silviasapora commited on
Commit
3634b98
·
verified ·
1 Parent(s): d827cd8

Model save

Browse files
.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: google/gemma-7b
3
+ library_name: transformers
4
+ model_name: gemma-7b-simpo-basic-5e-5
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - orpo
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for gemma-7b-simpo-basic-5e-5
13
+
14
+ This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b).
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="silviasapora/gemma-7b-simpo-basic-5e-5", 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/silvias/huggingface/runs/pb09p2zt)
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: 0.13.0
38
+ - Transformers: 4.48.1
39
+ - Pytorch: 2.5.1
40
+ - Datasets: 3.2.0
41
+ - Tokenizers: 0.21.0
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 Gallouédec},
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 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-7b",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 256,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 128,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "down_proj",
27
+ "up_proj",
28
+ "k_proj",
29
+ "q_proj",
30
+ "v_proj",
31
+ "gate_proj",
32
+ "o_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c79f4b9170716b1617374bb34c4a99da82a3bc5c38e9cbba344f316b290d61b6
3
+ size 1600180696
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9765925925925925,
3
+ "total_flos": 0.0,
4
+ "train_loss": 95.88784930516803,
5
+ "train_runtime": 8067.9754,
6
+ "train_samples": 6750,
7
+ "train_samples_per_second": 2.51,
8
+ "train_steps_per_second": 0.039
9
+ }
runs/Jan27_19-09-16_b4d476355ce0/events.out.tfevents.1738004968.b4d476355ce0.106708.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2dd7c7ad92d6106818b90bf12d0f418890c77c2972e8b379a1a7c28f93fd190
3
+ size 59656
runs/Jan27_19-09-16_b4d476355ce0/events.out.tfevents.1738004969.b4d476355ce0.106711.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65ad0be62b860b454f8ea83a73173f17932e1f7c87f8a97426ede59747a4d306
3
+ size 59656
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:f559f2189f392b4555613965f089e7c4d300b41fbe080bf79da0d676e33ee7f0
3
+ size 34356041
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json ADDED
@@ -0,0 +1,1758 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
1742
+ "additional_special_tokens": [
1743
+ "<start_of_turn>",
1744
+ "<end_of_turn>"
1745
+ ],
1746
+ "bos_token": "<bos>",
1747
+ "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
1748
+ "clean_up_tokenization_spaces": false,
1749
+ "eos_token": "<eos>",
1750
+ "extra_special_tokens": {},
1751
+ "model_max_length": 2048,
1752
+ "pad_token": "<pad>",
1753
+ "sp_model_kwargs": {},
1754
+ "spaces_between_special_tokens": false,
1755
+ "tokenizer_class": "GemmaTokenizer",
1756
+ "unk_token": "<unk>",
1757
+ "use_default_system_prompt": false
1758
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9765925925925925,
3
+ "total_flos": 0.0,
4
+ "train_loss": 95.88784930516803,
5
+ "train_runtime": 8067.9754,
6
+ "train_samples": 6750,
7
+ "train_samples_per_second": 2.51,
8
+ "train_steps_per_second": 0.039
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9765925925925925,
5
+ "eval_steps": 500,
6
+ "global_step": 315,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.047407407407407405,
13
+ "grad_norm": 1740.1898193359375,
14
+ "learning_rate": 7.8125e-06,
15
+ "log_odds_chosen": -3.2558395862579346,
16
+ "log_odds_ratio": -11.297467231750488,
17
+ "logits/chosen": 151.8887176513672,
18
+ "logits/rejected": 125.08770751953125,
19
+ "logps/chosen": -21.25274658203125,
20
+ "logps/rejected": -17.99789810180664,
21
+ "loss": 957.1256,
22
+ "nll_loss": 9.109880447387695,
23
+ "rewards/accuracies": 0.5062500238418579,
24
+ "rewards/chosen": -2.125274658203125,
25
+ "rewards/margins": -0.32548460364341736,
26
+ "rewards/rejected": -1.7997897863388062,
27
+ "step": 5
28
+ },
29
+ {
30
+ "epoch": 0.09481481481481481,
31
+ "grad_norm": 1201.3779296875,
32
+ "learning_rate": 1.5625e-05,
33
+ "log_odds_chosen": -0.513113796710968,
34
+ "log_odds_ratio": -9.646921157836914,
35
+ "logits/chosen": 151.55584716796875,
36
+ "logits/rejected": 114.66656494140625,
37
+ "logps/chosen": -19.74169158935547,
38
+ "logps/rejected": -19.229528427124023,
39
+ "loss": 899.8229,
40
+ "nll_loss": 8.330388069152832,
41
+ "rewards/accuracies": 0.4000000059604645,
42
+ "rewards/chosen": -1.974169135093689,
43
+ "rewards/margins": -0.05121617391705513,
44
+ "rewards/rejected": -1.9229530096054077,
45
+ "step": 10
46
+ },
47
+ {
48
+ "epoch": 0.14222222222222222,
49
+ "grad_norm": 1059.2998046875,
50
+ "learning_rate": 2.34375e-05,
51
+ "log_odds_chosen": -3.0506296157836914,
52
+ "log_odds_ratio": -12.488919258117676,
53
+ "logits/chosen": 162.9476776123047,
54
+ "logits/rejected": 133.8412628173828,
55
+ "logps/chosen": -23.586645126342773,
56
+ "logps/rejected": -20.534006118774414,
57
+ "loss": 868.7248,
58
+ "nll_loss": 8.015983581542969,
59
+ "rewards/accuracies": 0.45625001192092896,
60
+ "rewards/chosen": -2.3586642742156982,
61
+ "rewards/margins": -0.30526378750801086,
62
+ "rewards/rejected": -2.053400754928589,
63
+ "step": 15
64
+ },
65
+ {
66
+ "epoch": 0.18962962962962962,
67
+ "grad_norm": 5671.9423828125,
68
+ "learning_rate": 3.125e-05,
69
+ "log_odds_chosen": -1.1081632375717163,
70
+ "log_odds_ratio": -5.528253078460693,
71
+ "logits/chosen": 162.40701293945312,
72
+ "logits/rejected": 144.20594787597656,
73
+ "logps/chosen": -11.981878280639648,
74
+ "logps/rejected": -10.876971244812012,
75
+ "loss": 601.0812,
76
+ "nll_loss": 5.25473165512085,
77
+ "rewards/accuracies": 0.4375,
78
+ "rewards/chosen": -1.1981879472732544,
79
+ "rewards/margins": -0.11049075424671173,
80
+ "rewards/rejected": -1.0876972675323486,
81
+ "step": 20
82
+ },
83
+ {
84
+ "epoch": 0.23703703703703705,
85
+ "grad_norm": 361.9310302734375,
86
+ "learning_rate": 3.90625e-05,
87
+ "log_odds_chosen": -0.1702435463666916,
88
+ "log_odds_ratio": -1.2489330768585205,
89
+ "logits/chosen": 171.29396057128906,
90
+ "logits/rejected": 182.26473999023438,
91
+ "logps/chosen": -2.5449886322021484,
92
+ "logps/rejected": -2.3741650581359863,
93
+ "loss": 147.2234,
94
+ "nll_loss": 2.534252166748047,
95
+ "rewards/accuracies": 0.512499988079071,
96
+ "rewards/chosen": -0.2544988691806793,
97
+ "rewards/margins": -0.017082329839468002,
98
+ "rewards/rejected": -0.23741650581359863,
99
+ "step": 25
100
+ },
101
+ {
102
+ "epoch": 0.28444444444444444,
103
+ "grad_norm": 316.0004577636719,
104
+ "learning_rate": 4.6875e-05,
105
+ "log_odds_chosen": -0.06582697480916977,
106
+ "log_odds_ratio": -0.9077370762825012,
107
+ "logits/chosen": 203.27645874023438,
108
+ "logits/rejected": 206.0833282470703,
109
+ "logps/chosen": -1.7753212451934814,
110
+ "logps/rejected": -1.7229360342025757,
111
+ "loss": 97.9589,
112
+ "nll_loss": 2.0022435188293457,
113
+ "rewards/accuracies": 0.48750001192092896,
114
+ "rewards/chosen": -0.1775321513414383,
115
+ "rewards/margins": -0.005238535348325968,
116
+ "rewards/rejected": -0.17229360342025757,
117
+ "step": 30
118
+ },
119
+ {
120
+ "epoch": 0.33185185185185184,
121
+ "grad_norm": 243.56875610351562,
122
+ "learning_rate": 4.998613757348784e-05,
123
+ "log_odds_chosen": 0.24516336619853973,
124
+ "log_odds_ratio": -0.7577110528945923,
125
+ "logits/chosen": 205.0412139892578,
126
+ "logits/rejected": 199.2989959716797,
127
+ "logps/chosen": -1.4802477359771729,
128
+ "logps/rejected": -1.6970373392105103,
129
+ "loss": 88.2151,
130
+ "nll_loss": 1.8365882635116577,
131
+ "rewards/accuracies": 0.518750011920929,
132
+ "rewards/chosen": -0.148024782538414,
133
+ "rewards/margins": 0.021678971126675606,
134
+ "rewards/rejected": -0.16970375180244446,
135
+ "step": 35
136
+ },
137
+ {
138
+ "epoch": 0.37925925925925924,
139
+ "grad_norm": 207.0272674560547,
140
+ "learning_rate": 4.990147841143462e-05,
141
+ "log_odds_chosen": 0.33367791771888733,
142
+ "log_odds_ratio": -0.713233232498169,
143
+ "logits/chosen": 204.61990356445312,
144
+ "logits/rejected": 207.46060180664062,
145
+ "logps/chosen": -1.4064643383026123,
146
+ "logps/rejected": -1.6824305057525635,
147
+ "loss": 79.1586,
148
+ "nll_loss": 1.7922122478485107,
149
+ "rewards/accuracies": 0.6000000238418579,
150
+ "rewards/chosen": -0.14064642786979675,
151
+ "rewards/margins": 0.027596602216362953,
152
+ "rewards/rejected": -0.16824303567409515,
153
+ "step": 40
154
+ },
155
+ {
156
+ "epoch": 0.4266666666666667,
157
+ "grad_norm": 217.22921752929688,
158
+ "learning_rate": 4.97401218720448e-05,
159
+ "log_odds_chosen": 0.22436106204986572,
160
+ "log_odds_ratio": -0.7068377137184143,
161
+ "logits/chosen": 193.02835083007812,
162
+ "logits/rejected": 190.45382690429688,
163
+ "logps/chosen": -1.2889686822891235,
164
+ "logps/rejected": -1.4903218746185303,
165
+ "loss": 73.5881,
166
+ "nll_loss": 1.6512086391448975,
167
+ "rewards/accuracies": 0.581250011920929,
168
+ "rewards/chosen": -0.12889686226844788,
169
+ "rewards/margins": 0.020135333761572838,
170
+ "rewards/rejected": -0.14903220534324646,
171
+ "step": 45
172
+ },
173
+ {
174
+ "epoch": 0.4740740740740741,
175
+ "grad_norm": 263.44036865234375,
176
+ "learning_rate": 4.9502564938797946e-05,
177
+ "log_odds_chosen": 0.2294200211763382,
178
+ "log_odds_ratio": -0.6946156024932861,
179
+ "logits/chosen": 186.02200317382812,
180
+ "logits/rejected": 179.02650451660156,
181
+ "logps/chosen": -1.194486379623413,
182
+ "logps/rejected": -1.3947676420211792,
183
+ "loss": 66.8774,
184
+ "nll_loss": 1.5524386167526245,
185
+ "rewards/accuracies": 0.581250011920929,
186
+ "rewards/chosen": -0.11944863945245743,
187
+ "rewards/margins": 0.020028119906783104,
188
+ "rewards/rejected": -0.13947676122188568,
189
+ "step": 50
190
+ },
191
+ {
192
+ "epoch": 0.5214814814814814,
193
+ "grad_norm": 116.24183654785156,
194
+ "learning_rate": 4.918953929490768e-05,
195
+ "log_odds_chosen": 0.199480801820755,
196
+ "log_odds_ratio": -0.7110514044761658,
197
+ "logits/chosen": 176.92135620117188,
198
+ "logits/rejected": 182.1995086669922,
199
+ "logps/chosen": -1.1935983896255493,
200
+ "logps/rejected": -1.3527660369873047,
201
+ "loss": 67.4109,
202
+ "nll_loss": 1.5539511442184448,
203
+ "rewards/accuracies": 0.5687500238418579,
204
+ "rewards/chosen": -0.11935983598232269,
205
+ "rewards/margins": 0.01591675728559494,
206
+ "rewards/rejected": -0.13527658581733704,
207
+ "step": 55
208
+ },
209
+ {
210
+ "epoch": 0.5688888888888889,
211
+ "grad_norm": 387.7615661621094,
212
+ "learning_rate": 4.88020090697132e-05,
213
+ "log_odds_chosen": 0.20628318190574646,
214
+ "log_odds_ratio": -0.6839777827262878,
215
+ "logits/chosen": 174.76670837402344,
216
+ "logits/rejected": 168.65625,
217
+ "logps/chosen": -1.1928430795669556,
218
+ "logps/rejected": -1.3618948459625244,
219
+ "loss": 67.3674,
220
+ "nll_loss": 1.5756242275238037,
221
+ "rewards/accuracies": 0.5687500238418579,
222
+ "rewards/chosen": -0.11928431689739227,
223
+ "rewards/margins": 0.016905177384614944,
224
+ "rewards/rejected": -0.13618949055671692,
225
+ "step": 60
226
+ },
227
+ {
228
+ "epoch": 0.6162962962962963,
229
+ "grad_norm": 180.0065155029297,
230
+ "learning_rate": 4.834116786912897e-05,
231
+ "log_odds_chosen": 0.24322107434272766,
232
+ "log_odds_ratio": -0.6678293943405151,
233
+ "logits/chosen": 162.81387329101562,
234
+ "logits/rejected": 167.76327514648438,
235
+ "logps/chosen": -1.166547179222107,
236
+ "logps/rejected": -1.3516491651535034,
237
+ "loss": 63.7135,
238
+ "nll_loss": 1.5179404020309448,
239
+ "rewards/accuracies": 0.574999988079071,
240
+ "rewards/chosen": -0.11665471643209457,
241
+ "rewards/margins": 0.018510203808546066,
242
+ "rewards/rejected": -0.13516491651535034,
243
+ "step": 65
244
+ },
245
+ {
246
+ "epoch": 0.6637037037037037,
247
+ "grad_norm": 337.4962158203125,
248
+ "learning_rate": 4.7808435099299045e-05,
249
+ "log_odds_chosen": 0.23248204588890076,
250
+ "log_odds_ratio": -0.6779593229293823,
251
+ "logits/chosen": 164.27587890625,
252
+ "logits/rejected": 164.59402465820312,
253
+ "logps/chosen": -1.0993386507034302,
254
+ "logps/rejected": -1.279801607131958,
255
+ "loss": 62.676,
256
+ "nll_loss": 1.4791990518569946,
257
+ "rewards/accuracies": 0.59375,
258
+ "rewards/chosen": -0.10993386805057526,
259
+ "rewards/margins": 0.018046308308839798,
260
+ "rewards/rejected": -0.12798015773296356,
261
+ "step": 70
262
+ },
263
+ {
264
+ "epoch": 0.7111111111111111,
265
+ "grad_norm": 266.1570129394531,
266
+ "learning_rate": 4.720545159477922e-05,
267
+ "log_odds_chosen": 0.2760678231716156,
268
+ "log_odds_ratio": -0.6774192452430725,
269
+ "logits/chosen": 165.2519989013672,
270
+ "logits/rejected": 175.3682098388672,
271
+ "logps/chosen": -1.0903198719024658,
272
+ "logps/rejected": -1.2979156970977783,
273
+ "loss": 60.5395,
274
+ "nll_loss": 1.5055925846099854,
275
+ "rewards/accuracies": 0.606249988079071,
276
+ "rewards/chosen": -0.10903197526931763,
277
+ "rewards/margins": 0.020759599283337593,
278
+ "rewards/rejected": -0.12979158759117126,
279
+ "step": 75
280
+ },
281
+ {
282
+ "epoch": 0.7585185185185185,
283
+ "grad_norm": 127.31847381591797,
284
+ "learning_rate": 4.653407456471222e-05,
285
+ "log_odds_chosen": 0.14735503494739532,
286
+ "log_odds_ratio": -0.7135955691337585,
287
+ "logits/chosen": 185.9381103515625,
288
+ "logits/rejected": 176.81234741210938,
289
+ "logps/chosen": -1.0871061086654663,
290
+ "logps/rejected": -1.193958044052124,
291
+ "loss": 58.9735,
292
+ "nll_loss": 1.4323160648345947,
293
+ "rewards/accuracies": 0.5,
294
+ "rewards/chosen": -0.1087106242775917,
295
+ "rewards/margins": 0.010685184970498085,
296
+ "rewards/rejected": -0.11939580738544464,
297
+ "step": 80
298
+ },
299
+ {
300
+ "epoch": 0.8059259259259259,
301
+ "grad_norm": 473.7615051269531,
302
+ "learning_rate": 4.579637187256222e-05,
303
+ "log_odds_chosen": 0.10262985527515411,
304
+ "log_odds_ratio": -0.7151901721954346,
305
+ "logits/chosen": 184.52096557617188,
306
+ "logits/rejected": 183.83230590820312,
307
+ "logps/chosen": -1.0544980764389038,
308
+ "logps/rejected": -1.1398108005523682,
309
+ "loss": 59.7409,
310
+ "nll_loss": 1.4580681324005127,
311
+ "rewards/accuracies": 0.5874999761581421,
312
+ "rewards/chosen": -0.10544981062412262,
313
+ "rewards/margins": 0.008531274273991585,
314
+ "rewards/rejected": -0.11398109048604965,
315
+ "step": 85
316
+ },
317
+ {
318
+ "epoch": 0.8533333333333334,
319
+ "grad_norm": 108.44992065429688,
320
+ "learning_rate": 4.499461566702685e-05,
321
+ "log_odds_chosen": 0.18465110659599304,
322
+ "log_odds_ratio": -0.6907774806022644,
323
+ "logits/chosen": 171.22189331054688,
324
+ "logits/rejected": 175.73953247070312,
325
+ "logps/chosen": -1.028497338294983,
326
+ "logps/rejected": -1.1620924472808838,
327
+ "loss": 56.0386,
328
+ "nll_loss": 1.3667221069335938,
329
+ "rewards/accuracies": 0.59375,
330
+ "rewards/chosen": -0.10284973680973053,
331
+ "rewards/margins": 0.01335950382053852,
332
+ "rewards/rejected": -0.1162092462182045,
333
+ "step": 90
334
+ },
335
+ {
336
+ "epoch": 0.9007407407407407,
337
+ "grad_norm": 246.35232543945312,
338
+ "learning_rate": 4.413127538374411e-05,
339
+ "log_odds_chosen": 0.08530735224485397,
340
+ "log_odds_ratio": -0.7315806746482849,
341
+ "logits/chosen": 180.68896484375,
342
+ "logits/rejected": 178.9383544921875,
343
+ "logps/chosen": -1.1185877323150635,
344
+ "logps/rejected": -1.1824891567230225,
345
+ "loss": 59.4866,
346
+ "nll_loss": 1.451053500175476,
347
+ "rewards/accuracies": 0.53125,
348
+ "rewards/chosen": -0.11185877025127411,
349
+ "rewards/margins": 0.006390163209289312,
350
+ "rewards/rejected": -0.11824893951416016,
351
+ "step": 95
352
+ },
353
+ {
354
+ "epoch": 0.9481481481481482,
355
+ "grad_norm": 173.8784942626953,
356
+ "learning_rate": 4.320901013934887e-05,
357
+ "log_odds_chosen": 0.23844632506370544,
358
+ "log_odds_ratio": -0.6666170358657837,
359
+ "logits/chosen": 182.5182647705078,
360
+ "logits/rejected": 184.78826904296875,
361
+ "logps/chosen": -1.0542734861373901,
362
+ "logps/rejected": -1.2187533378601074,
363
+ "loss": 57.2162,
364
+ "nll_loss": 1.3994534015655518,
365
+ "rewards/accuracies": 0.574999988079071,
366
+ "rewards/chosen": -0.10542736202478409,
367
+ "rewards/margins": 0.016447991132736206,
368
+ "rewards/rejected": -0.1218753457069397,
369
+ "step": 100
370
+ },
371
+ {
372
+ "epoch": 0.9955555555555555,
373
+ "grad_norm": 331.2377624511719,
374
+ "learning_rate": 4.223066054130568e-05,
375
+ "log_odds_chosen": 0.24726486206054688,
376
+ "log_odds_ratio": -0.6888165473937988,
377
+ "logits/chosen": 186.27188110351562,
378
+ "logits/rejected": 191.9564971923828,
379
+ "logps/chosen": -1.067476511001587,
380
+ "logps/rejected": -1.2659533023834229,
381
+ "loss": 58.9663,
382
+ "nll_loss": 1.464313268661499,
383
+ "rewards/accuracies": 0.550000011920929,
384
+ "rewards/chosen": -0.10674764961004257,
385
+ "rewards/margins": 0.01984768733382225,
386
+ "rewards/rejected": -0.12659534811973572,
387
+ "step": 105
388
+ },
389
+ {
390
+ "epoch": 1.037925925925926,
391
+ "grad_norm": 260.459228515625,
392
+ "learning_rate": 4.1199239938743797e-05,
393
+ "log_odds_chosen": 0.5561641454696655,
394
+ "log_odds_ratio": -0.5538166761398315,
395
+ "logits/chosen": 185.56787109375,
396
+ "logits/rejected": 184.26124572753906,
397
+ "logps/chosen": -0.8777849078178406,
398
+ "logps/rejected": -1.2192728519439697,
399
+ "loss": 42.6572,
400
+ "nll_loss": 1.2877055406570435,
401
+ "rewards/accuracies": 0.7342657446861267,
402
+ "rewards/chosen": -0.0877784937620163,
403
+ "rewards/margins": 0.034148797392845154,
404
+ "rewards/rejected": -0.12192727625370026,
405
+ "step": 110
406
+ },
407
+ {
408
+ "epoch": 1.0853333333333333,
409
+ "grad_norm": 216.40223693847656,
410
+ "learning_rate": 4.0117925141242174e-05,
411
+ "log_odds_chosen": 0.5818439722061157,
412
+ "log_odds_ratio": -0.5539088249206543,
413
+ "logits/chosen": 165.58583068847656,
414
+ "logits/rejected": 177.4764862060547,
415
+ "logps/chosen": -0.826498806476593,
416
+ "logps/rejected": -1.1634178161621094,
417
+ "loss": 43.4649,
418
+ "nll_loss": 1.2354695796966553,
419
+ "rewards/accuracies": 0.668749988079071,
420
+ "rewards/chosen": -0.08264987170696259,
421
+ "rewards/margins": 0.033691905438899994,
422
+ "rewards/rejected": -0.11634178459644318,
423
+ "step": 115
424
+ },
425
+ {
426
+ "epoch": 1.1327407407407408,
427
+ "grad_norm": 268.2698669433594,
428
+ "learning_rate": 3.899004663415084e-05,
429
+ "log_odds_chosen": 0.5598589181900024,
430
+ "log_odds_ratio": -0.5634177923202515,
431
+ "logits/chosen": 166.57980346679688,
432
+ "logits/rejected": 172.7939910888672,
433
+ "logps/chosen": -0.8440117835998535,
434
+ "logps/rejected": -1.1848386526107788,
435
+ "loss": 45.6121,
436
+ "nll_loss": 1.277220606803894,
437
+ "rewards/accuracies": 0.706250011920929,
438
+ "rewards/chosen": -0.08440117537975311,
439
+ "rewards/margins": 0.03408268839120865,
440
+ "rewards/rejected": -0.11848386377096176,
441
+ "step": 120
442
+ },
443
+ {
444
+ "epoch": 1.1801481481481482,
445
+ "grad_norm": 284.48974609375,
446
+ "learning_rate": 3.781907832058587e-05,
447
+ "log_odds_chosen": 0.624763548374176,
448
+ "log_odds_ratio": -0.5155161619186401,
449
+ "logits/chosen": 173.51644897460938,
450
+ "logits/rejected": 173.76979064941406,
451
+ "logps/chosen": -0.8432798385620117,
452
+ "logps/rejected": -1.2360132932662964,
453
+ "loss": 45.1322,
454
+ "nll_loss": 1.1900274753570557,
455
+ "rewards/accuracies": 0.7562500238418579,
456
+ "rewards/chosen": -0.08432798832654953,
457
+ "rewards/margins": 0.03927333280444145,
458
+ "rewards/rejected": -0.12360131740570068,
459
+ "step": 125
460
+ },
461
+ {
462
+ "epoch": 1.2275555555555555,
463
+ "grad_norm": 87.84806060791016,
464
+ "learning_rate": 3.660862682169282e-05,
465
+ "log_odds_chosen": 0.6305242776870728,
466
+ "log_odds_ratio": -0.5334250330924988,
467
+ "logits/chosen": 171.10394287109375,
468
+ "logits/rejected": 179.3053436279297,
469
+ "logps/chosen": -0.9056023359298706,
470
+ "logps/rejected": -1.2814991474151611,
471
+ "loss": 44.7938,
472
+ "nll_loss": 1.2281415462493896,
473
+ "rewards/accuracies": 0.7124999761581421,
474
+ "rewards/chosen": -0.09056023508310318,
475
+ "rewards/margins": 0.03758968040347099,
476
+ "rewards/rejected": -0.12814991176128387,
477
+ "step": 130
478
+ },
479
+ {
480
+ "epoch": 1.274962962962963,
481
+ "grad_norm": 125.42166137695312,
482
+ "learning_rate": 3.5362420368134356e-05,
483
+ "log_odds_chosen": 0.6436266899108887,
484
+ "log_odds_ratio": -0.50090491771698,
485
+ "logits/chosen": 178.05384826660156,
486
+ "logits/rejected": 175.2784881591797,
487
+ "logps/chosen": -0.757787823677063,
488
+ "logps/rejected": -1.1044118404388428,
489
+ "loss": 42.02,
490
+ "nll_loss": 1.169008493423462,
491
+ "rewards/accuracies": 0.7562500238418579,
492
+ "rewards/chosen": -0.0757787898182869,
493
+ "rewards/margins": 0.0346623957157135,
494
+ "rewards/rejected": -0.1104411855340004,
495
+ "step": 135
496
+ },
497
+ {
498
+ "epoch": 1.3223703703703704,
499
+ "grad_norm": 81.14250946044922,
500
+ "learning_rate": 3.408429731701635e-05,
501
+ "log_odds_chosen": 0.6462007761001587,
502
+ "log_odds_ratio": -0.5447597503662109,
503
+ "logits/chosen": 172.18807983398438,
504
+ "logits/rejected": 175.19412231445312,
505
+ "logps/chosen": -0.8518229722976685,
506
+ "logps/rejected": -1.22883939743042,
507
+ "loss": 44.6455,
508
+ "nll_loss": 1.2209603786468506,
509
+ "rewards/accuracies": 0.7250000238418579,
510
+ "rewards/chosen": -0.0851822942495346,
511
+ "rewards/margins": 0.037701647728681564,
512
+ "rewards/rejected": -0.12288393825292587,
513
+ "step": 140
514
+ },
515
+ {
516
+ "epoch": 1.3697777777777778,
517
+ "grad_norm": 129.7603302001953,
518
+ "learning_rate": 3.2778194329621104e-05,
519
+ "log_odds_chosen": 0.5821535587310791,
520
+ "log_odds_ratio": -0.5562936663627625,
521
+ "logits/chosen": 160.73605346679688,
522
+ "logits/rejected": 165.95870971679688,
523
+ "logps/chosen": -0.8286741375923157,
524
+ "logps/rejected": -1.1823114156723022,
525
+ "loss": 44.5354,
526
+ "nll_loss": 1.2288296222686768,
527
+ "rewards/accuracies": 0.668749988079071,
528
+ "rewards/chosen": -0.08286741375923157,
529
+ "rewards/margins": 0.03536374121904373,
530
+ "rewards/rejected": -0.1182311549782753,
531
+ "step": 145
532
+ },
533
+ {
534
+ "epoch": 1.417185185185185,
535
+ "grad_norm": 160.31822204589844,
536
+ "learning_rate": 3.144813424636031e-05,
537
+ "log_odds_chosen": 0.5738444924354553,
538
+ "log_odds_ratio": -0.5622869729995728,
539
+ "logits/chosen": 161.04830932617188,
540
+ "logits/rejected": 166.18789672851562,
541
+ "logps/chosen": -0.8428765535354614,
542
+ "logps/rejected": -1.2003581523895264,
543
+ "loss": 41.9011,
544
+ "nll_loss": 1.1795659065246582,
545
+ "rewards/accuracies": 0.668749988079071,
546
+ "rewards/chosen": -0.08428765088319778,
547
+ "rewards/margins": 0.03574815019965172,
548
+ "rewards/rejected": -0.12003578990697861,
549
+ "step": 150
550
+ },
551
+ {
552
+ "epoch": 1.4645925925925927,
553
+ "grad_norm": 105.11316680908203,
554
+ "learning_rate": 3.0098213696293542e-05,
555
+ "log_odds_chosen": 0.6681560277938843,
556
+ "log_odds_ratio": -0.5097799897193909,
557
+ "logits/chosen": 166.84762573242188,
558
+ "logits/rejected": 175.52871704101562,
559
+ "logps/chosen": -0.8135679364204407,
560
+ "logps/rejected": -1.2058597803115845,
561
+ "loss": 42.8798,
562
+ "nll_loss": 1.2104473114013672,
563
+ "rewards/accuracies": 0.75,
564
+ "rewards/chosen": -0.08135677874088287,
565
+ "rewards/margins": 0.03922919183969498,
566
+ "rewards/rejected": -0.12058597803115845,
567
+ "step": 155
568
+ },
569
+ {
570
+ "epoch": 1.512,
571
+ "grad_norm": 231.7557830810547,
572
+ "learning_rate": 2.8732590479375165e-05,
573
+ "log_odds_chosen": 0.6469327807426453,
574
+ "log_odds_ratio": -0.5286628007888794,
575
+ "logits/chosen": 168.23556518554688,
576
+ "logits/rejected": 179.05519104003906,
577
+ "logps/chosen": -0.7896637320518494,
578
+ "logps/rejected": -1.1779615879058838,
579
+ "loss": 41.1882,
580
+ "nll_loss": 1.1598231792449951,
581
+ "rewards/accuracies": 0.6875,
582
+ "rewards/chosen": -0.07896637171506882,
583
+ "rewards/margins": 0.03882979229092598,
584
+ "rewards/rejected": -0.1177961602807045,
585
+ "step": 160
586
+ },
587
+ {
588
+ "epoch": 1.5594074074074074,
589
+ "grad_norm": 127.51461791992188,
590
+ "learning_rate": 2.7355470760292956e-05,
591
+ "log_odds_chosen": 0.6626273393630981,
592
+ "log_odds_ratio": -0.517857015132904,
593
+ "logits/chosen": 164.04891967773438,
594
+ "logits/rejected": 170.9124755859375,
595
+ "logps/chosen": -0.7660794854164124,
596
+ "logps/rejected": -1.1452827453613281,
597
+ "loss": 41.7151,
598
+ "nll_loss": 1.1981559991836548,
599
+ "rewards/accuracies": 0.75,
600
+ "rewards/chosen": -0.07660795003175735,
601
+ "rewards/margins": 0.03792034834623337,
602
+ "rewards/rejected": -0.11452829837799072,
603
+ "step": 165
604
+ },
605
+ {
606
+ "epoch": 1.6068148148148147,
607
+ "grad_norm": 201.5820770263672,
608
+ "learning_rate": 2.597109611334169e-05,
609
+ "log_odds_chosen": 0.6843355298042297,
610
+ "log_odds_ratio": -0.486748605966568,
611
+ "logits/chosen": 167.65890502929688,
612
+ "logits/rejected": 177.57144165039062,
613
+ "logps/chosen": -0.7862690687179565,
614
+ "logps/rejected": -1.2108625173568726,
615
+ "loss": 41.7587,
616
+ "nll_loss": 1.2069928646087646,
617
+ "rewards/accuracies": 0.762499988079071,
618
+ "rewards/chosen": -0.07862690836191177,
619
+ "rewards/margins": 0.04245934635400772,
620
+ "rewards/rejected": -0.1210862547159195,
621
+ "step": 170
622
+ },
623
+ {
624
+ "epoch": 1.6542222222222223,
625
+ "grad_norm": 115.46862030029297,
626
+ "learning_rate": 2.458373045823404e-05,
627
+ "log_odds_chosen": 0.5835137367248535,
628
+ "log_odds_ratio": -0.53892982006073,
629
+ "logits/chosen": 166.1542510986328,
630
+ "logits/rejected": 168.4519500732422,
631
+ "logps/chosen": -0.8141013979911804,
632
+ "logps/rejected": -1.1682002544403076,
633
+ "loss": 41.5316,
634
+ "nll_loss": 1.1594789028167725,
635
+ "rewards/accuracies": 0.71875,
636
+ "rewards/chosen": -0.08141013979911804,
637
+ "rewards/margins": 0.03540989011526108,
638
+ "rewards/rejected": -0.11682002246379852,
639
+ "step": 175
640
+ },
641
+ {
642
+ "epoch": 1.7016296296296296,
643
+ "grad_norm": 118.51079559326172,
644
+ "learning_rate": 2.3197646927086697e-05,
645
+ "log_odds_chosen": 0.6879704594612122,
646
+ "log_odds_ratio": -0.5013464689254761,
647
+ "logits/chosen": 162.96640014648438,
648
+ "logits/rejected": 172.0683135986328,
649
+ "logps/chosen": -0.7627670168876648,
650
+ "logps/rejected": -1.173905611038208,
651
+ "loss": 41.5345,
652
+ "nll_loss": 1.1955446004867554,
653
+ "rewards/accuracies": 0.762499988079071,
654
+ "rewards/chosen": -0.07627670466899872,
655
+ "rewards/margins": 0.041113872081041336,
656
+ "rewards/rejected": -0.11739057302474976,
657
+ "step": 180
658
+ },
659
+ {
660
+ "epoch": 1.749037037037037,
661
+ "grad_norm": 74.93000793457031,
662
+ "learning_rate": 2.1817114703032176e-05,
663
+ "log_odds_chosen": 0.6024610996246338,
664
+ "log_odds_ratio": -0.5312515497207642,
665
+ "logits/chosen": 171.1946563720703,
666
+ "logits/rejected": 165.66786193847656,
667
+ "logps/chosen": -0.8485876321792603,
668
+ "logps/rejected": -1.2339482307434082,
669
+ "loss": 42.8973,
670
+ "nll_loss": 1.169698715209961,
671
+ "rewards/accuracies": 0.731249988079071,
672
+ "rewards/chosen": -0.08485876023769379,
673
+ "rewards/margins": 0.03853606432676315,
674
+ "rewards/rejected": -0.12339482456445694,
675
+ "step": 185
676
+ },
677
+ {
678
+ "epoch": 1.7964444444444445,
679
+ "grad_norm": 90.15260314941406,
680
+ "learning_rate": 2.0446385870993467e-05,
681
+ "log_odds_chosen": 0.7374637722969055,
682
+ "log_odds_ratio": -0.5001427531242371,
683
+ "logits/chosen": 164.8547821044922,
684
+ "logits/rejected": 172.21884155273438,
685
+ "logps/chosen": -0.740398108959198,
686
+ "logps/rejected": -1.1602150201797485,
687
+ "loss": 41.8807,
688
+ "nll_loss": 1.2132307291030884,
689
+ "rewards/accuracies": 0.78125,
690
+ "rewards/chosen": -0.07403980940580368,
691
+ "rewards/margins": 0.04198168218135834,
692
+ "rewards/rejected": -0.11602149903774261,
693
+ "step": 190
694
+ },
695
+ {
696
+ "epoch": 1.8438518518518519,
697
+ "grad_norm": 92.40069580078125,
698
+ "learning_rate": 1.9089682321121834e-05,
699
+ "log_odds_chosen": 0.7128893136978149,
700
+ "log_odds_ratio": -0.47155600786209106,
701
+ "logits/chosen": 165.87669372558594,
702
+ "logits/rejected": 172.61318969726562,
703
+ "logps/chosen": -0.754193127155304,
704
+ "logps/rejected": -1.180406928062439,
705
+ "loss": 41.496,
706
+ "nll_loss": 1.1548162698745728,
707
+ "rewards/accuracies": 0.8187500238418579,
708
+ "rewards/chosen": -0.07541932165622711,
709
+ "rewards/margins": 0.04262138158082962,
710
+ "rewards/rejected": -0.11804070323705673,
711
+ "step": 195
712
+ },
713
+ {
714
+ "epoch": 1.8912592592592592,
715
+ "grad_norm": 162.5179901123047,
716
+ "learning_rate": 1.775118274523545e-05,
717
+ "log_odds_chosen": 0.6597492694854736,
718
+ "log_odds_ratio": -0.5039402842521667,
719
+ "logits/chosen": 170.98081970214844,
720
+ "logits/rejected": 160.72286987304688,
721
+ "logps/chosen": -0.7827887535095215,
722
+ "logps/rejected": -1.1850932836532593,
723
+ "loss": 43.5257,
724
+ "nll_loss": 1.1609065532684326,
725
+ "rewards/accuracies": 0.75,
726
+ "rewards/chosen": -0.07827886939048767,
727
+ "rewards/margins": 0.04023047536611557,
728
+ "rewards/rejected": -0.11850935220718384,
729
+ "step": 200
730
+ },
731
+ {
732
+ "epoch": 1.9386666666666668,
733
+ "grad_norm": 108.07565307617188,
734
+ "learning_rate": 1.643500976631037e-05,
735
+ "log_odds_chosen": 0.5795512199401855,
736
+ "log_odds_ratio": -0.5528998970985413,
737
+ "logits/chosen": 164.41201782226562,
738
+ "logits/rejected": 164.38758850097656,
739
+ "logps/chosen": -0.8399173021316528,
740
+ "logps/rejected": -1.179202675819397,
741
+ "loss": 41.0177,
742
+ "nll_loss": 1.1463985443115234,
743
+ "rewards/accuracies": 0.71875,
744
+ "rewards/chosen": -0.08399172127246857,
745
+ "rewards/margins": 0.03392853960394859,
746
+ "rewards/rejected": -0.11792026460170746,
747
+ "step": 205
748
+ },
749
+ {
750
+ "epoch": 1.986074074074074,
751
+ "grad_norm": 115.8080825805664,
752
+ "learning_rate": 1.514521724066537e-05,
753
+ "log_odds_chosen": 0.5534907579421997,
754
+ "log_odds_ratio": -0.5411711931228638,
755
+ "logits/chosen": 154.23106384277344,
756
+ "logits/rejected": 170.20620727539062,
757
+ "logps/chosen": -0.8084504008293152,
758
+ "logps/rejected": -1.1170052289962769,
759
+ "loss": 42.6147,
760
+ "nll_loss": 1.186996340751648,
761
+ "rewards/accuracies": 0.731249988079071,
762
+ "rewards/chosen": -0.08084504306316376,
763
+ "rewards/margins": 0.030855495482683182,
764
+ "rewards/rejected": -0.11170053482055664,
765
+ "step": 210
766
+ },
767
+ {
768
+ "epoch": 2.0284444444444443,
769
+ "grad_norm": 90.59041595458984,
770
+ "learning_rate": 1.3885777771950348e-05,
771
+ "log_odds_chosen": 0.8948329091072083,
772
+ "log_odds_ratio": -0.4475046992301941,
773
+ "logits/chosen": 148.672119140625,
774
+ "logits/rejected": 165.1870880126953,
775
+ "logps/chosen": -0.6647176146507263,
776
+ "logps/rejected": -1.11704683303833,
777
+ "loss": 27.1004,
778
+ "nll_loss": 1.003554105758667,
779
+ "rewards/accuracies": 0.7902097702026367,
780
+ "rewards/chosen": -0.06647177040576935,
781
+ "rewards/margins": 0.04523293301463127,
782
+ "rewards/rejected": -0.11170468479394913,
783
+ "step": 215
784
+ },
785
+ {
786
+ "epoch": 2.075851851851852,
787
+ "grad_norm": 86.0616226196289,
788
+ "learning_rate": 1.2660570475395683e-05,
789
+ "log_odds_chosen": 1.250009298324585,
790
+ "log_odds_ratio": -0.36795759201049805,
791
+ "logits/chosen": 148.93313598632812,
792
+ "logits/rejected": 143.25082397460938,
793
+ "logps/chosen": -0.5993420481681824,
794
+ "logps/rejected": -1.2455394268035889,
795
+ "loss": 30.4452,
796
+ "nll_loss": 0.9209936857223511,
797
+ "rewards/accuracies": 0.84375,
798
+ "rewards/chosen": -0.059934210032224655,
799
+ "rewards/margins": 0.0646197497844696,
800
+ "rewards/rejected": -0.12455395609140396,
801
+ "step": 220
802
+ },
803
+ {
804
+ "epoch": 2.1232592592592594,
805
+ "grad_norm": 84.1713638305664,
806
+ "learning_rate": 1.1473369030008974e-05,
807
+ "log_odds_chosen": 1.174658179283142,
808
+ "log_odds_ratio": -0.356853723526001,
809
+ "logits/chosen": 143.72671508789062,
810
+ "logits/rejected": 158.54354858398438,
811
+ "logps/chosen": -0.6264591813087463,
812
+ "logps/rejected": -1.2464309930801392,
813
+ "loss": 28.8671,
814
+ "nll_loss": 0.9537235498428345,
815
+ "rewards/accuracies": 0.8687499761581421,
816
+ "rewards/chosen": -0.06264591962099075,
817
+ "rewards/margins": 0.0619971938431263,
818
+ "rewards/rejected": -0.12464310973882675,
819
+ "step": 225
820
+ },
821
+ {
822
+ "epoch": 2.1706666666666665,
823
+ "grad_norm": 77.91154479980469,
824
+ "learning_rate": 1.0327830055518842e-05,
825
+ "log_odds_chosen": 1.4034736156463623,
826
+ "log_odds_ratio": -0.3213329017162323,
827
+ "logits/chosen": 139.12863159179688,
828
+ "logits/rejected": 152.34979248046875,
829
+ "logps/chosen": -0.523759663105011,
830
+ "logps/rejected": -1.247804880142212,
831
+ "loss": 28.4987,
832
+ "nll_loss": 0.9499783515930176,
833
+ "rewards/accuracies": 0.8500000238418579,
834
+ "rewards/chosen": -0.05237596482038498,
835
+ "rewards/margins": 0.07240451872348785,
836
+ "rewards/rejected": -0.12478047609329224,
837
+ "step": 230
838
+ },
839
+ {
840
+ "epoch": 2.218074074074074,
841
+ "grad_norm": 83.66588592529297,
842
+ "learning_rate": 9.227481849865235e-06,
843
+ "log_odds_chosen": 1.2579195499420166,
844
+ "log_odds_ratio": -0.3566834032535553,
845
+ "logits/chosen": 147.706298828125,
846
+ "logits/rejected": 154.14144897460938,
847
+ "logps/chosen": -0.5796977877616882,
848
+ "logps/rejected": -1.2237907648086548,
849
+ "loss": 29.3935,
850
+ "nll_loss": 1.031733512878418,
851
+ "rewards/accuracies": 0.862500011920929,
852
+ "rewards/chosen": -0.05796977877616882,
853
+ "rewards/margins": 0.0644093006849289,
854
+ "rewards/rejected": -0.12237907946109772,
855
+ "step": 235
856
+ },
857
+ {
858
+ "epoch": 2.2654814814814817,
859
+ "grad_norm": 74.43516540527344,
860
+ "learning_rate": 8.175713521924978e-06,
861
+ "log_odds_chosen": 1.3422095775604248,
862
+ "log_odds_ratio": -0.3374899923801422,
863
+ "logits/chosen": 149.18312072753906,
864
+ "logits/rejected": 154.009521484375,
865
+ "logps/chosen": -0.5643447637557983,
866
+ "logps/rejected": -1.2900631427764893,
867
+ "loss": 27.9328,
868
+ "nll_loss": 0.9503912925720215,
869
+ "rewards/accuracies": 0.8687499761581421,
870
+ "rewards/chosen": -0.056434474885463715,
871
+ "rewards/margins": 0.07257183641195297,
872
+ "rewards/rejected": -0.1290062963962555,
873
+ "step": 240
874
+ },
875
+ {
876
+ "epoch": 2.3128888888888888,
877
+ "grad_norm": 75.92787170410156,
878
+ "learning_rate": 7.1757645529443665e-06,
879
+ "log_odds_chosen": 1.2318410873413086,
880
+ "log_odds_ratio": -0.35098910331726074,
881
+ "logits/chosen": 143.47189331054688,
882
+ "logits/rejected": 149.70175170898438,
883
+ "logps/chosen": -0.5589536428451538,
884
+ "logps/rejected": -1.1729671955108643,
885
+ "loss": 28.1651,
886
+ "nll_loss": 0.9808350801467896,
887
+ "rewards/accuracies": 0.8812500238418579,
888
+ "rewards/chosen": -0.0558953657746315,
889
+ "rewards/margins": 0.0614013597369194,
890
+ "rewards/rejected": -0.1172967329621315,
891
+ "step": 245
892
+ },
893
+ {
894
+ "epoch": 2.3602962962962963,
895
+ "grad_norm": 74.89574432373047,
896
+ "learning_rate": 6.230714818829733e-06,
897
+ "log_odds_chosen": 1.2893285751342773,
898
+ "log_odds_ratio": -0.3291093111038208,
899
+ "logits/chosen": 142.4235382080078,
900
+ "logits/rejected": 155.55056762695312,
901
+ "logps/chosen": -0.5391908884048462,
902
+ "logps/rejected": -1.1565053462982178,
903
+ "loss": 27.3194,
904
+ "nll_loss": 0.9568870663642883,
905
+ "rewards/accuracies": 0.887499988079071,
906
+ "rewards/chosen": -0.053919095546007156,
907
+ "rewards/margins": 0.06173144653439522,
908
+ "rewards/rejected": -0.11565053462982178,
909
+ "step": 250
910
+ },
911
+ {
912
+ "epoch": 2.407703703703704,
913
+ "grad_norm": 101.1366958618164,
914
+ "learning_rate": 5.343475104027743e-06,
915
+ "log_odds_chosen": 1.3717255592346191,
916
+ "log_odds_ratio": -0.31057819724082947,
917
+ "logits/chosen": 145.82192993164062,
918
+ "logits/rejected": 157.4121551513672,
919
+ "logps/chosen": -0.5673968195915222,
920
+ "logps/rejected": -1.292184829711914,
921
+ "loss": 27.6674,
922
+ "nll_loss": 0.9738559722900391,
923
+ "rewards/accuracies": 0.9312499761581421,
924
+ "rewards/chosen": -0.056739676743745804,
925
+ "rewards/margins": 0.07247880846261978,
926
+ "rewards/rejected": -0.12921848893165588,
927
+ "step": 255
928
+ },
929
+ {
930
+ "epoch": 2.455111111111111,
931
+ "grad_norm": 70.32421112060547,
932
+ "learning_rate": 4.516778136213037e-06,
933
+ "log_odds_chosen": 1.2915947437286377,
934
+ "log_odds_ratio": -0.3315240442752838,
935
+ "logits/chosen": 148.68887329101562,
936
+ "logits/rejected": 152.3128204345703,
937
+ "logps/chosen": -0.5507271885871887,
938
+ "logps/rejected": -1.2073142528533936,
939
+ "loss": 26.7991,
940
+ "nll_loss": 0.9244152903556824,
941
+ "rewards/accuracies": 0.893750011920929,
942
+ "rewards/chosen": -0.05507272481918335,
943
+ "rewards/margins": 0.06565871089696884,
944
+ "rewards/rejected": -0.12073143571615219,
945
+ "step": 260
946
+ },
947
+ {
948
+ "epoch": 2.5025185185185186,
949
+ "grad_norm": 88.66117095947266,
950
+ "learning_rate": 3.7531701693965554e-06,
951
+ "log_odds_chosen": 1.0783891677856445,
952
+ "log_odds_ratio": -0.39326241612434387,
953
+ "logits/chosen": 142.20773315429688,
954
+ "logits/rejected": 157.72744750976562,
955
+ "logps/chosen": -0.6386336088180542,
956
+ "logps/rejected": -1.203892469406128,
957
+ "loss": 29.5263,
958
+ "nll_loss": 0.9696661233901978,
959
+ "rewards/accuracies": 0.84375,
960
+ "rewards/chosen": -0.0638633519411087,
961
+ "rewards/margins": 0.05652589350938797,
962
+ "rewards/rejected": -0.12038924545049667,
963
+ "step": 265
964
+ },
965
+ {
966
+ "epoch": 2.549925925925926,
967
+ "grad_norm": 70.87348175048828,
968
+ "learning_rate": 3.055003141378948e-06,
969
+ "log_odds_chosen": 1.294119119644165,
970
+ "log_odds_ratio": -0.3384076952934265,
971
+ "logits/chosen": 142.66116333007812,
972
+ "logits/rejected": 156.8292236328125,
973
+ "logps/chosen": -0.5477794408798218,
974
+ "logps/rejected": -1.212263822555542,
975
+ "loss": 27.8183,
976
+ "nll_loss": 0.9275133013725281,
977
+ "rewards/accuracies": 0.8687499761581421,
978
+ "rewards/chosen": -0.05477794259786606,
979
+ "rewards/margins": 0.06644842028617859,
980
+ "rewards/rejected": -0.12122637033462524,
981
+ "step": 270
982
+ },
983
+ {
984
+ "epoch": 2.5973333333333333,
985
+ "grad_norm": 73.7018814086914,
986
+ "learning_rate": 2.424427429704365e-06,
987
+ "log_odds_chosen": 1.2953561544418335,
988
+ "log_odds_ratio": -0.32855290174484253,
989
+ "logits/chosen": 150.72714233398438,
990
+ "logits/rejected": 158.3098602294922,
991
+ "logps/chosen": -0.5738321542739868,
992
+ "logps/rejected": -1.2267369031906128,
993
+ "loss": 28.1227,
994
+ "nll_loss": 0.9237186312675476,
995
+ "rewards/accuracies": 0.9125000238418579,
996
+ "rewards/chosen": -0.057383209466934204,
997
+ "rewards/margins": 0.06529048830270767,
998
+ "rewards/rejected": -0.12267370522022247,
999
+ "step": 275
1000
+ },
1001
+ {
1002
+ "epoch": 2.644740740740741,
1003
+ "grad_norm": 92.6484375,
1004
+ "learning_rate": 1.8633852284264508e-06,
1005
+ "log_odds_chosen": 1.1647107601165771,
1006
+ "log_odds_ratio": -0.37838152050971985,
1007
+ "logits/chosen": 141.84115600585938,
1008
+ "logits/rejected": 145.9304656982422,
1009
+ "logps/chosen": -0.5830275416374207,
1010
+ "logps/rejected": -1.177208423614502,
1011
+ "loss": 27.6605,
1012
+ "nll_loss": 0.9372474551200867,
1013
+ "rewards/accuracies": 0.8374999761581421,
1014
+ "rewards/chosen": -0.05830276012420654,
1015
+ "rewards/margins": 0.05941808223724365,
1016
+ "rewards/rejected": -0.1177208423614502,
1017
+ "step": 280
1018
+ },
1019
+ {
1020
+ "epoch": 2.6921481481481484,
1021
+ "grad_norm": 81.41842651367188,
1022
+ "learning_rate": 1.3736045660864034e-06,
1023
+ "log_odds_chosen": 1.3637919425964355,
1024
+ "log_odds_ratio": -0.34803614020347595,
1025
+ "logits/chosen": 144.5272216796875,
1026
+ "logits/rejected": 154.29530334472656,
1027
+ "logps/chosen": -0.5901254415512085,
1028
+ "logps/rejected": -1.2950876951217651,
1029
+ "loss": 30.498,
1030
+ "nll_loss": 0.9892587661743164,
1031
+ "rewards/accuracies": 0.8812500238418579,
1032
+ "rewards/chosen": -0.059012554585933685,
1033
+ "rewards/margins": 0.07049622386693954,
1034
+ "rewards/rejected": -0.12950876355171204,
1035
+ "step": 285
1036
+ },
1037
+ {
1038
+ "epoch": 2.7395555555555555,
1039
+ "grad_norm": 70.63267517089844,
1040
+ "learning_rate": 9.565939833279192e-07,
1041
+ "log_odds_chosen": 1.1086750030517578,
1042
+ "log_odds_ratio": -0.3829512894153595,
1043
+ "logits/chosen": 146.74859619140625,
1044
+ "logits/rejected": 152.9655303955078,
1045
+ "logps/chosen": -0.629029393196106,
1046
+ "logps/rejected": -1.188488245010376,
1047
+ "loss": 29.3787,
1048
+ "nll_loss": 0.9796354174613953,
1049
+ "rewards/accuracies": 0.856249988079071,
1050
+ "rewards/chosen": -0.06290294229984283,
1051
+ "rewards/margins": 0.05594587326049805,
1052
+ "rewards/rejected": -0.11884882301092148,
1053
+ "step": 290
1054
+ },
1055
+ {
1056
+ "epoch": 2.786962962962963,
1057
+ "grad_norm": 82.847412109375,
1058
+ "learning_rate": 6.136378865420872e-07,
1059
+ "log_odds_chosen": 1.1708170175552368,
1060
+ "log_odds_ratio": -0.37719085812568665,
1061
+ "logits/chosen": 151.70347595214844,
1062
+ "logits/rejected": 152.47293090820312,
1063
+ "logps/chosen": -0.5851238965988159,
1064
+ "logps/rejected": -1.1528735160827637,
1065
+ "loss": 30.4969,
1066
+ "nll_loss": 1.000079870223999,
1067
+ "rewards/accuracies": 0.84375,
1068
+ "rewards/chosen": -0.05851238965988159,
1069
+ "rewards/margins": 0.05677497386932373,
1070
+ "rewards/rejected": -0.11528736352920532,
1071
+ "step": 295
1072
+ },
1073
+ {
1074
+ "epoch": 2.83437037037037,
1075
+ "grad_norm": 75.43782806396484,
1076
+ "learning_rate": 3.45792591853214e-07,
1077
+ "log_odds_chosen": 1.2519772052764893,
1078
+ "log_odds_ratio": -0.3575822710990906,
1079
+ "logits/chosen": 148.45394897460938,
1080
+ "logits/rejected": 153.39785766601562,
1081
+ "logps/chosen": -0.5753505825996399,
1082
+ "logps/rejected": -1.1751220226287842,
1083
+ "loss": 27.3766,
1084
+ "nll_loss": 0.9554588198661804,
1085
+ "rewards/accuracies": 0.8500000238418579,
1086
+ "rewards/chosen": -0.05753505229949951,
1087
+ "rewards/margins": 0.05997713282704353,
1088
+ "rewards/rejected": -0.11751220375299454,
1089
+ "step": 300
1090
+ },
1091
+ {
1092
+ "epoch": 2.8817777777777778,
1093
+ "grad_norm": 81.6047592163086,
1094
+ "learning_rate": 1.538830716302092e-07,
1095
+ "log_odds_chosen": 1.2772716283798218,
1096
+ "log_odds_ratio": -0.35476574301719666,
1097
+ "logits/chosen": 143.99130249023438,
1098
+ "logits/rejected": 158.716552734375,
1099
+ "logps/chosen": -0.5493041276931763,
1100
+ "logps/rejected": -1.1942790746688843,
1101
+ "loss": 26.0526,
1102
+ "nll_loss": 0.9715076684951782,
1103
+ "rewards/accuracies": 0.8687499761581421,
1104
+ "rewards/chosen": -0.054930418729782104,
1105
+ "rewards/margins": 0.06449749320745468,
1106
+ "rewards/rejected": -0.11942791938781738,
1107
+ "step": 305
1108
+ },
1109
+ {
1110
+ "epoch": 2.9291851851851853,
1111
+ "grad_norm": 91.33307647705078,
1112
+ "learning_rate": 3.8500413544415025e-08,
1113
+ "log_odds_chosen": 1.4484364986419678,
1114
+ "log_odds_ratio": -0.29417362809181213,
1115
+ "logits/chosen": 142.21377563476562,
1116
+ "logits/rejected": 151.10494995117188,
1117
+ "logps/chosen": -0.5301700234413147,
1118
+ "logps/rejected": -1.2688218355178833,
1119
+ "loss": 26.2553,
1120
+ "nll_loss": 0.9414353370666504,
1121
+ "rewards/accuracies": 0.918749988079071,
1122
+ "rewards/chosen": -0.05301700159907341,
1123
+ "rewards/margins": 0.07386518269777298,
1124
+ "rewards/rejected": -0.1268821805715561,
1125
+ "step": 310
1126
+ },
1127
+ {
1128
+ "epoch": 2.9765925925925925,
1129
+ "grad_norm": 79.46037292480469,
1130
+ "learning_rate": 0.0,
1131
+ "log_odds_chosen": 1.233816385269165,
1132
+ "log_odds_ratio": -0.33173733949661255,
1133
+ "logits/chosen": 133.51519775390625,
1134
+ "logits/rejected": 147.31552124023438,
1135
+ "logps/chosen": -0.5080527663230896,
1136
+ "logps/rejected": -1.0923200845718384,
1137
+ "loss": 24.852,
1138
+ "nll_loss": 0.8680761456489563,
1139
+ "rewards/accuracies": 0.8999999761581421,
1140
+ "rewards/chosen": -0.05080527812242508,
1141
+ "rewards/margins": 0.05842672660946846,
1142
+ "rewards/rejected": -0.10923199355602264,
1143
+ "step": 315
1144
+ },
1145
+ {
1146
+ "epoch": 2.9765925925925925,
1147
+ "step": 315,
1148
+ "total_flos": 0.0,
1149
+ "train_loss": 95.88784930516803,
1150
+ "train_runtime": 8067.9754,
1151
+ "train_samples_per_second": 2.51,
1152
+ "train_steps_per_second": 0.039
1153
+ }
1154
+ ],
1155
+ "logging_steps": 5,
1156
+ "max_steps": 315,
1157
+ "num_input_tokens_seen": 0,
1158
+ "num_train_epochs": 3,
1159
+ "save_steps": 100000,
1160
+ "stateful_callbacks": {
1161
+ "TrainerControl": {
1162
+ "args": {
1163
+ "should_epoch_stop": false,
1164
+ "should_evaluate": false,
1165
+ "should_log": false,
1166
+ "should_save": true,
1167
+ "should_training_stop": true
1168
+ },
1169
+ "attributes": {}
1170
+ }
1171
+ },
1172
+ "total_flos": 0.0,
1173
+ "train_batch_size": 1,
1174
+ "trial_name": null,
1175
+ "trial_params": null
1176
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce9d1a2c55964a783afdb3d1c1a0ceb4345f749a94a10158c62a5168f25541bb
3
+ size 5688