loss": 1125.8024,
1282
+ "rewards/accuracies": 0.734375,
1283
+ "rewards/chosen": -0.20751963555812836,
1284
+ "rewards/margins": 0.1787126660346985,
1285
+ "rewards/rejected": -0.38623228669166565,
1286
+ "sft_loss": 0.9687177538871765,
1287
+ "step": 71
1288
+ },
1289
+ {
1290
+ "epoch": 0.9485384932070811,
1291
+ "grad_norm": 18457.01171875,
1292
+ "learning_rate": 2.469371366337264e-09,
1293
+ "logits/chosen": -0.7673330903053284,
1294
+ "logits/rejected": -0.8481195569038391,
1295
+ "logps/chosen": -281.8998107910156,
1296
+ "logps/ref_chosen": -260.8071594238281,
1297
+ "logps/ref_rejected": -384.2206115722656,
1298
+ "logps/rejected": -420.32147216796875,
1299
+ "loss": 963.4489,
1300
+ "rewards/accuracies": 0.71875,
1301
+ "rewards/chosen": -0.21092607080936432,
1302
+ "rewards/margins": 0.15008221566677094,
1303
+ "rewards/rejected": -0.36100828647613525,
1304
+ "sft_loss": 0.9569988250732422,
1305
+ "step": 72
1306
+ },
1307
+ {
1308
+ "epoch": 0.9617126389460683,
1309
+ "grad_norm": 21579.51171875,
1310
+ "learning_rate": 1.0985044945254762e-09,
1311
+ "logits/chosen": -0.7896211743354797,
1312
+ "logits/rejected": -0.8543872833251953,
1313
+ "logps/chosen": -287.5456848144531,
1314
+ "logps/ref_chosen": -265.0205383300781,
1315
+ "logps/ref_rejected": -415.27532958984375,
1316
+ "logps/rejected": -454.45166015625,
1317
+ "loss": 1135.3003,
1318
+ "rewards/accuracies": 0.6875,
1319
+ "rewards/chosen": -0.22525182366371155,
1320
+ "rewards/margins": 0.16651120781898499,
1321
+ "rewards/rejected": -0.39176300168037415,
1322
+ "sft_loss": 1.0159409046173096,
1323
+ "step": 73
1324
+ },
1325
+ {
1326
+ "epoch": 0.9748867846850556,
1327
+ "grad_norm": 34807.4765625,
1328
+ "learning_rate": 2.7477712857215675e-10,
1329
+ "logits/chosen": -0.7803131341934204,
1330
+ "logits/rejected": -0.8543556928634644,
1331
+ "logps/chosen": -276.9373779296875,
1332
+ "logps/ref_chosen": -256.0310363769531,
1333
+ "logps/ref_rejected": -395.774169921875,
1334
+ "logps/rejected": -431.9486389160156,
1335
+ "loss": 1060.5397,
1336
+ "rewards/accuracies": 0.7109375,
1337
+ "rewards/chosen": -0.20906318724155426,
1338
+ "rewards/margins": 0.15268170833587646,
1339
+ "rewards/rejected": -0.36174488067626953,
1340
+ "sft_loss": 1.023523211479187,
1341
+ "step": 74
1342
+ },
1343
+ {
1344
+ "epoch": 0.9880609304240429,
1345
+ "grad_norm": 23669.484375,
1346
+ "learning_rate": 0.0,
1347
+ "logits/chosen": -0.7702288627624512,
1348
+ "logits/rejected": -0.7675869464874268,
1349
+ "logps/chosen": -276.1815185546875,
1350
+ "logps/ref_chosen": -256.006103515625,
1351
+ "logps/ref_rejected": -373.4369201660156,
1352
+ "logps/rejected": -408.344482421875,
1353
+ "loss": 925.0488,
1354
+ "rewards/accuracies": 0.7578125,
1355
+ "rewards/chosen": -0.20175378024578094,
1356
+ "rewards/margins": 0.14732176065444946,
1357
+ "rewards/rejected": -0.349075585603714,
1358
+ "sft_loss": 0.9371762275695801,
1359
+ "step": 75
1360
+ },
1361
+ {
1362
+ "epoch": 0.9880609304240429,
1363
+ "step": 75,
1364
+ "total_flos": 0.0,
1365
+ "train_loss": 1284.6718611653646,
1366
+ "train_runtime": 5197.2653,
1367
+ "train_samples_per_second": 1.869,
1368
+ "train_steps_per_second": 0.014
1369
+ }
1370
+ ],
1371
+ "logging_steps": 1,
1372
+ "max_steps": 75,
1373
+ "num_input_tokens_seen": 0,
1374
+ "num_train_epochs": 1,
1375
+ "save_steps": 100000,
1376
+ "stateful_callbacks": {
1377
+ "TrainerControl": {
1378
+ "args": {
1379
+ "should_epoch_stop": false,
1380
+ "should_evaluate": false,
1381
+ "should_log": false,
1382
+ "should_save": false,
1383
+ "should_training_stop": false
1384
+ },
1385
+ "attributes": {}
1386
+ }
1387
+ },
1388
+ "total_flos": 0.0,
1389
+ "train_batch_size": 2,
1390
+ "trial_name": null,
1391
+ "trial_params": null
1392
+ }
Llama-3.2-3B-Instruct-ipo-proportion1.0-sft0.0-chunk7_6_rr_all/2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3bc98d799dfa1223953bf5c33c0f52fb2dc0545c852e33c9ee57a04201c96c7
3
+ size 7416