Hugging Face's logo

OpenBabylon
/
MamayLM-ORPO-align-lora256

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
orpo
Model card Files Metrics Community
antonpolishko commited on
Commit
e549932
·
verified ·
1 Parent(s): 02d1ef5

Model save

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. README.md +67 -0
  3. adapter_config.json +34 -0
  4. adapter_model.safetensors +3 -0
  5. all_results.json +9 -0
  6. runs/May09_00-34-17_sky-3542-mykola-5e9d8a2f-head-4qgcm7zi-compute/events.out.tfevents.1746750936.sky-3542-mykola-5e9d8a2f-head-4qgcm7zi-compute.93488.0 +3 -0
  7. special_tokens_map.json +34 -0
  8. tokenizer.json +3 -0
  9. tokenizer_config.json +2014 -0
  10. train_results.json +9 -0
  11. trainer_state.json +1429 -0
  12. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: INSAIT-Institute/MamayLM-Gemma-2-9B-IT-v0.1
3
+ library_name: transformers
4
+ model_name: MamayLM-ORPO-align-lora256
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - orpo
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for MamayLM-ORPO-align-lora256
13
+
14
+ This model is a fine-tuned version of [INSAIT-Institute/MamayLM-Gemma-2-9B-IT-v0.1](https://huggingface.co/INSAIT-Institute/MamayLM-Gemma-2-9B-IT-v0.1).
15
+ It has been trained using [TRL](https://github.com/huggingface/trl).
16
+
17
+ ## Quick start
18
+
19
+ ```python
20
+ from transformers import pipeline
21
+
22
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
+ generator = pipeline("text-generation", model="OpenBabylon/MamayLM-ORPO-align-lora256", device="cuda")
24
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
+ print(output["generated_text"])
26
+ ```
27
+
28
+ ## Training procedure
29
+
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/polyagent/MamayLM-ORPO/runs/hyy28wgh)
31
+
32
+
33
+ This model was trained with ORPO, a method introduced in [ORPO: Monolithic Preference Optimization without Reference Model](https://huggingface.co/papers/2403.07691).
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.17.0
38
+ - Transformers: 4.51.3
39
+ - Pytorch: 2.6.0
40
+ - Datasets: 3.6.0
41
+ - Tokenizers: 0.21.1
42
+
43
+ ## Citations
44
+
45
+ Cite ORPO as:
46
+
47
+ ```bibtex
48
+ @article{hong2024orpo,
49
+ title = {{ORPO: Monolithic Preference Optimization without Reference Model}},
50
+ author = {Jiwoo Hong and Noah Lee and James Thorne},
51
+ year = 2024,
52
+ eprint = {arXiv:2403.07691}
53
+ }
54
+ ```
55
+
56
+ Cite TRL as:
57
+
58
+ ```bibtex
59
+ @misc{vonwerra2022trl,
60
+ title = {{TRL: Transformer Reinforcement Learning}},
61
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
62
+ year = 2020,
63
+ journal = {GitHub repository},
64
+ publisher = {GitHub},
65
+ howpublished = {\url{https://github.com/huggingface/trl}}
66
+ }
67
+ ```
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "INSAIT-Institute/MamayLM-Gemma-2-9B-IT-v0.1",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 4096,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 256,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "q_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "trainable_token_indices": null,
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6172db751edb874a7340d83946629b6e1105ef18588b66befbfa8e8262d2f49e
3
+ size 286284472
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 1.0934507308467742,
5
+ "train_runtime": 1550.1799,
6
+ "train_samples": 12400,
7
+ "train_samples_per_second": 7.999,
8
+ "train_steps_per_second": 0.5
9
+ }
runs/May09_00-34-17_sky-3542-mykola-5e9d8a2f-head-4qgcm7zi-compute/events.out.tfevents.1746750936.sky-3542-mykola-5e9d8a2f-head-4qgcm7zi-compute.93488.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30f73dcfbea3b0b9068030d60f7f864ea6cb51b4f9e102d0c1e4cf72fccd26cf
3
+ size 72151
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
3
+ size 34362873
tokenizer_config.json ADDED
@@ -0,0 +1,2014 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "5": {
46
+ "content": "<2mass>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "7": {
62
+ "content": "<unused0>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "8": {
70
+ "content": "<unused1>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "9": {
78
+ "content": "<unused2>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "10": {
86
+ "content": "<unused3>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "11": {
94
+ "content": "<unused4>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "12": {
102
+ "content": "<unused5>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "13": {
110
+ "content": "<unused6>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "14": {
118
+ "content": "<unused7>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "15": {
126
+ "content": "<unused8>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "16": {
134
+ "content": "<unused9>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "17": {
142
+ "content": "<unused10>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "18": {
150
+ "content": "<unused11>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "19": {
158
+ "content": "<unused12>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "20": {
166
+ "content": "<unused13>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "21": {
174
+ "content": "<unused14>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "22": {
182
+ "content": "<unused15>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "23": {
190
+ "content": "<unused16>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "24": {
198
+ "content": "<unused17>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "25": {
206
+ "content": "<unused18>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "26": {
214
+ "content": "<unused19>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "27": {
222
+ "content": "<unused20>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "28": {
230
+ "content": "<unused21>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "29": {
238
+ "content": "<unused22>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "30": {
246
+ "content": "<unused23>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "31": {
254
+ "content": "<unused24>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "32": {
262
+ "content": "<unused25>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "33": {
270
+ "content": "<unused26>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "34": {
278
+ "content": "<unused27>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "35": {
286
+ "content": "<unused28>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "36": {
294
+ "content": "<unused29>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "37": {
302
+ "content": "<unused30>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<unused31>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "<unused32>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<unused33>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "41": {
334
+ "content": "<unused34>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "42": {
342
+ "content": "<unused35>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "43": {
350
+ "content": "<unused36>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "44": {
358
+ "content": "<unused37>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "45": {
366
+ "content": "<unused38>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "46": {
374
+ "content": "<unused39>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "47": {
382
+ "content": "<unused40>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "48": {
390
+ "content": "<unused41>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "49": {
398
+ "content": "<unused42>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "50": {
406
+ "content": "<unused43>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "51": {
414
+ "content": "<unused44>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "52": {
422
+ "content": "<unused45>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "53": {
430
+ "content": "<unused46>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "54": {
438
+ "content": "<unused47>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "55": {
446
+ "content": "<unused48>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "56": {
454
+ "content": "<unused49>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "57": {
462
+ "content": "<unused50>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "58": {
470
+ "content": "<unused51>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "59": {
478
+ "content": "<unused52>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "60": {
486
+ "content": "<unused53>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "61": {
494
+ "content": "<unused54>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "62": {
502
+ "content": "<unused55>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "63": {
510
+ "content": "<unused56>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "64": {
518
+ "content": "<unused57>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "65": {
526
+ "content": "<unused58>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "66": {
534
+ "content": "<unused59>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "67": {
542
+ "content": "<unused60>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "68": {
550
+ "content": "<unused61>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "69": {
558
+ "content": "<unused62>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "70": {
566
+ "content": "<unused63>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "71": {
574
+ "content": "<unused64>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "72": {
582
+ "content": "<unused65>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "73": {
590
+ "content": "<unused66>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "74": {
598
+ "content": "<unused67>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "75": {
606
+ "content": "<unused68>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "76": {
614
+ "content": "<unused69>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "77": {
622
+ "content": "<unused70>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "78": {
630
+ "content": "<unused71>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "79": {
638
+ "content": "<unused72>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "80": {
646
+ "content": "<unused73>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "81": {
654
+ "content": "<unused74>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "82": {
662
+ "content": "<unused75>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "83": {
670
+ "content": "<unused76>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "84": {
678
+ "content": "<unused77>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "85": {
686
+ "content": "<unused78>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "86": {
694
+ "content": "<unused79>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "87": {
702
+ "content": "<unused80>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "88": {
710
+ "content": "<unused81>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "89": {
718
+ "content": "<unused82>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "90": {
726
+ "content": "<unused83>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "91": {
734
+ "content": "<unused84>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "92": {
742
+ "content": "<unused85>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "93": {
750
+ "content": "<unused86>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "94": {
758
+ "content": "<unused87>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "95": {
766
+ "content": "<unused88>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "96": {
774
+ "content": "<unused89>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "97": {
782
+ "content": "<unused90>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "98": {
790
+ "content": "<unused91>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "99": {
798
+ "content": "<unused92>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "100": {
806
+ "content": "<unused93>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "101": {
814
+ "content": "<unused94>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "102": {
822
+ "content": "<unused95>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "103": {
830
+ "content": "<unused96>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "104": {
838
+ "content": "<unused97>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "105": {
846
+ "content": "<unused98>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "108": {
870
+ "content": "\n",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "109": {
878
+ "content": "\n\n",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "110": {
886
+ "content": "\n\n\n",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
+ },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": false
1060
+ },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": false
1068
+ },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": false
1076
+ },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": false
1084
+ },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false
1092
+ },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": false
1100
+ },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": false
1108
+ },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": false
1116
+ },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": false
1124
+ },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": false
1132
+ },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": false
1140
+ },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": false
1148
+ },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": false
1156
+ },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false
1164
+ },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": false
1172
+ },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": false
1180
+ },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": false
1188
+ },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": false
1196
+ },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": false
1204
+ },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": false
1212
+ },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": false
1220
+ },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": false
1228
+ },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false
1236
+ },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": false
1244
+ },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": false
1268
+ },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": false
1276
+ },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": false
1284
+ },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": false
1292
+ },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": false
1300
+ },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false
1308
+ },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": false
1316
+ },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": false
1324
+ },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": false
1332
+ },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": false
1340
+ },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": false
1348
+ },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": false
1356
+ },
1357
+ "169": {
1358
+ "content": "<table>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": false
1364
+ },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": false
1372
+ },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false
1380
+ },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": false
1388
+ },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": false
1396
+ },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": false
1404
+ },
1405
+ "175": {
1406
+ "content": "<th>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": false
1412
+ },
1413
+ "176": {
1414
+ "content": "<td>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": false
1420
+ },
1421
+ "177": {
1422
+ "content": "</table>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": false
1428
+ },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": false
1436
+ },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": false
1444
+ },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false
1452
+ },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": false
1460
+ },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": false
1468
+ },
1469
+ "183": {
1470
+ "content": "</th>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "184": {
1478
+ "content": "</td>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false
1524
+ },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": false
1532
+ },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": false
1540
+ },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": false
1548
+ },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": false
1556
+ },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": false
1564
+ },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "200": {
1606
+ "content": "<em>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ },
1613
+ "201": {
1614
+ "content": "<b>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": false
1620
+ },
1621
+ "202": {
1622
+ "content": "<i>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": false
1628
+ },
1629
+ "203": {
1630
+ "content": "<u>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": false
1636
+ },
1637
+ "204": {
1638
+ "content": "<s>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": false
1644
+ },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": false
1652
+ },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": false
1660
+ },
1661
+ "207": {
1662
+ "content": "<code>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false
1668
+ },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": false
1676
+ },
1677
+ "209": {
1678
+ "content": "</em>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": false
1684
+ },
1685
+ "210": {
1686
+ "content": "</b>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": false
1692
+ },
1693
+ "211": {
1694
+ "content": "</i>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": false
1700
+ },
1701
+ "212": {
1702
+ "content": "</u>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": false
1708
+ },
1709
+ "213": {
1710
+ "content": "</s>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": false
1716
+ },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": false
1724
+ },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": false
1732
+ },
1733
+ "216": {
1734
+ "content": "</code>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false
1740
+ },
1741
+ "255968": {
1742
+ "content": "[toxicity=0]",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": false
1748
+ },
1749
+ "255969": {
1750
+ "content": "\t\t",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": false
1756
+ },
1757
+ "255970": {
1758
+ "content": "\t\t\t",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": false
1764
+ },
1765
+ "255971": {
1766
+ "content": "\t\t\t\t",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": false
1772
+ },
1773
+ "255972": {
1774
+ "content": "\t\t\t\t\t",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": false
1780
+ },
1781
+ "255973": {
1782
+ "content": "\t\t\t\t\t\t",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": false
1788
+ },
1789
+ "255974": {
1790
+ "content": "\t\t\t\t\t\t\t",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": false
1796
+ },
1797
+ "255975": {
1798
+ "content": "\t\t\t\t\t\t\t\t",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": false
1804
+ },
1805
+ "255976": {
1806
+ "content": "\t\t\t\t\t\t\t\t\t",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": false
1812
+ },
1813
+ "255977": {
1814
+ "content": "\t\t\t\t\t\t\t\t\t\t",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": false
1820
+ },
1821
+ "255978": {
1822
+ "content": "\t\t\t\t\t\t\t\t\t\t\t",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": false
1828
+ },
1829
+ "255979": {
1830
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": false
1836
+ },
1837
+ "255980": {
1838
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": false
1844
+ },
1845
+ "255981": {
1846
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": false
1852
+ },
1853
+ "255982": {
1854
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": false
1860
+ },
1861
+ "255983": {
1862
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": false
1868
+ },
1869
+ "255984": {
1870
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": false
1876
+ },
1877
+ "255985": {
1878
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": false
1884
+ },
1885
+ "255986": {
1886
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": false
1892
+ },
1893
+ "255987": {
1894
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": false
1900
+ },
1901
+ "255988": {
1902
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": false
1908
+ },
1909
+ "255989": {
1910
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": false
1916
+ },
1917
+ "255990": {
1918
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": false
1924
+ },
1925
+ "255991": {
1926
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": false
1932
+ },
1933
+ "255992": {
1934
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": false
1940
+ },
1941
+ "255993": {
1942
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": false
1948
+ },
1949
+ "255994": {
1950
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": false
1956
+ },
1957
+ "255995": {
1958
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": false
1964
+ },
1965
+ "255996": {
1966
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": false
1972
+ },
1973
+ "255997": {
1974
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": false
1980
+ },
1981
+ "255998": {
1982
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": false
1988
+ },
1989
+ "255999": {
1990
+ "content": "<unused99>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": false
1996
+ }
1997
+ },
1998
+ "additional_special_tokens": [
1999
+ "<start_of_turn>",
2000
+ "<end_of_turn>"
2001
+ ],
2002
+ "bos_token": "<bos>",
2003
+ "chat_template": "{{ bos_token }}{% for message in messages %}\n{% if message.role == 'assistant' %}\n {{ '<start_of_turn>model ' + message.content | trim + '<end_of_turn> ' }}\n{% elif message.role == 'system' %}\n {# ←-- skip system turns completely #}\n{% else %}\n {{ '<start_of_turn>' + message.role + ' ' + message.content | trim + '<end_of_turn> ' }}\n{% endif %}\n{% endfor %}\n{% if add_generation_prompt %}{{ '<start_of_turn>model ' }}{% endif %}\n",
2004
+ "clean_up_tokenization_spaces": false,
2005
+ "eos_token": "<eos>",
2006
+ "extra_special_tokens": {},
2007
+ "model_max_length": 2048,
2008
+ "pad_token": "<pad>",
2009
+ "sp_model_kwargs": {},
2010
+ "spaces_between_special_tokens": false,
2011
+ "tokenizer_class": "GemmaTokenizerFast",
2012
+ "unk_token": "<unk>",
2013
+ "use_default_system_prompt": false
2014
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 1.0934507308467742,
5
+ "train_runtime": 1550.1799,
6
+ "train_samples": 12400,
7
+ "train_samples_per_second": 7.999,
8
+ "train_steps_per_second": 0.5
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1429 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 775,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.012903225806451613,
14
+ "grad_norm": 49.70627156027633,
15
+ "learning_rate": 9e-08,
16
+ "log_odds_chosen": 1.0792968273162842,
17
+ "log_odds_ratio": -0.33574217557907104,
18
+ "logits/chosen": -1.0568358898162842,
19
+ "logits/rejected": 15.681249618530273,
20
+ "logps/chosen": -1.658593773841858,
21
+ "logps/rejected": -2.604687452316284,
22
+ "loss": 2.0072,
23
+ "nll_loss": 1.9914062023162842,
24
+ "rewards/accuracies": 0.949999988079071,
25
+ "rewards/chosen": -0.08281250298023224,
26
+ "rewards/margins": 0.04736328125,
27
+ "rewards/rejected": -0.13007812201976776,
28
+ "step": 10
29
+ },
30
+ {
31
+ "epoch": 0.025806451612903226,
32
+ "grad_norm": 30.171727040948067,
33
+ "learning_rate": 1.8999999999999998e-07,
34
+ "log_odds_chosen": 1.074609398841858,
35
+ "log_odds_ratio": -0.33623045682907104,
36
+ "logits/chosen": -0.768359363079071,
37
+ "logits/rejected": 16.9375,
38
+ "logps/chosen": -1.6257812976837158,
39
+ "logps/rejected": -2.5609374046325684,
40
+ "loss": 1.9264,
41
+ "nll_loss": 1.9093749523162842,
42
+ "rewards/accuracies": 0.9750000238418579,
43
+ "rewards/chosen": -0.08120117336511612,
44
+ "rewards/margins": 0.04676513746380806,
45
+ "rewards/rejected": -0.12802734971046448,
46
+ "step": 20
47
+ },
48
+ {
49
+ "epoch": 0.03870967741935484,
50
+ "grad_norm": 24.09532939818586,
51
+ "learning_rate": 2.9e-07,
52
+ "log_odds_chosen": 0.7685546875,
53
+ "log_odds_ratio": -0.41425782442092896,
54
+ "logits/chosen": -0.579296886920929,
55
+ "logits/rejected": 16.618749618530273,
56
+ "logps/chosen": -1.521875023841858,
57
+ "logps/rejected": -2.1585936546325684,
58
+ "loss": 1.8082,
59
+ "nll_loss": 1.786718726158142,
60
+ "rewards/accuracies": 0.918749988079071,
61
+ "rewards/chosen": -0.07612304389476776,
62
+ "rewards/margins": 0.0318603515625,
63
+ "rewards/rejected": -0.10791015625,
64
+ "step": 30
65
+ },
66
+ {
67
+ "epoch": 0.05161290322580645,
68
+ "grad_norm": 15.677239750315456,
69
+ "learning_rate": 3.8999999999999997e-07,
70
+ "log_odds_chosen": 0.5810546875,
71
+ "log_odds_ratio": -0.4683593809604645,
72
+ "logits/chosen": 0.649487316608429,
73
+ "logits/rejected": 17.106250762939453,
74
+ "logps/chosen": -1.369531273841858,
75
+ "logps/rejected": -1.8312499523162842,
76
+ "loss": 1.6297,
77
+ "nll_loss": 1.60546875,
78
+ "rewards/accuracies": 0.918749988079071,
79
+ "rewards/chosen": -0.06843261420726776,
80
+ "rewards/margins": 0.02312622033059597,
81
+ "rewards/rejected": -0.09165038913488388,
82
+ "step": 40
83
+ },
84
+ {
85
+ "epoch": 0.06451612903225806,
86
+ "grad_norm": 11.041193525639065,
87
+ "learning_rate": 4.9e-07,
88
+ "log_odds_chosen": 0.4306640625,
89
+ "log_odds_ratio": -0.5328124761581421,
90
+ "logits/chosen": 1.29931640625,
91
+ "logits/rejected": 17.337499618530273,
92
+ "logps/chosen": -1.2703125476837158,
93
+ "logps/rejected": -1.6023437976837158,
94
+ "loss": 1.4658,
95
+ "nll_loss": 1.4406249523162842,
96
+ "rewards/accuracies": 0.7749999761581421,
97
+ "rewards/chosen": -0.06340332329273224,
98
+ "rewards/margins": 0.01667175255715847,
99
+ "rewards/rejected": -0.08022461086511612,
100
+ "step": 50
101
+ },
102
+ {
103
+ "epoch": 0.07741935483870968,
104
+ "grad_norm": 11.724138338625753,
105
+ "learning_rate": 5.9e-07,
106
+ "log_odds_chosen": 0.25605469942092896,
107
+ "log_odds_ratio": -0.607421875,
108
+ "logits/chosen": 1.3015625476837158,
109
+ "logits/rejected": 16.975000381469727,
110
+ "logps/chosen": -1.2265625,
111
+ "logps/rejected": -1.4226562976837158,
112
+ "loss": 1.3937,
113
+ "nll_loss": 1.36328125,
114
+ "rewards/accuracies": 0.6499999761581421,
115
+ "rewards/chosen": -0.06137695163488388,
116
+ "rewards/margins": 0.00977325439453125,
117
+ "rewards/rejected": -0.0711669921875,
118
+ "step": 60
119
+ },
120
+ {
121
+ "epoch": 0.09032258064516129,
122
+ "grad_norm": 9.740328527335777,
123
+ "learning_rate": 6.9e-07,
124
+ "log_odds_chosen": 0.2662109434604645,
125
+ "log_odds_ratio": -0.596484363079071,
126
+ "logits/chosen": 0.48261719942092896,
127
+ "logits/rejected": 17.049999237060547,
128
+ "logps/chosen": -1.1023437976837158,
129
+ "logps/rejected": -1.303125023841858,
130
+ "loss": 1.2443,
131
+ "nll_loss": 1.21484375,
132
+ "rewards/accuracies": 0.706250011920929,
133
+ "rewards/chosen": -0.05512695387005806,
134
+ "rewards/margins": 0.010111999697983265,
135
+ "rewards/rejected": -0.06528320163488388,
136
+ "step": 70
137
+ },
138
+ {
139
+ "epoch": 0.1032258064516129,
140
+ "grad_norm": 11.193492093253996,
141
+ "learning_rate": 7.9e-07,
142
+ "log_odds_chosen": 0.1834716796875,
143
+ "log_odds_ratio": -0.6371093988418579,
144
+ "logits/chosen": -0.14792481064796448,
145
+ "logits/rejected": 16.693750381469727,
146
+ "logps/chosen": -1.11328125,
147
+ "logps/rejected": -1.2453124523162842,
148
+ "loss": 1.2082,
149
+ "nll_loss": 1.1765625476837158,
150
+ "rewards/accuracies": 0.668749988079071,
151
+ "rewards/chosen": -0.05561523512005806,
152
+ "rewards/margins": 0.006572723388671875,
153
+ "rewards/rejected": -0.06228027492761612,
154
+ "step": 80
155
+ },
156
+ {
157
+ "epoch": 0.11612903225806452,
158
+ "grad_norm": 8.924505161358022,
159
+ "learning_rate": 8.9e-07,
160
+ "log_odds_chosen": 0.4200195372104645,
161
+ "log_odds_ratio": -0.5423828363418579,
162
+ "logits/chosen": -0.7088623046875,
163
+ "logits/rejected": 16.268749237060547,
164
+ "logps/chosen": -1.0769531726837158,
165
+ "logps/rejected": -1.37890625,
166
+ "loss": 1.1544,
167
+ "nll_loss": 1.1281249523162842,
168
+ "rewards/accuracies": 0.7437499761581421,
169
+ "rewards/chosen": -0.05378418043255806,
170
+ "rewards/margins": 0.01514282263815403,
171
+ "rewards/rejected": -0.06894531100988388,
172
+ "step": 90
173
+ },
174
+ {
175
+ "epoch": 0.12903225806451613,
176
+ "grad_norm": 12.076066826365905,
177
+ "learning_rate": 9.9e-07,
178
+ "log_odds_chosen": 0.8257812261581421,
179
+ "log_odds_ratio": -0.4107421934604645,
180
+ "logits/chosen": -1.249609351158142,
181
+ "logits/rejected": 15.487500190734863,
182
+ "logps/chosen": -1.103906273841858,
183
+ "logps/rejected": -1.73828125,
184
+ "loss": 1.1656,
185
+ "nll_loss": 1.14453125,
186
+ "rewards/accuracies": 0.893750011920929,
187
+ "rewards/chosen": -0.05520019680261612,
188
+ "rewards/margins": 0.03176269680261612,
189
+ "rewards/rejected": -0.0869140625,
190
+ "step": 100
191
+ },
192
+ {
193
+ "epoch": 0.14193548387096774,
194
+ "grad_norm": 15.202198043236956,
195
+ "learning_rate": 9.578262852211513e-07,
196
+ "log_odds_chosen": 1.3203125,
197
+ "log_odds_ratio": -0.29169923067092896,
198
+ "logits/chosen": -0.812451183795929,
199
+ "logits/rejected": 16.131250381469727,
200
+ "logps/chosen": -1.0925781726837158,
201
+ "logps/rejected": -2.143749952316284,
202
+ "loss": 1.1375,
203
+ "nll_loss": 1.1222655773162842,
204
+ "rewards/accuracies": 0.9437500238418579,
205
+ "rewards/chosen": -0.05466308444738388,
206
+ "rewards/margins": 0.05246581882238388,
207
+ "rewards/rejected": -0.107177734375,
208
+ "step": 110
209
+ },
210
+ {
211
+ "epoch": 0.15483870967741936,
212
+ "grad_norm": 8.65251972518117,
213
+ "learning_rate": 9.166984970282113e-07,
214
+ "log_odds_chosen": 1.6789062023162842,
215
+ "log_odds_ratio": -0.23710937798023224,
216
+ "logits/chosen": -1.5061066150665283,
217
+ "logits/rejected": 16.456249237060547,
218
+ "logps/chosen": -1.0703125,
219
+ "logps/rejected": -2.426562547683716,
220
+ "loss": 1.1029,
221
+ "nll_loss": 1.091406226158142,
222
+ "rewards/accuracies": 0.9437500238418579,
223
+ "rewards/chosen": -0.05354003980755806,
224
+ "rewards/margins": 0.06794433295726776,
225
+ "rewards/rejected": -0.12153320014476776,
226
+ "step": 120
227
+ },
228
+ {
229
+ "epoch": 0.16774193548387098,
230
+ "grad_norm": 9.543867756428785,
231
+ "learning_rate": 8.804509063256238e-07,
232
+ "log_odds_chosen": 1.8585937023162842,
233
+ "log_odds_ratio": -0.2021484375,
234
+ "logits/chosen": -0.5859375,
235
+ "logits/rejected": 16.193750381469727,
236
+ "logps/chosen": -1.100000023841858,
237
+ "logps/rejected": -2.6265625953674316,
238
+ "loss": 1.1302,
239
+ "nll_loss": 1.1203124523162842,
240
+ "rewards/accuracies": 0.9624999761581421,
241
+ "rewards/chosen": -0.054931640625,
242
+ "rewards/margins": 0.07631836086511612,
243
+ "rewards/rejected": -0.13129882514476776,
244
+ "step": 130
245
+ },
246
+ {
247
+ "epoch": 0.18064516129032257,
248
+ "grad_norm": 9.110822418673385,
249
+ "learning_rate": 8.481889296799708e-07,
250
+ "log_odds_chosen": 1.7273437976837158,
251
+ "log_odds_ratio": -0.208984375,
252
+ "logits/chosen": -1.088769555091858,
253
+ "logits/rejected": 15.6875,
254
+ "logps/chosen": -1.073828101158142,
255
+ "logps/rejected": -2.467968702316284,
256
+ "loss": 1.1026,
257
+ "nll_loss": 1.0925781726837158,
258
+ "rewards/accuracies": 0.987500011920929,
259
+ "rewards/chosen": -0.05373535305261612,
260
+ "rewards/margins": 0.06960449367761612,
261
+ "rewards/rejected": -0.12324218451976776,
262
+ "step": 140
263
+ },
264
+ {
265
+ "epoch": 0.1935483870967742,
266
+ "grad_norm": 9.034516194801183,
267
+ "learning_rate": 8.192319205190404e-07,
268
+ "log_odds_chosen": 1.810156226158142,
269
+ "log_odds_ratio": -0.20615234971046448,
270
+ "logits/chosen": -1.556640625,
271
+ "logits/rejected": 15.6875,
272
+ "logps/chosen": -1.064062476158142,
273
+ "logps/rejected": -2.543750047683716,
274
+ "loss": 1.0917,
275
+ "nll_loss": 1.0808594226837158,
276
+ "rewards/accuracies": 0.981249988079071,
277
+ "rewards/chosen": -0.05317382887005806,
278
+ "rewards/margins": 0.073974609375,
279
+ "rewards/rejected": -0.12734374403953552,
280
+ "step": 150
281
+ },
282
+ {
283
+ "epoch": 0.2064516129032258,
284
+ "grad_norm": 11.756984822063554,
285
+ "learning_rate": 7.93051585718144e-07,
286
+ "log_odds_chosen": 1.8171875476837158,
287
+ "log_odds_ratio": -0.21816405653953552,
288
+ "logits/chosen": -2.0663084983825684,
289
+ "logits/rejected": 15.09375,
290
+ "logps/chosen": -1.0285155773162842,
291
+ "logps/rejected": -2.503124952316284,
292
+ "loss": 1.0641,
293
+ "nll_loss": 1.053125023841858,
294
+ "rewards/accuracies": 0.9750000238418579,
295
+ "rewards/chosen": -0.05136718600988388,
296
+ "rewards/margins": 0.07377929985523224,
297
+ "rewards/rejected": -0.12509766221046448,
298
+ "step": 160
299
+ },
300
+ {
301
+ "epoch": 0.21935483870967742,
302
+ "grad_norm": 8.627859846051514,
303
+ "learning_rate": 7.692307692307691e-07,
304
+ "log_odds_chosen": 2.004687547683716,
305
+ "log_odds_ratio": -0.17290039360523224,
306
+ "logits/chosen": -1.9910156726837158,
307
+ "logits/rejected": 16.25,
308
+ "logps/chosen": -0.9867187738418579,
309
+ "logps/rejected": -2.6109375953674316,
310
+ "loss": 1.0264,
311
+ "nll_loss": 1.017968773841858,
312
+ "rewards/accuracies": 0.9937499761581421,
313
+ "rewards/chosen": -0.04934082180261612,
314
+ "rewards/margins": 0.08115234225988388,
315
+ "rewards/rejected": -0.13046875596046448,
316
+ "step": 170
317
+ },
318
+ {
319
+ "epoch": 0.23225806451612904,
320
+ "grad_norm": 9.527291194409495,
321
+ "learning_rate": 7.474350927519359e-07,
322
+ "log_odds_chosen": 1.9148437976837158,
323
+ "log_odds_ratio": -0.18808594346046448,
324
+ "logits/chosen": -1.7332031726837158,
325
+ "logits/rejected": 15.59375,
326
+ "logps/chosen": -1.021484375,
327
+ "logps/rejected": -2.5703125,
328
+ "loss": 1.0421,
329
+ "nll_loss": 1.0339844226837158,
330
+ "rewards/accuracies": 0.9750000238418579,
331
+ "rewards/chosen": -0.0511474609375,
332
+ "rewards/margins": 0.07758788764476776,
333
+ "rewards/rejected": -0.12856444716453552,
334
+ "step": 180
335
+ },
336
+ {
337
+ "epoch": 0.24516129032258063,
338
+ "grad_norm": 8.651906842906772,
339
+ "learning_rate": 7.273929674533079e-07,
340
+ "log_odds_chosen": 1.8828125,
341
+ "log_odds_ratio": -0.19472655653953552,
342
+ "logits/chosen": -1.141992211341858,
343
+ "logits/rejected": 16.087499618530273,
344
+ "logps/chosen": -1.011328101158142,
345
+ "logps/rejected": -2.535937547683716,
346
+ "loss": 1.0458,
347
+ "nll_loss": 1.035546898841858,
348
+ "rewards/accuracies": 0.96875,
349
+ "rewards/chosen": -0.05061035230755806,
350
+ "rewards/margins": 0.076171875,
351
+ "rewards/rejected": -0.12680664658546448,
352
+ "step": 190
353
+ },
354
+ {
355
+ "epoch": 0.25806451612903225,
356
+ "grad_norm": 8.860357440935188,
357
+ "learning_rate": 7.088812050083358e-07,
358
+ "log_odds_chosen": 2.0757813453674316,
359
+ "log_odds_ratio": -0.16391602158546448,
360
+ "logits/chosen": -1.6111328601837158,
361
+ "logits/rejected": 16.25,
362
+ "logps/chosen": -1.04296875,
363
+ "logps/rejected": -2.754687547683716,
364
+ "loss": 1.0695,
365
+ "nll_loss": 1.060937523841858,
366
+ "rewards/accuracies": 0.9937499761581421,
367
+ "rewards/chosen": -0.05217285081744194,
368
+ "rewards/margins": 0.08540038764476776,
369
+ "rewards/rejected": -0.1376953125,
370
+ "step": 200
371
+ },
372
+ {
373
+ "epoch": 0.2709677419354839,
374
+ "grad_norm": 9.53626963534049,
375
+ "learning_rate": 6.917144638660746e-07,
376
+ "log_odds_chosen": 2.059375047683716,
377
+ "log_odds_ratio": -0.18574218451976776,
378
+ "logits/chosen": -2.100390672683716,
379
+ "logits/rejected": 15.381250381469727,
380
+ "logps/chosen": -1.026953101158142,
381
+ "logps/rejected": -2.707812547683716,
382
+ "loss": 1.0444,
383
+ "nll_loss": 1.0359375476837158,
384
+ "rewards/accuracies": 0.96875,
385
+ "rewards/chosen": -0.0513916015625,
386
+ "rewards/margins": 0.08403320610523224,
387
+ "rewards/rejected": -0.13525390625,
388
+ "step": 210
389
+ },
390
+ {
391
+ "epoch": 0.2838709677419355,
392
+ "grad_norm": 9.083636368143717,
393
+ "learning_rate": 6.757373783994859e-07,
394
+ "log_odds_chosen": 2.0093750953674316,
395
+ "log_odds_ratio": -0.20771484076976776,
396
+ "logits/chosen": -1.235937476158142,
397
+ "logits/rejected": 15.949999809265137,
398
+ "logps/chosen": -1.0832030773162842,
399
+ "logps/rejected": -2.7562499046325684,
400
+ "loss": 1.105,
401
+ "nll_loss": 1.0949218273162842,
402
+ "rewards/accuracies": 0.925000011920929,
403
+ "rewards/chosen": -0.05417480319738388,
404
+ "rewards/margins": 0.08376464992761612,
405
+ "rewards/rejected": -0.13813476264476776,
406
+ "step": 220
407
+ },
408
+ {
409
+ "epoch": 0.2967741935483871,
410
+ "grad_norm": 9.478501511961401,
411
+ "learning_rate": 6.608186004550897e-07,
412
+ "log_odds_chosen": 1.9328124523162842,
413
+ "log_odds_ratio": -0.19472655653953552,
414
+ "logits/chosen": -0.9737304449081421,
415
+ "logits/rejected": 15.65625,
416
+ "logps/chosen": -1.0750000476837158,
417
+ "logps/rejected": -2.6656250953674316,
418
+ "loss": 1.0952,
419
+ "nll_loss": 1.0847656726837158,
420
+ "rewards/accuracies": 0.96875,
421
+ "rewards/chosen": -0.05373535305261612,
422
+ "rewards/margins": 0.07958984375,
423
+ "rewards/rejected": -0.13334961235523224,
424
+ "step": 230
425
+ },
426
+ {
427
+ "epoch": 0.3096774193548387,
428
+ "grad_norm": 46.68237974376569,
429
+ "learning_rate": 6.468462273531509e-07,
430
+ "log_odds_chosen": 2.008593797683716,
431
+ "log_odds_ratio": -0.18378905951976776,
432
+ "logits/chosen": -2.227734327316284,
433
+ "logits/rejected": 14.28125,
434
+ "logps/chosen": -1.028906226158142,
435
+ "logps/rejected": -2.674999952316284,
436
+ "loss": 1.059,
437
+ "nll_loss": 1.05078125,
438
+ "rewards/accuracies": 0.987500011920929,
439
+ "rewards/chosen": -0.05146484449505806,
440
+ "rewards/margins": 0.082275390625,
441
+ "rewards/rejected": -0.1337890625,
442
+ "step": 240
443
+ },
444
+ {
445
+ "epoch": 0.3225806451612903,
446
+ "grad_norm": 8.824580348066425,
447
+ "learning_rate": 6.337242505244779e-07,
448
+ "log_odds_chosen": 2.4437499046325684,
449
+ "log_odds_ratio": -0.13422851264476776,
450
+ "logits/chosen": -2.5560545921325684,
451
+ "logits/rejected": 15.268750190734863,
452
+ "logps/chosen": -0.984375,
453
+ "logps/rejected": -3.018749952316284,
454
+ "loss": 1.0172,
455
+ "nll_loss": 1.0109374523162842,
456
+ "rewards/accuracies": 0.987500011920929,
457
+ "rewards/chosen": -0.04924316331744194,
458
+ "rewards/margins": 0.10166015475988388,
459
+ "rewards/rejected": -0.15087890625,
460
+ "step": 250
461
+ },
462
+ {
463
+ "epoch": 0.33548387096774196,
464
+ "grad_norm": 8.52330516891079,
465
+ "learning_rate": 6.213697660011999e-07,
466
+ "log_odds_chosen": 2.0453124046325684,
467
+ "log_odds_ratio": -0.19428710639476776,
468
+ "logits/chosen": -2.333984375,
469
+ "logits/rejected": 15.28125,
470
+ "logps/chosen": -1.0128905773162842,
471
+ "logps/rejected": -2.690624952316284,
472
+ "loss": 1.0436,
473
+ "nll_loss": 1.033593773841858,
474
+ "rewards/accuracies": 0.9750000238418579,
475
+ "rewards/chosen": -0.05063476413488388,
476
+ "rewards/margins": 0.08393554389476776,
477
+ "rewards/rejected": -0.13457031548023224,
478
+ "step": 260
479
+ },
480
+ {
481
+ "epoch": 0.34838709677419355,
482
+ "grad_norm": 9.5127221175917,
483
+ "learning_rate": 6.097107608496924e-07,
484
+ "log_odds_chosen": 2.2632813453674316,
485
+ "log_odds_ratio": -0.16718749701976776,
486
+ "logits/chosen": -1.9333007335662842,
487
+ "logits/rejected": 15.193750381469727,
488
+ "logps/chosen": -0.9828125238418579,
489
+ "logps/rejected": -2.859375,
490
+ "loss": 1.0127,
491
+ "nll_loss": 1.0050780773162842,
492
+ "rewards/accuracies": 0.987500011920929,
493
+ "rewards/chosen": -0.04916992038488388,
494
+ "rewards/margins": 0.09389648586511612,
495
+ "rewards/rejected": -0.14296874403953552,
496
+ "step": 270
497
+ },
498
+ {
499
+ "epoch": 0.36129032258064514,
500
+ "grad_norm": 9.860473824781176,
501
+ "learning_rate": 5.986843400892497e-07,
502
+ "log_odds_chosen": 2.4124999046325684,
503
+ "log_odds_ratio": -0.14082030951976776,
504
+ "logits/chosen": -1.830078125,
505
+ "logits/rejected": 15.375,
506
+ "logps/chosen": -1.0496094226837158,
507
+ "logps/rejected": -3.0687499046325684,
508
+ "loss": 1.0598,
509
+ "nll_loss": 1.052734375,
510
+ "rewards/accuracies": 0.981249988079071,
511
+ "rewards/chosen": -0.052490234375,
512
+ "rewards/margins": 0.10092773288488388,
513
+ "rewards/rejected": -0.15341797471046448,
514
+ "step": 280
515
+ },
516
+ {
517
+ "epoch": 0.3741935483870968,
518
+ "grad_norm": 8.838888576042063,
519
+ "learning_rate": 5.88235294117647e-07,
520
+ "log_odds_chosen": 2.3218750953674316,
521
+ "log_odds_ratio": -0.147216796875,
522
+ "logits/chosen": -1.9469726085662842,
523
+ "logits/rejected": 15.693750381469727,
524
+ "logps/chosen": -1.009765625,
525
+ "logps/rejected": -2.9281249046325684,
526
+ "loss": 1.0247,
527
+ "nll_loss": 1.017578125,
528
+ "rewards/accuracies": 0.981249988079071,
529
+ "rewards/chosen": -0.05043945461511612,
530
+ "rewards/margins": 0.095947265625,
531
+ "rewards/rejected": -0.146484375,
532
+ "step": 290
533
+ },
534
+ {
535
+ "epoch": 0.3870967741935484,
536
+ "grad_norm": 12.157936385517715,
537
+ "learning_rate": 5.783149319662401e-07,
538
+ "log_odds_chosen": 2.682812452316284,
539
+ "log_odds_ratio": -0.14907225966453552,
540
+ "logits/chosen": -2.0484375953674316,
541
+ "logits/rejected": 15.512499809265137,
542
+ "logps/chosen": -1.0363280773162842,
543
+ "logps/rejected": -3.328125,
544
+ "loss": 1.0538,
545
+ "nll_loss": 1.046484351158142,
546
+ "rewards/accuracies": 0.9437500238418579,
547
+ "rewards/chosen": -0.05185546725988388,
548
+ "rewards/margins": 0.11459960788488388,
549
+ "rewards/rejected": -0.16640624403953552,
550
+ "step": 300
551
+ },
552
+ {
553
+ "epoch": 0.4,
554
+ "grad_norm": 10.167650321260759,
555
+ "learning_rate": 5.688801239885743e-07,
556
+ "log_odds_chosen": 2.581249952316284,
557
+ "log_odds_ratio": -0.1533203125,
558
+ "logits/chosen": -1.969140648841858,
559
+ "logits/rejected": 15.0,
560
+ "logps/chosen": -1.002343773841858,
561
+ "logps/rejected": -3.1875,
562
+ "loss": 1.0266,
563
+ "nll_loss": 1.0183594226837158,
564
+ "rewards/accuracies": 0.9624999761581421,
565
+ "rewards/chosen": -0.05014648288488388,
566
+ "rewards/margins": 0.109375,
567
+ "rewards/rejected": -0.15952149033546448,
568
+ "step": 310
569
+ },
570
+ {
571
+ "epoch": 0.4129032258064516,
572
+ "grad_norm": 9.820983475120558,
573
+ "learning_rate": 5.598925109558543e-07,
574
+ "log_odds_chosen": 2.5757813453674316,
575
+ "log_odds_ratio": -0.15253905951976776,
576
+ "logits/chosen": -1.750390648841858,
577
+ "logits/rejected": 15.574999809265137,
578
+ "logps/chosen": -1.009374976158142,
579
+ "logps/rejected": -3.1890625953674316,
580
+ "loss": 1.0216,
581
+ "nll_loss": 1.014062523841858,
582
+ "rewards/accuracies": 0.949999988079071,
583
+ "rewards/chosen": -0.05046386644244194,
584
+ "rewards/margins": 0.109130859375,
585
+ "rewards/rejected": -0.15947265923023224,
586
+ "step": 320
587
+ },
588
+ {
589
+ "epoch": 0.4258064516129032,
590
+ "grad_norm": 11.34862116569962,
591
+ "learning_rate": 5.513178464199713e-07,
592
+ "log_odds_chosen": 2.825000047683716,
593
+ "log_odds_ratio": -0.12358398735523224,
594
+ "logits/chosen": -2.0824217796325684,
595
+ "logits/rejected": 15.606249809265137,
596
+ "logps/chosen": -1.0320312976837158,
597
+ "logps/rejected": -3.4468750953674316,
598
+ "loss": 1.0659,
599
+ "nll_loss": 1.060546875,
600
+ "rewards/accuracies": 0.987500011920929,
601
+ "rewards/chosen": -0.05158691480755806,
602
+ "rewards/margins": 0.12075195461511612,
603
+ "rewards/rejected": -0.17236328125,
604
+ "step": 330
605
+ },
606
+ {
607
+ "epoch": 0.43870967741935485,
608
+ "grad_norm": 10.251022653605174,
609
+ "learning_rate": 5.431254465935684e-07,
610
+ "log_odds_chosen": 2.8125,
611
+ "log_odds_ratio": -0.12094726413488388,
612
+ "logits/chosen": -1.5583007335662842,
613
+ "logits/rejected": 15.456250190734863,
614
+ "logps/chosen": -1.0437500476837158,
615
+ "logps/rejected": -3.4546875953674316,
616
+ "loss": 1.0422,
617
+ "nll_loss": 1.036718726158142,
618
+ "rewards/accuracies": 0.987500011920929,
619
+ "rewards/chosen": -0.05217285081744194,
620
+ "rewards/margins": 0.12075195461511612,
621
+ "rewards/rejected": -0.1728515625,
622
+ "step": 340
623
+ },
624
+ {
625
+ "epoch": 0.45161290322580644,
626
+ "grad_norm": 11.248413371201321,
627
+ "learning_rate": 5.352877275721892e-07,
628
+ "log_odds_chosen": 2.9156250953674316,
629
+ "log_odds_ratio": -0.119384765625,
630
+ "logits/chosen": -2.2730469703674316,
631
+ "logits/rejected": 15.3125,
632
+ "logps/chosen": -0.9921875,
633
+ "logps/rejected": -3.4781250953674316,
634
+ "loss": 1.021,
635
+ "nll_loss": 1.0148437023162842,
636
+ "rewards/accuracies": 0.9937499761581421,
637
+ "rewards/chosen": -0.04951171949505806,
638
+ "rewards/margins": 0.12446288764476776,
639
+ "rewards/rejected": -0.173828125,
640
+ "step": 350
641
+ },
642
+ {
643
+ "epoch": 0.4645161290322581,
644
+ "grad_norm": 10.421624014672119,
645
+ "learning_rate": 5.277798139692595e-07,
646
+ "log_odds_chosen": 2.9437499046325684,
647
+ "log_odds_ratio": -0.12277831882238388,
648
+ "logits/chosen": -2.1968750953674316,
649
+ "logits/rejected": 15.387499809265137,
650
+ "logps/chosen": -1.01953125,
651
+ "logps/rejected": -3.549999952316284,
652
+ "loss": 1.0334,
653
+ "nll_loss": 1.027734398841858,
654
+ "rewards/accuracies": 0.96875,
655
+ "rewards/chosen": -0.05095214769244194,
656
+ "rewards/margins": 0.12651367485523224,
657
+ "rewards/rejected": -0.17753906548023224,
658
+ "step": 360
659
+ },
660
+ {
661
+ "epoch": 0.4774193548387097,
662
+ "grad_norm": 19.501158423107107,
663
+ "learning_rate": 5.205792062953535e-07,
664
+ "log_odds_chosen": 2.8828125,
665
+ "log_odds_ratio": -0.13864746689796448,
666
+ "logits/chosen": -2.21875,
667
+ "logits/rejected": 15.75,
668
+ "logps/chosen": -1.0207030773162842,
669
+ "logps/rejected": -3.5015625953674316,
670
+ "loss": 1.0347,
671
+ "nll_loss": 1.027734398841858,
672
+ "rewards/accuracies": 0.956250011920929,
673
+ "rewards/chosen": -0.051025390625,
674
+ "rewards/margins": 0.12412109225988388,
675
+ "rewards/rejected": -0.1748046875,
676
+ "step": 370
677
+ },
678
+ {
679
+ "epoch": 0.49032258064516127,
680
+ "grad_norm": 8.603683531871,
681
+ "learning_rate": 5.136654969375141e-07,
682
+ "log_odds_chosen": 2.2718749046325684,
683
+ "log_odds_ratio": -0.16552734375,
684
+ "logits/chosen": -2.2125000953674316,
685
+ "logits/rejected": 15.449999809265137,
686
+ "logps/chosen": -0.991015613079071,
687
+ "logps/rejected": -2.8671875,
688
+ "loss": 1.0037,
689
+ "nll_loss": 0.9957031011581421,
690
+ "rewards/accuracies": 0.9750000238418579,
691
+ "rewards/chosen": -0.04958496242761612,
692
+ "rewards/margins": 0.09355469048023224,
693
+ "rewards/rejected": -0.14326171576976776,
694
+ "step": 380
695
+ },
696
+ {
697
+ "epoch": 0.5032258064516129,
698
+ "grad_norm": 9.533968967560126,
699
+ "learning_rate": 5.070201265633937e-07,
700
+ "log_odds_chosen": 2.157031297683716,
701
+ "log_odds_ratio": -0.16904297471046448,
702
+ "logits/chosen": -2.240234375,
703
+ "logits/rejected": 15.693750381469727,
704
+ "logps/chosen": -1.003515601158142,
705
+ "logps/rejected": -2.776562452316284,
706
+ "loss": 1.0286,
707
+ "nll_loss": 1.021093726158142,
708
+ "rewards/accuracies": 0.96875,
709
+ "rewards/chosen": -0.05026855319738388,
710
+ "rewards/margins": 0.08857421576976776,
711
+ "rewards/rejected": -0.13896484673023224,
712
+ "step": 390
713
+ },
714
+ {
715
+ "epoch": 0.5161290322580645,
716
+ "grad_norm": 8.931828315275236,
717
+ "learning_rate": 5.006261743217588e-07,
718
+ "log_odds_chosen": 2.06640625,
719
+ "log_odds_ratio": -0.17392578721046448,
720
+ "logits/chosen": -2.532031297683716,
721
+ "logits/rejected": 15.34375,
722
+ "logps/chosen": -0.9996093511581421,
723
+ "logps/rejected": -2.676562547683716,
724
+ "loss": 1.0219,
725
+ "nll_loss": 1.0128905773162842,
726
+ "rewards/accuracies": 0.96875,
727
+ "rewards/chosen": -0.0499267578125,
728
+ "rewards/margins": 0.08383788913488388,
729
+ "rewards/rejected": -0.13388672471046448,
730
+ "step": 400
731
+ },
732
+ {
733
+ "epoch": 0.5290322580645161,
734
+ "grad_norm": 9.944767871538893,
735
+ "learning_rate": 4.944681764341487e-07,
736
+ "log_odds_chosen": 2.069531202316284,
737
+ "log_odds_ratio": -0.17167969048023224,
738
+ "logits/chosen": -2.1773438453674316,
739
+ "logits/rejected": 15.5,
740
+ "logps/chosen": -0.992968738079071,
741
+ "logps/rejected": -2.6875,
742
+ "loss": 1.013,
743
+ "nll_loss": 1.0046875476837158,
744
+ "rewards/accuracies": 0.96875,
745
+ "rewards/chosen": -0.04965820163488388,
746
+ "rewards/margins": 0.08457031100988388,
747
+ "rewards/rejected": -0.13432617485523224,
748
+ "step": 410
749
+ },
750
+ {
751
+ "epoch": 0.5419354838709678,
752
+ "grad_norm": 10.812894387219792,
753
+ "learning_rate": 4.885319687460315e-07,
754
+ "log_odds_chosen": 2.121875047683716,
755
+ "log_odds_ratio": -0.18027344346046448,
756
+ "logits/chosen": -1.947656273841858,
757
+ "logits/rejected": 15.268750190734863,
758
+ "logps/chosen": -1.026953101158142,
759
+ "logps/rejected": -2.7890625,
760
+ "loss": 1.0427,
761
+ "nll_loss": 1.033203125,
762
+ "rewards/accuracies": 0.9624999761581421,
763
+ "rewards/chosen": -0.05134277418255806,
764
+ "rewards/margins": 0.08793945610523224,
765
+ "rewards/rejected": -0.13925781846046448,
766
+ "step": 420
767
+ },
768
+ {
769
+ "epoch": 0.5548387096774193,
770
+ "grad_norm": 9.98404825724108,
771
+ "learning_rate": 4.828045495852675e-07,
772
+ "log_odds_chosen": 2.229687452316284,
773
+ "log_odds_ratio": -0.1552734375,
774
+ "logits/chosen": -1.334570288658142,
775
+ "logits/rejected": 16.181249618530273,
776
+ "logps/chosen": -1.05078125,
777
+ "logps/rejected": -2.895312547683716,
778
+ "loss": 1.0373,
779
+ "nll_loss": 1.03125,
780
+ "rewards/accuracies": 0.9937499761581421,
781
+ "rewards/chosen": -0.05263672024011612,
782
+ "rewards/margins": 0.09213867038488388,
783
+ "rewards/rejected": -0.14472655951976776,
784
+ "step": 430
785
+ },
786
+ {
787
+ "epoch": 0.567741935483871,
788
+ "grad_norm": 12.00678261128581,
789
+ "learning_rate": 4.772739599033477e-07,
790
+ "log_odds_chosen": 2.2265625,
791
+ "log_odds_ratio": -0.15590819716453552,
792
+ "logits/chosen": -2.212109327316284,
793
+ "logits/rejected": 15.53125,
794
+ "logps/chosen": -1.0226562023162842,
795
+ "logps/rejected": -2.870312452316284,
796
+ "loss": 1.0489,
797
+ "nll_loss": 1.040624976158142,
798
+ "rewards/accuracies": 0.9937499761581421,
799
+ "rewards/chosen": -0.05117187649011612,
800
+ "rewards/margins": 0.09238281100988388,
801
+ "rewards/rejected": -0.14365234971046448,
802
+ "step": 440
803
+ },
804
+ {
805
+ "epoch": 0.5806451612903226,
806
+ "grad_norm": 9.483863861986295,
807
+ "learning_rate": 4.719291781830087e-07,
808
+ "log_odds_chosen": 2.2437500953674316,
809
+ "log_odds_ratio": -0.17988280951976776,
810
+ "logits/chosen": -2.1664061546325684,
811
+ "logits/rejected": 15.199999809265137,
812
+ "logps/chosen": -1.042578101158142,
813
+ "logps/rejected": -2.9124999046325684,
814
+ "loss": 1.066,
815
+ "nll_loss": 1.057031273841858,
816
+ "rewards/accuracies": 0.9437500238418579,
817
+ "rewards/chosen": -0.05205078050494194,
818
+ "rewards/margins": 0.09360351413488388,
819
+ "rewards/rejected": -0.14555664360523224,
820
+ "step": 450
821
+ },
822
+ {
823
+ "epoch": 0.5935483870967742,
824
+ "grad_norm": 10.744804299130992,
825
+ "learning_rate": 4.6676002800933655e-07,
826
+ "log_odds_chosen": 2.6500000953674316,
827
+ "log_odds_ratio": -0.15590819716453552,
828
+ "logits/chosen": -2.111132860183716,
829
+ "logits/rejected": 15.574999809265137,
830
+ "logps/chosen": -0.999218761920929,
831
+ "logps/rejected": -3.2484374046325684,
832
+ "loss": 1.022,
833
+ "nll_loss": 1.0144531726837158,
834
+ "rewards/accuracies": 0.9437500238418579,
835
+ "rewards/chosen": -0.04995117336511612,
836
+ "rewards/margins": 0.11235351860523224,
837
+ "rewards/rejected": -0.16230468451976776,
838
+ "step": 460
839
+ },
840
+ {
841
+ "epoch": 0.6064516129032258,
842
+ "grad_norm": 11.405069443063873,
843
+ "learning_rate": 4.617570965396101e-07,
844
+ "log_odds_chosen": 2.663281202316284,
845
+ "log_odds_ratio": -0.17055663466453552,
846
+ "logits/chosen": -2.385937452316284,
847
+ "logits/rejected": 14.893750190734863,
848
+ "logps/chosen": -1.0441405773162842,
849
+ "logps/rejected": -3.34375,
850
+ "loss": 1.0533,
851
+ "nll_loss": 1.045312523841858,
852
+ "rewards/accuracies": 0.925000011920929,
853
+ "rewards/chosen": -0.05219726637005806,
854
+ "rewards/margins": 0.11518554389476776,
855
+ "rewards/rejected": -0.16733399033546448,
856
+ "step": 470
857
+ },
858
+ {
859
+ "epoch": 0.6193548387096774,
860
+ "grad_norm": 10.056175126015189,
861
+ "learning_rate": 4.5691166238495384e-07,
862
+ "log_odds_chosen": 3.198437452316284,
863
+ "log_odds_ratio": -0.10649414360523224,
864
+ "logits/chosen": -2.434375047683716,
865
+ "logits/rejected": 15.731249809265137,
866
+ "logps/chosen": -0.9496093988418579,
867
+ "logps/rejected": -3.6953125,
868
+ "loss": 0.9738,
869
+ "nll_loss": 0.969531238079071,
870
+ "rewards/accuracies": 0.9750000238418579,
871
+ "rewards/chosen": -0.0474853515625,
872
+ "rewards/margins": 0.137451171875,
873
+ "rewards/rejected": -0.18486328423023224,
874
+ "step": 480
875
+ },
876
+ {
877
+ "epoch": 0.632258064516129,
878
+ "grad_norm": 10.810272399773496,
879
+ "learning_rate": 4.5221563164613456e-07,
880
+ "log_odds_chosen": 3.0218749046325684,
881
+ "log_odds_ratio": -0.10493163764476776,
882
+ "logits/chosen": -2.4688963890075684,
883
+ "logits/rejected": 15.837499618530273,
884
+ "logps/chosen": -1.0398437976837158,
885
+ "logps/rejected": -3.653125047683716,
886
+ "loss": 1.0554,
887
+ "nll_loss": 1.05078125,
888
+ "rewards/accuracies": 0.987500011920929,
889
+ "rewards/chosen": -0.052001953125,
890
+ "rewards/margins": 0.13071289658546448,
891
+ "rewards/rejected": -0.1826171875,
892
+ "step": 490
893
+ },
894
+ {
895
+ "epoch": 0.6451612903225806,
896
+ "grad_norm": 9.48010740121237,
897
+ "learning_rate": 4.4766148103584516e-07,
898
+ "log_odds_chosen": 3.0093750953674316,
899
+ "log_odds_ratio": -0.12412109225988388,
900
+ "logits/chosen": -2.3089842796325684,
901
+ "logits/rejected": 15.3125,
902
+ "logps/chosen": -1.0750000476837158,
903
+ "logps/rejected": -3.6812500953674316,
904
+ "loss": 1.0706,
905
+ "nll_loss": 1.0656249523162842,
906
+ "rewards/accuracies": 0.9750000238418579,
907
+ "rewards/chosen": -0.05378418043255806,
908
+ "rewards/margins": 0.13037109375,
909
+ "rewards/rejected": -0.18417969346046448,
910
+ "step": 500
911
+ },
912
+ {
913
+ "epoch": 0.6580645161290323,
914
+ "grad_norm": 10.022112996932664,
915
+ "learning_rate": 4.4324220717793627e-07,
916
+ "log_odds_chosen": 3.206249952316284,
917
+ "log_odds_ratio": -0.10196533054113388,
918
+ "logits/chosen": -2.4449219703674316,
919
+ "logits/rejected": 15.199999809265137,
920
+ "logps/chosen": -0.9769531488418579,
921
+ "logps/rejected": -3.7437500953674316,
922
+ "loss": 1.0094,
923
+ "nll_loss": 1.0046875476837158,
924
+ "rewards/accuracies": 0.987500011920929,
925
+ "rewards/chosen": -0.048828125,
926
+ "rewards/margins": 0.13823242485523224,
927
+ "rewards/rejected": -0.18710938096046448,
928
+ "step": 510
929
+ },
930
+ {
931
+ "epoch": 0.6709677419354839,
932
+ "grad_norm": 9.713862092351485,
933
+ "learning_rate": 4.38951281306147e-07,
934
+ "log_odds_chosen": 3.2015624046325684,
935
+ "log_odds_ratio": -0.09931640326976776,
936
+ "logits/chosen": -2.676562547683716,
937
+ "logits/rejected": 15.506250381469727,
938
+ "logps/chosen": -0.986328125,
939
+ "logps/rejected": -3.746875047683716,
940
+ "loss": 1.0009,
941
+ "nll_loss": 0.99609375,
942
+ "rewards/accuracies": 0.9937499761581421,
943
+ "rewards/chosen": -0.04926757887005806,
944
+ "rewards/margins": 0.13789062201976776,
945
+ "rewards/rejected": -0.18710938096046448,
946
+ "step": 520
947
+ },
948
+ {
949
+ "epoch": 0.6838709677419355,
950
+ "grad_norm": 9.894690348315464,
951
+ "learning_rate": 4.347826086956522e-07,
952
+ "log_odds_chosen": 2.989062547683716,
953
+ "log_odds_ratio": -0.118896484375,
954
+ "logits/chosen": -1.4220702648162842,
955
+ "logits/rejected": 15.09375,
956
+ "logps/chosen": -0.969531238079071,
957
+ "logps/rejected": -3.5234375,
958
+ "loss": 0.9935,
959
+ "nll_loss": 0.9878906011581421,
960
+ "rewards/accuracies": 0.981249988079071,
961
+ "rewards/chosen": -0.0484619140625,
962
+ "rewards/margins": 0.12758788466453552,
963
+ "rewards/rejected": -0.17617186903953552,
964
+ "step": 530
965
+ },
966
+ {
967
+ "epoch": 0.6967741935483871,
968
+ "grad_norm": 9.470806668661435,
969
+ "learning_rate": 4.3073049225394797e-07,
970
+ "log_odds_chosen": 3.059375047683716,
971
+ "log_odds_ratio": -0.13020019233226776,
972
+ "logits/chosen": -1.7101562023162842,
973
+ "logits/rejected": 15.993749618530273,
974
+ "logps/chosen": -1.0402343273162842,
975
+ "logps/rejected": -3.660937547683716,
976
+ "loss": 1.0107,
977
+ "nll_loss": 1.0046875476837158,
978
+ "rewards/accuracies": 0.987500011920929,
979
+ "rewards/chosen": -0.052001953125,
980
+ "rewards/margins": 0.13105468451976776,
981
+ "rewards/rejected": -0.18300780653953552,
982
+ "step": 540
983
+ },
984
+ {
985
+ "epoch": 0.7096774193548387,
986
+ "grad_norm": 10.844114526302421,
987
+ "learning_rate": 4.267895997763199e-07,
988
+ "log_odds_chosen": 2.995312452316284,
989
+ "log_odds_ratio": -0.10224609076976776,
990
+ "logits/chosen": -2.097851514816284,
991
+ "logits/rejected": 15.506250381469727,
992
+ "logps/chosen": -1.019140601158142,
993
+ "logps/rejected": -3.598437547683716,
994
+ "loss": 1.0239,
995
+ "nll_loss": 1.01953125,
996
+ "rewards/accuracies": 0.987500011920929,
997
+ "rewards/chosen": -0.051025390625,
998
+ "rewards/margins": 0.12875977158546448,
999
+ "rewards/rejected": -0.17988280951976776,
1000
+ "step": 550
1001
+ },
1002
+ {
1003
+ "epoch": 0.7225806451612903,
1004
+ "grad_norm": 9.279679191290775,
1005
+ "learning_rate": 4.2295493443781356e-07,
1006
+ "log_odds_chosen": 3.0015625953674316,
1007
+ "log_odds_ratio": -0.1204833984375,
1008
+ "logits/chosen": -2.2398438453674316,
1009
+ "logits/rejected": 15.393750190734863,
1010
+ "logps/chosen": -1.012109398841858,
1011
+ "logps/rejected": -3.606250047683716,
1012
+ "loss": 1.0322,
1013
+ "nll_loss": 1.0265624523162842,
1014
+ "rewards/accuracies": 0.96875,
1015
+ "rewards/chosen": -0.05061035230755806,
1016
+ "rewards/margins": 0.12968750298023224,
1017
+ "rewards/rejected": -0.18017578125,
1018
+ "step": 560
1019
+ },
1020
+ {
1021
+ "epoch": 0.7354838709677419,
1022
+ "grad_norm": 8.805051898638501,
1023
+ "learning_rate": 4.192218081503185e-07,
1024
+ "log_odds_chosen": 3.2109375,
1025
+ "log_odds_ratio": -0.10671386867761612,
1026
+ "logits/chosen": -2.34765625,
1027
+ "logits/rejected": 15.481249809265137,
1028
+ "logps/chosen": -0.9730468988418579,
1029
+ "logps/rejected": -3.7515625953674316,
1030
+ "loss": 0.9964,
1031
+ "nll_loss": 0.9906250238418579,
1032
+ "rewards/accuracies": 0.9937499761581421,
1033
+ "rewards/chosen": -0.04865722730755806,
1034
+ "rewards/margins": 0.13886718451976776,
1035
+ "rewards/rejected": -0.1875,
1036
+ "step": 570
1037
+ },
1038
+ {
1039
+ "epoch": 0.7483870967741936,
1040
+ "grad_norm": 9.93334719820595,
1041
+ "learning_rate": 4.1558581746169135e-07,
1042
+ "log_odds_chosen": 3.2046875953674316,
1043
+ "log_odds_ratio": -0.10039062798023224,
1044
+ "logits/chosen": -2.58203125,
1045
+ "logits/rejected": 14.84375,
1046
+ "logps/chosen": -0.953906238079071,
1047
+ "logps/rejected": -3.706249952316284,
1048
+ "loss": 0.9811,
1049
+ "nll_loss": 0.9765625,
1050
+ "rewards/accuracies": 0.981249988079071,
1051
+ "rewards/chosen": -0.04770507663488388,
1052
+ "rewards/margins": 0.13764648139476776,
1053
+ "rewards/rejected": -0.18525390326976776,
1054
+ "step": 580
1055
+ },
1056
+ {
1057
+ "epoch": 0.7612903225806451,
1058
+ "grad_norm": 9.994090818032287,
1059
+ "learning_rate": 4.1204282171516457e-07,
1060
+ "log_odds_chosen": 3.4124999046325684,
1061
+ "log_odds_ratio": -0.09580077975988388,
1062
+ "logits/chosen": -2.7906250953674316,
1063
+ "logits/rejected": 15.1875,
1064
+ "logps/chosen": -0.958984375,
1065
+ "logps/rejected": -3.918750047683716,
1066
+ "loss": 0.99,
1067
+ "nll_loss": 0.984375,
1068
+ "rewards/accuracies": 0.981249988079071,
1069
+ "rewards/chosen": -0.04792480543255806,
1070
+ "rewards/margins": 0.14799804985523224,
1071
+ "rewards/rejected": -0.19599609076976776,
1072
+ "step": 590
1073
+ },
1074
+ {
1075
+ "epoch": 0.7741935483870968,
1076
+ "grad_norm": 11.079217088405928,
1077
+ "learning_rate": 4.085889232227184e-07,
1078
+ "log_odds_chosen": 3.4984374046325684,
1079
+ "log_odds_ratio": -0.09406737983226776,
1080
+ "logits/chosen": -2.1612181663513184,
1081
+ "logits/rejected": 15.524999618530273,
1082
+ "logps/chosen": -1.00390625,
1083
+ "logps/rejected": -4.074999809265137,
1084
+ "loss": 1.0228,
1085
+ "nll_loss": 1.0187499523162842,
1086
+ "rewards/accuracies": 0.9937499761581421,
1087
+ "rewards/chosen": -0.0501708984375,
1088
+ "rewards/margins": 0.15341797471046448,
1089
+ "rewards/rejected": -0.20361328125,
1090
+ "step": 600
1091
+ },
1092
+ {
1093
+ "epoch": 0.7870967741935484,
1094
+ "grad_norm": 9.702803147701095,
1095
+ "learning_rate": 4.052204492365539e-07,
1096
+ "log_odds_chosen": 3.8734374046325684,
1097
+ "log_odds_ratio": -0.08826903998851776,
1098
+ "logits/chosen": -3.1421875953674316,
1099
+ "logits/rejected": 15.375,
1100
+ "logps/chosen": -1.007421851158142,
1101
+ "logps/rejected": -4.440625190734863,
1102
+ "loss": 1.0284,
1103
+ "nll_loss": 1.0242187976837158,
1104
+ "rewards/accuracies": 0.9750000238418579,
1105
+ "rewards/chosen": -0.05036621168255806,
1106
+ "rewards/margins": 0.17158202826976776,
1107
+ "rewards/rejected": -0.22197265923023224,
1108
+ "step": 610
1109
+ },
1110
+ {
1111
+ "epoch": 0.8,
1112
+ "grad_norm": 10.811873212530353,
1113
+ "learning_rate": 4.0193393552907036e-07,
1114
+ "log_odds_chosen": 3.629687547683716,
1115
+ "log_odds_ratio": -0.10126952826976776,
1116
+ "logits/chosen": -2.7289061546325684,
1117
+ "logits/rejected": 15.725000381469727,
1118
+ "logps/chosen": -0.98828125,
1119
+ "logps/rejected": -4.173437595367432,
1120
+ "loss": 1.01,
1121
+ "nll_loss": 1.0050780773162842,
1122
+ "rewards/accuracies": 0.981249988079071,
1123
+ "rewards/chosen": -0.0494384765625,
1124
+ "rewards/margins": 0.1591796875,
1125
+ "rewards/rejected": -0.20878906548023224,
1126
+ "step": 620
1127
+ },
1128
+ {
1129
+ "epoch": 0.8129032258064516,
1130
+ "grad_norm": 10.459419740251699,
1131
+ "learning_rate": 3.9872611141445e-07,
1132
+ "log_odds_chosen": 3.4937500953674316,
1133
+ "log_odds_ratio": -0.09774170070886612,
1134
+ "logits/chosen": -2.5296874046325684,
1135
+ "logits/rejected": 15.631250381469727,
1136
+ "logps/chosen": -0.962890625,
1137
+ "logps/rejected": -4.003125190734863,
1138
+ "loss": 0.974,
1139
+ "nll_loss": 0.969921886920929,
1140
+ "rewards/accuracies": 0.9937499761581421,
1141
+ "rewards/chosen": -0.04814453050494194,
1142
+ "rewards/margins": 0.15214844048023224,
1143
+ "rewards/rejected": -0.20029297471046448,
1144
+ "step": 630
1145
+ },
1146
+ {
1147
+ "epoch": 0.8258064516129032,
1148
+ "grad_norm": 12.748029660157858,
1149
+ "learning_rate": 3.9559388606461773e-07,
1150
+ "log_odds_chosen": 3.698437452316284,
1151
+ "log_odds_ratio": -0.09205321967601776,
1152
+ "logits/chosen": -2.2269530296325684,
1153
+ "logits/rejected": 15.681249618530273,
1154
+ "logps/chosen": -1.023828148841858,
1155
+ "logps/rejected": -4.284375190734863,
1156
+ "loss": 1.027,
1157
+ "nll_loss": 1.021875023841858,
1158
+ "rewards/accuracies": 0.9937499761581421,
1159
+ "rewards/chosen": -0.05117187649011612,
1160
+ "rewards/margins": 0.16279296576976776,
1161
+ "rewards/rejected": -0.21425780653953552,
1162
+ "step": 640
1163
+ },
1164
+ {
1165
+ "epoch": 0.8387096774193549,
1166
+ "grad_norm": 9.924737194605854,
1167
+ "learning_rate": 3.9253433598942976e-07,
1168
+ "log_odds_chosen": 4.120312690734863,
1169
+ "log_odds_ratio": -0.0667724609375,
1170
+ "logits/chosen": -2.40234375,
1171
+ "logits/rejected": 16.231250762939453,
1172
+ "logps/chosen": -1.015234351158142,
1173
+ "logps/rejected": -4.693749904632568,
1174
+ "loss": 1.0354,
1175
+ "nll_loss": 1.032812476158142,
1176
+ "rewards/accuracies": 0.981249988079071,
1177
+ "rewards/chosen": -0.05078125,
1178
+ "rewards/margins": 0.18388672173023224,
1179
+ "rewards/rejected": -0.23457030951976776,
1180
+ "step": 650
1181
+ },
1182
+ {
1183
+ "epoch": 0.8516129032258064,
1184
+ "grad_norm": 10.136817544950782,
1185
+ "learning_rate": 3.8954469356580987e-07,
1186
+ "log_odds_chosen": 3.762500047683716,
1187
+ "log_odds_ratio": -0.09760741889476776,
1188
+ "logits/chosen": -1.853124976158142,
1189
+ "logits/rejected": 15.581250190734863,
1190
+ "logps/chosen": -1.0246093273162842,
1191
+ "logps/rejected": -4.365624904632568,
1192
+ "loss": 1.0292,
1193
+ "nll_loss": 1.0242187976837158,
1194
+ "rewards/accuracies": 0.9750000238418579,
1195
+ "rewards/chosen": -0.05126953125,
1196
+ "rewards/margins": 0.16679687798023224,
1197
+ "rewards/rejected": -0.21816405653953552,
1198
+ "step": 660
1199
+ },
1200
+ {
1201
+ "epoch": 0.864516129032258,
1202
+ "grad_norm": 9.124030966145908,
1203
+ "learning_rate": 3.866223365135295e-07,
1204
+ "log_odds_chosen": 3.878124952316284,
1205
+ "log_odds_ratio": -0.07924804836511612,
1206
+ "logits/chosen": -2.537109375,
1207
+ "logits/rejected": 15.449999809265137,
1208
+ "logps/chosen": -0.9976562261581421,
1209
+ "logps/rejected": -4.432812690734863,
1210
+ "loss": 1.016,
1211
+ "nll_loss": 1.0125000476837158,
1212
+ "rewards/accuracies": 0.987500011920929,
1213
+ "rewards/chosen": -0.0499267578125,
1214
+ "rewards/margins": 0.17128905653953552,
1215
+ "rewards/rejected": -0.22119140625,
1216
+ "step": 670
1217
+ },
1218
+ {
1219
+ "epoch": 0.8774193548387097,
1220
+ "grad_norm": 10.68555701756856,
1221
+ "learning_rate": 3.837647782266681e-07,
1222
+ "log_odds_chosen": 4.125,
1223
+ "log_odds_ratio": -0.06992187350988388,
1224
+ "logits/chosen": -2.118359327316284,
1225
+ "logits/rejected": 15.600000381469727,
1226
+ "logps/chosen": -1.0496094226837158,
1227
+ "logps/rejected": -4.748437404632568,
1228
+ "loss": 1.0451,
1229
+ "nll_loss": 1.042578101158142,
1230
+ "rewards/accuracies": 0.9937499761581421,
1231
+ "rewards/chosen": -0.05253906175494194,
1232
+ "rewards/margins": 0.18476562201976776,
1233
+ "rewards/rejected": -0.23710937798023224,
1234
+ "step": 680
1235
+ },
1236
+ {
1237
+ "epoch": 0.8903225806451613,
1238
+ "grad_norm": 10.483078834555872,
1239
+ "learning_rate": 3.809696588797297e-07,
1240
+ "log_odds_chosen": 3.8343749046325684,
1241
+ "log_odds_ratio": -0.09882812201976776,
1242
+ "logits/chosen": -2.076171875,
1243
+ "logits/rejected": 15.225000381469727,
1244
+ "logps/chosen": -1.02734375,
1245
+ "logps/rejected": -4.409375190734863,
1246
+ "loss": 1.0054,
1247
+ "nll_loss": 1.000390648841858,
1248
+ "rewards/accuracies": 0.9750000238418579,
1249
+ "rewards/chosen": -0.0513916015625,
1250
+ "rewards/margins": 0.1689453125,
1251
+ "rewards/rejected": -0.22041015326976776,
1252
+ "step": 690
1253
+ },
1254
+ {
1255
+ "epoch": 0.9032258064516129,
1256
+ "grad_norm": 9.997428329910527,
1257
+ "learning_rate": 3.782347372361169e-07,
1258
+ "log_odds_chosen": 3.4671874046325684,
1259
+ "log_odds_ratio": -0.09860839694738388,
1260
+ "logits/chosen": -2.198437452316284,
1261
+ "logits/rejected": 15.387499809265137,
1262
+ "logps/chosen": -0.958984375,
1263
+ "logps/rejected": -3.9781250953674316,
1264
+ "loss": 0.978,
1265
+ "nll_loss": 0.9730468988418579,
1266
+ "rewards/accuracies": 0.981249988079071,
1267
+ "rewards/chosen": -0.0479736328125,
1268
+ "rewards/margins": 0.15107421576976776,
1269
+ "rewards/rejected": -0.19902344048023224,
1270
+ "step": 700
1271
+ },
1272
+ {
1273
+ "epoch": 0.9161290322580645,
1274
+ "grad_norm": 10.274238841741218,
1275
+ "learning_rate": 3.7555788309433984e-07,
1276
+ "log_odds_chosen": 3.706249952316284,
1277
+ "log_odds_ratio": -0.09814453125,
1278
+ "logits/chosen": -2.5234375,
1279
+ "logits/rejected": 15.337499618530273,
1280
+ "logps/chosen": -0.9921875,
1281
+ "logps/rejected": -4.264062404632568,
1282
+ "loss": 1.0152,
1283
+ "nll_loss": 1.010156273841858,
1284
+ "rewards/accuracies": 0.9750000238418579,
1285
+ "rewards/chosen": -0.04960937425494194,
1286
+ "rewards/margins": 0.16367188096046448,
1287
+ "rewards/rejected": -0.21308593451976776,
1288
+ "step": 710
1289
+ },
1290
+ {
1291
+ "epoch": 0.9290322580645162,
1292
+ "grad_norm": 9.173321971857236,
1293
+ "learning_rate": 3.7293707031410074e-07,
1294
+ "log_odds_chosen": 3.9749999046325684,
1295
+ "log_odds_ratio": -0.06779785454273224,
1296
+ "logits/chosen": -2.144335985183716,
1297
+ "logits/rejected": 15.53125,
1298
+ "logps/chosen": -0.969921886920929,
1299
+ "logps/rejected": -4.487500190734863,
1300
+ "loss": 0.9937,
1301
+ "nll_loss": 0.991015613079071,
1302
+ "rewards/accuracies": 1.0,
1303
+ "rewards/chosen": -0.04851074144244194,
1304
+ "rewards/margins": 0.17558594048023224,
1305
+ "rewards/rejected": -0.22402343153953552,
1306
+ "step": 720
1307
+ },
1308
+ {
1309
+ "epoch": 0.9419354838709677,
1310
+ "grad_norm": 31.72522099709603,
1311
+ "learning_rate": 3.703703703703703e-07,
1312
+ "log_odds_chosen": 3.6703124046325684,
1313
+ "log_odds_ratio": -0.08078613132238388,
1314
+ "logits/chosen": -2.496875047683716,
1315
+ "logits/rejected": 15.306249618530273,
1316
+ "logps/chosen": -0.992968738079071,
1317
+ "logps/rejected": -4.214062690734863,
1318
+ "loss": 1.014,
1319
+ "nll_loss": 1.0109374523162842,
1320
+ "rewards/accuracies": 0.9937499761581421,
1321
+ "rewards/chosen": -0.04963378980755806,
1322
+ "rewards/margins": 0.16123047471046448,
1323
+ "rewards/rejected": -0.21074219048023224,
1324
+ "step": 730
1325
+ },
1326
+ {
1327
+ "epoch": 0.9548387096774194,
1328
+ "grad_norm": 9.448597760801611,
1329
+ "learning_rate": 3.678559463888548e-07,
1330
+ "log_odds_chosen": 3.559375047683716,
1331
+ "log_odds_ratio": -0.09282226860523224,
1332
+ "logits/chosen": -2.79150390625,
1333
+ "logits/rejected": 14.893750190734863,
1334
+ "logps/chosen": -0.971484363079071,
1335
+ "logps/rejected": -4.078125,
1336
+ "loss": 0.9695,
1337
+ "nll_loss": 0.9644531011581421,
1338
+ "rewards/accuracies": 0.981249988079071,
1339
+ "rewards/chosen": -0.04853515699505806,
1340
+ "rewards/margins": 0.15537109971046448,
1341
+ "rewards/rejected": -0.20390625298023224,
1342
+ "step": 740
1343
+ },
1344
+ {
1345
+ "epoch": 0.967741935483871,
1346
+ "grad_norm": 10.254613043765856,
1347
+ "learning_rate": 3.653920476209348e-07,
1348
+ "log_odds_chosen": 3.862499952316284,
1349
+ "log_odds_ratio": -0.0780029296875,
1350
+ "logits/chosen": -2.54296875,
1351
+ "logits/rejected": 15.556249618530273,
1352
+ "logps/chosen": -1.001562476158142,
1353
+ "logps/rejected": -4.418749809265137,
1354
+ "loss": 1.025,
1355
+ "nll_loss": 1.021093726158142,
1356
+ "rewards/accuracies": 0.981249988079071,
1357
+ "rewards/chosen": -0.05002441257238388,
1358
+ "rewards/margins": 0.17041015625,
1359
+ "rewards/rejected": -0.220703125,
1360
+ "step": 750
1361
+ },
1362
+ {
1363
+ "epoch": 0.9806451612903225,
1364
+ "grad_norm": 10.120227212074116,
1365
+ "learning_rate": 3.629770043203138e-07,
1366
+ "log_odds_chosen": 3.5078125,
1367
+ "log_odds_ratio": -0.11138916015625,
1368
+ "logits/chosen": -2.26953125,
1369
+ "logits/rejected": 15.324999809265137,
1370
+ "logps/chosen": -0.989062488079071,
1371
+ "logps/rejected": -4.064062595367432,
1372
+ "loss": 1.0132,
1373
+ "nll_loss": 1.008203148841858,
1374
+ "rewards/accuracies": 0.9750000238418579,
1375
+ "rewards/chosen": -0.04946289211511612,
1376
+ "rewards/margins": 0.15390625596046448,
1377
+ "rewards/rejected": -0.20341797173023224,
1378
+ "step": 760
1379
+ },
1380
+ {
1381
+ "epoch": 0.9935483870967742,
1382
+ "grad_norm": 179.52451118961835,
1383
+ "learning_rate": 3.6060922298730937e-07,
1384
+ "log_odds_chosen": 3.7750000953674316,
1385
+ "log_odds_ratio": -0.09243164211511612,
1386
+ "logits/chosen": -2.84375,
1387
+ "logits/rejected": 15.125,
1388
+ "logps/chosen": -0.995312511920929,
1389
+ "logps/rejected": -4.321875095367432,
1390
+ "loss": 1.0145,
1391
+ "nll_loss": 1.0105469226837158,
1392
+ "rewards/accuracies": 0.9750000238418579,
1393
+ "rewards/chosen": -0.04975586012005806,
1394
+ "rewards/margins": 0.16650390625,
1395
+ "rewards/rejected": -0.21611328423023224,
1396
+ "step": 770
1397
+ },
1398
+ {
1399
+ "epoch": 1.0,
1400
+ "step": 775,
1401
+ "total_flos": 0.0,
1402
+ "train_loss": 1.0934507308467742,
1403
+ "train_runtime": 1550.1799,
1404
+ "train_samples_per_second": 7.999,
1405
+ "train_steps_per_second": 0.5
1406
+ }
1407
+ ],
1408
+ "logging_steps": 10,
1409
+ "max_steps": 775,
1410
+ "num_input_tokens_seen": 0,
1411
+ "num_train_epochs": 1,
1412
+ "save_steps": 500,
1413
+ "stateful_callbacks": {
1414
+ "TrainerControl": {
1415
+ "args": {
1416
+ "should_epoch_stop": false,
1417
+ "should_evaluate": false,
1418
+ "should_log": false,
1419
+ "should_save": true,
1420
+ "should_training_stop": true
1421
+ },
1422
+ "attributes": {}
1423
+ }
1424
+ },
1425
+ "total_flos": 0.0,
1426
+ "train_batch_size": 2,
1427
+ "trial_name": null,
1428
+ "trial_params": null
1429
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dcff9f10844a49388333a2c7fe23cadc80c65579bcbcb5d2a962c93771cd02d
3
+ size 7032