wzhouad commited on
Commit
df30c76
1 Parent(s): d911ac3

Model save

Browse files
README.md CHANGED
@@ -15,15 +15,15 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model was trained from scratch on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0452
19
- - Rewards/chosen: -0.7061
20
- - Rewards/rejected: -1.3068
21
- - Rewards/accuracies: 0.7461
22
- - Rewards/margins: 0.6007
23
- - Logps/rejected: -519.9530
24
- - Logps/chosen: -453.7436
25
- - Logits/rejected: 1.9484
26
- - Logits/chosen: 1.8118
27
 
28
  ## Model description
29
 
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
45
  - learning_rate: 5e-07
46
  - train_batch_size: 4
47
  - eval_batch_size: 8
48
- - seed: 1
49
  - distributed_type: multi-GPU
50
  - num_devices: 8
51
  - gradient_accumulation_steps: 4
@@ -60,10 +60,10 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
62
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
63
- | 0.083 | 0.21 | 100 | 0.0868 | -0.1017 | -0.2999 | 0.6914 | 0.1983 | -419.2635 | -393.2946 | 0.6233 | 0.5822 |
64
- | 0.0508 | 0.42 | 200 | 0.0527 | -0.3791 | -0.9024 | 0.75 | 0.5233 | -479.5171 | -421.0424 | 0.7278 | 0.6574 |
65
- | 0.0492 | 0.63 | 300 | 0.0506 | -0.4422 | -1.0378 | 0.7344 | 0.5956 | -493.0536 | -427.3528 | 1.4837 | 1.3643 |
66
- | 0.0478 | 0.84 | 400 | 0.0452 | -0.7061 | -1.3068 | 0.7461 | 0.6007 | -519.9530 | -453.7436 | 1.9484 | 1.8118 |
67
 
68
 
69
  ### Framework versions
 
15
 
16
  This model was trained from scratch on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0449
19
+ - Rewards/chosen: -0.6529
20
+ - Rewards/rejected: -1.2907
21
+ - Rewards/accuracies: 0.7383
22
+ - Rewards/margins: 0.6378
23
+ - Logps/rejected: -518.3444
24
+ - Logps/chosen: -448.4197
25
+ - Logits/rejected: 1.6154
26
+ - Logits/chosen: 1.4915
27
 
28
  ## Model description
29
 
 
45
  - learning_rate: 5e-07
46
  - train_batch_size: 4
47
  - eval_batch_size: 8
48
+ - seed: 2
49
  - distributed_type: multi-GPU
50
  - num_devices: 8
51
  - gradient_accumulation_steps: 4
 
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
62
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
63
+ | 0.09 | 0.21 | 100 | 0.0844 | -0.0945 | -0.2957 | 0.6992 | 0.2012 | -418.8424 | -392.5748 | 0.5303 | 0.4926 |
64
+ | 0.0405 | 0.42 | 200 | 0.0452 | -0.6625 | -1.1657 | 0.7539 | 0.5032 | -505.8466 | -449.3789 | 1.2734 | 1.1859 |
65
+ | 0.0479 | 0.63 | 300 | 0.0477 | -0.5208 | -1.1204 | 0.7383 | 0.5995 | -501.3084 | -435.2133 | 1.4093 | 1.2982 |
66
+ | 0.0457 | 0.84 | 400 | 0.0449 | -0.6529 | -1.2907 | 0.7383 | 0.6378 | -518.3444 | -448.4197 | 1.6154 | 1.4915 |
67
 
68
 
69
  ### Framework versions
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.05715055298255425,
4
- "train_runtime": 4410.411,
5
  "train_samples": 61134,
6
- "train_samples_per_second": 13.861,
7
  "train_steps_per_second": 0.108
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.0564979040210352,
4
+ "train_runtime": 4410.0999,
5
  "train_samples": 61134,
6
+ "train_samples_per_second": 13.862,
7
  "train_steps_per_second": 0.108
8
  }
config.json CHANGED
@@ -1,26 +1,28 @@
1
  {
2
- "_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
3
  "architectures": [
4
- "MistralForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
  "hidden_act": "silu",
10
  "hidden_size": 4096,
11
  "initializer_range": 0.02,
12
  "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
  "num_attention_heads": 32,
16
  "num_hidden_layers": 32,
17
  "num_key_value_heads": 8,
 
18
  "rms_norm_eps": 1e-05,
19
- "rope_theta": 10000.0,
20
- "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
- "transformers_version": "4.41.1",
24
  "use_cache": false,
25
- "vocab_size": 32000
26
  }
 
1
  {
2
+ "_name_or_path": "/share5/projects/llm/finetune-accelerate/weight/Meta-Llama-3-8B-Instruct",
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
+ "attention_bias": false,
7
  "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
  "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.35.2",
26
  "use_cache": false,
27
+ "vocab_size": 128256
28
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:129691185845d73bd26d449be24a5e7bce3c4c9aeede67042569ec622388fa71
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa9dffcb77ab3189cd6d31df43a9999157462785fcfe1e42f935bda4f76879ca
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03a77e37af87a05472f5d678f840985e3c5e1e9327e9448dda605aa98e68ced7
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8bd92f4300b6720e6b032d50778b46311cfb9c9ca0e0a29e27fcbbc0f94c753
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11dabf0ae40369316fc339c713bc4f446bf3b1c397b0fc162cf4cd211170cf17
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35adcf4975afb03beecf8682ca73b508035dc1111eaa8ac9c1c845d9e17b2771
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1c04ac243cac0a66abeef680b5f41ad9a4b21a0742b005c143de6ab7bbae1cc
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3354edbf514b761f330b3fd36ab24f0efc16b3d4069ec4dca2a2d0dfe157df28
3
  size 1168138808
special_tokens_map.json CHANGED
@@ -1,35 +1,17 @@
1
  {
2
- "additional_special_tokens": [
3
- "<unk>",
4
- "<s>",
5
- "</s>"
6
- ],
7
  "bos_token": {
8
- "content": "<s>",
9
  "lstrip": false,
10
  "normalized": false,
11
  "rstrip": false,
12
  "single_word": false
13
  },
14
  "eos_token": {
15
- "content": "</s>",
16
  "lstrip": false,
17
  "normalized": false,
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
- "pad_token": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false
27
- },
28
- "unk_token": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false
34
- }
35
  }
 
1
  {
 
 
 
 
 
2
  "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|end_of_text|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|end_of_text|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,25 +1,2047 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
  "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
- "1": {
14
- "content": "<s>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
- "2": {
22
- "content": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
@@ -27,22 +2049,15 @@
27
  "special": true
28
  }
29
  },
30
- "additional_special_tokens": [
31
- "<unk>",
32
- "<s>",
33
- "</s>"
 
 
 
34
  ],
35
- "bos_token": "<s>",
36
- "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
37
- "clean_up_tokenization_spaces": false,
38
- "eos_token": "</s>",
39
- "legacy": true,
40
  "model_max_length": 2048,
41
- "pad_token": "</s>",
42
- "sp_model_kwargs": {},
43
- "spaces_between_special_tokens": false,
44
- "tokenizer_class": "LlamaTokenizer",
45
- "truncation_side": "left",
46
- "unk_token": "<unk>",
47
- "use_default_system_prompt": true
48
  }
 
1
  {
 
 
2
  "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
  "lstrip": false,
2046
  "normalized": false,
2047
  "rstrip": false,
 
2049
  "special": true
2050
  }
2051
  },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
  ],
 
 
 
 
 
2060
  "model_max_length": 2048,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
 
2063
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.05715055298255425,
4
- "train_runtime": 4410.411,
5
  "train_samples": 61134,
6
- "train_samples_per_second": 13.861,
7
  "train_steps_per_second": 0.108
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.0564979040210352,
4
+ "train_runtime": 4410.0999,
5
  "train_samples": 61134,
6
+ "train_samples_per_second": 13.862,
7
  "train_steps_per_second": 0.108
8
  }
trainer_state.json CHANGED
@@ -11,11 +11,11 @@
11
  {
12
  "epoch": 0.0,
13
  "learning_rate": 1.0416666666666666e-08,
14
- "logits/chosen": -0.07052387297153473,
15
- "logits/rejected": -0.04838938266038895,
16
- "logps/chosen": -446.34246826171875,
17
- "logps/rejected": -438.6577453613281,
18
- "loss": 0.0926,
19
  "rewards/accuracies": 0.0,
20
  "rewards/chosen": 0.0,
21
  "rewards/margins": 0.0,
@@ -25,732 +25,732 @@
25
  {
26
  "epoch": 0.02,
27
  "learning_rate": 1.0416666666666667e-07,
28
- "logits/chosen": 0.015930278226733208,
29
- "logits/rejected": 0.04756825417280197,
30
- "logps/chosen": -400.2186279296875,
31
- "logps/rejected": -370.1379699707031,
32
- "loss": 0.0867,
33
- "rewards/accuracies": 0.4444444477558136,
34
- "rewards/chosen": -0.0008550214697606862,
35
- "rewards/margins": 0.00014371650468092412,
36
- "rewards/rejected": -0.0009987379889935255,
37
  "step": 10
38
  },
39
  {
40
  "epoch": 0.04,
41
  "learning_rate": 2.0833333333333333e-07,
42
- "logits/chosen": -0.051301874220371246,
43
- "logits/rejected": 0.014126487076282501,
44
- "logps/chosen": -451.12548828125,
45
- "logps/rejected": -394.4206848144531,
46
- "loss": 0.0896,
47
- "rewards/accuracies": 0.53125,
48
- "rewards/chosen": -0.0015964272897690535,
49
- "rewards/margins": 0.00038566262810491025,
50
- "rewards/rejected": -0.001982090063393116,
51
  "step": 20
52
  },
53
  {
54
  "epoch": 0.06,
55
  "learning_rate": 3.1249999999999997e-07,
56
- "logits/chosen": -0.017136255279183388,
57
- "logits/rejected": 0.038861632347106934,
58
- "logps/chosen": -423.1416015625,
59
- "logps/rejected": -397.456787109375,
60
- "loss": 0.0924,
61
- "rewards/accuracies": 0.625,
62
- "rewards/chosen": -0.004587138071656227,
63
- "rewards/margins": 0.002302540233358741,
64
- "rewards/rejected": -0.006889677606523037,
65
  "step": 30
66
  },
67
  {
68
  "epoch": 0.08,
69
  "learning_rate": 4.1666666666666667e-07,
70
- "logits/chosen": 0.017724500969052315,
71
- "logits/rejected": 0.04714775085449219,
72
- "logps/chosen": -386.85107421875,
73
- "logps/rejected": -395.1709899902344,
74
- "loss": 0.091,
75
- "rewards/accuracies": 0.643750011920929,
76
- "rewards/chosen": -0.005839453544467688,
77
- "rewards/margins": 0.007416002452373505,
78
- "rewards/rejected": -0.01325545646250248,
79
  "step": 40
80
  },
81
  {
82
  "epoch": 0.1,
83
  "learning_rate": 4.999731868769026e-07,
84
- "logits/chosen": 0.04165320470929146,
85
- "logits/rejected": 0.07117391377687454,
86
- "logps/chosen": -402.273193359375,
87
- "logps/rejected": -372.63580322265625,
88
- "loss": 0.0871,
89
  "rewards/accuracies": 0.65625,
90
- "rewards/chosen": -0.007713294588029385,
91
- "rewards/margins": 0.023772645741701126,
92
- "rewards/rejected": -0.031485941261053085,
93
  "step": 50
94
  },
95
  {
96
  "epoch": 0.13,
97
  "learning_rate": 4.990353313429303e-07,
98
- "logits/chosen": 0.11911481618881226,
99
- "logits/rejected": 0.15758278965950012,
100
- "logps/chosen": -341.6982421875,
101
- "logps/rejected": -342.1842956542969,
102
- "loss": 0.087,
103
- "rewards/accuracies": 0.65625,
104
- "rewards/chosen": -0.0181004349142313,
105
- "rewards/margins": 0.03961459547281265,
106
- "rewards/rejected": -0.057715028524398804,
107
  "step": 60
108
  },
109
  {
110
  "epoch": 0.15,
111
  "learning_rate": 4.967625656594781e-07,
112
- "logits/chosen": 0.10782989114522934,
113
- "logits/rejected": 0.1555609405040741,
114
- "logps/chosen": -383.43194580078125,
115
- "logps/rejected": -369.48626708984375,
116
- "loss": 0.0906,
117
- "rewards/accuracies": 0.637499988079071,
118
- "rewards/chosen": -0.02252626232802868,
119
- "rewards/margins": 0.04994729533791542,
120
- "rewards/rejected": -0.07247356325387955,
121
  "step": 70
122
  },
123
  {
124
  "epoch": 0.17,
125
  "learning_rate": 4.93167072587771e-07,
126
- "logits/chosen": 0.2392107993364334,
127
- "logits/rejected": 0.2645716071128845,
128
- "logps/chosen": -391.59271240234375,
129
- "logps/rejected": -379.87371826171875,
130
- "loss": 0.0857,
131
- "rewards/accuracies": 0.731249988079071,
132
- "rewards/chosen": -0.02302396669983864,
133
- "rewards/margins": 0.09161248058080673,
134
- "rewards/rejected": -0.11463644355535507,
135
  "step": 80
136
  },
137
  {
138
  "epoch": 0.19,
139
  "learning_rate": 4.882681251368548e-07,
140
- "logits/chosen": 0.3256095349788666,
141
- "logits/rejected": 0.3571871817111969,
142
- "logps/chosen": -394.9032897949219,
143
- "logps/rejected": -377.31365966796875,
144
- "loss": 0.0864,
145
  "rewards/accuracies": 0.6875,
146
- "rewards/chosen": -0.06340406835079193,
147
- "rewards/margins": 0.10541589558124542,
148
- "rewards/rejected": -0.16881996393203735,
149
  "step": 90
150
  },
151
  {
152
  "epoch": 0.21,
153
  "learning_rate": 4.820919832540181e-07,
154
- "logits/chosen": 0.4327087998390198,
155
- "logits/rejected": 0.5429254770278931,
156
- "logps/chosen": -407.58892822265625,
157
- "logps/rejected": -378.47100830078125,
158
- "loss": 0.083,
159
- "rewards/accuracies": 0.668749988079071,
160
- "rewards/chosen": -0.11268453299999237,
161
- "rewards/margins": 0.17376144230365753,
162
- "rewards/rejected": -0.2864459455013275,
163
  "step": 100
164
  },
165
  {
166
  "epoch": 0.21,
167
- "eval_logits/chosen": 0.5821782350540161,
168
- "eval_logits/rejected": 0.6232689023017883,
169
- "eval_logps/chosen": -393.29461669921875,
170
- "eval_logps/rejected": -419.2635192871094,
171
- "eval_loss": 0.08681700378656387,
172
- "eval_rewards/accuracies": 0.69140625,
173
- "eval_rewards/chosen": -0.10165297985076904,
174
- "eval_rewards/margins": 0.19825315475463867,
175
- "eval_rewards/rejected": -0.2999061346054077,
176
- "eval_runtime": 76.709,
177
- "eval_samples_per_second": 26.073,
178
- "eval_steps_per_second": 0.417,
179
  "step": 100
180
  },
181
  {
182
  "epoch": 0.23,
183
  "learning_rate": 4.7467175306295647e-07,
184
- "logits/chosen": 0.5684801340103149,
185
- "logits/rejected": 0.6398736238479614,
186
- "logps/chosen": -433.30438232421875,
187
- "logps/rejected": -459.71038818359375,
188
- "loss": 0.0822,
189
- "rewards/accuracies": 0.6875,
190
- "rewards/chosen": -0.14335554838180542,
191
- "rewards/margins": 0.19988378882408142,
192
- "rewards/rejected": -0.34323933720588684,
193
  "step": 110
194
  },
195
  {
196
  "epoch": 0.25,
197
  "learning_rate": 4.6604720940421207e-07,
198
- "logits/chosen": 0.6885138750076294,
199
- "logits/rejected": 0.7480685710906982,
200
- "logps/chosen": -428.5591735839844,
201
- "logps/rejected": -440.2229919433594,
202
- "loss": 0.066,
203
- "rewards/accuracies": 0.7250000238418579,
204
- "rewards/chosen": -0.25824135541915894,
205
- "rewards/margins": 0.2795271575450897,
206
- "rewards/rejected": -0.537768542766571,
207
  "step": 120
208
  },
209
  {
210
  "epoch": 0.27,
211
  "learning_rate": 4.5626458262912735e-07,
212
- "logits/chosen": 0.6938363313674927,
213
- "logits/rejected": 0.9847356081008911,
214
- "logps/chosen": -464.21453857421875,
215
- "logps/rejected": -395.2554626464844,
216
- "loss": 0.0673,
217
- "rewards/accuracies": 0.643750011920929,
218
- "rewards/chosen": -0.3627792000770569,
219
- "rewards/margins": 0.18995186686515808,
220
- "rewards/rejected": -0.5527310967445374,
221
  "step": 130
222
  },
223
  {
224
  "epoch": 0.29,
225
  "learning_rate": 4.453763107901675e-07,
226
- "logits/chosen": 0.712790310382843,
227
- "logits/rejected": 0.8445957899093628,
228
- "logps/chosen": -446.9529724121094,
229
- "logps/rejected": -424.1790466308594,
230
- "loss": 0.0563,
231
- "rewards/accuracies": 0.625,
232
- "rewards/chosen": -0.4803162217140198,
233
- "rewards/margins": 0.23708364367485046,
234
- "rewards/rejected": -0.7173997759819031,
235
  "step": 140
236
  },
237
  {
238
  "epoch": 0.31,
239
  "learning_rate": 4.3344075855595097e-07,
240
- "logits/chosen": 0.712822675704956,
241
- "logits/rejected": 0.8307243585586548,
242
- "logps/chosen": -439.9142150878906,
243
- "logps/rejected": -422.11456298828125,
244
- "loss": 0.0626,
245
- "rewards/accuracies": 0.699999988079071,
246
- "rewards/chosen": -0.3180200457572937,
247
- "rewards/margins": 0.3009991943836212,
248
- "rewards/rejected": -0.6190192699432373,
249
  "step": 150
250
  },
251
  {
252
  "epoch": 0.33,
253
  "learning_rate": 4.2052190435769554e-07,
254
- "logits/chosen": 0.8687634468078613,
255
- "logits/rejected": 1.0107380151748657,
256
- "logps/chosen": -412.14569091796875,
257
- "logps/rejected": -408.9898376464844,
258
- "loss": 0.0583,
259
- "rewards/accuracies": 0.699999988079071,
260
- "rewards/chosen": -0.33192020654678345,
261
- "rewards/margins": 0.3175792396068573,
262
- "rewards/rejected": -0.6494994759559631,
263
  "step": 160
264
  },
265
  {
266
  "epoch": 0.36,
267
  "learning_rate": 4.0668899744407567e-07,
268
- "logits/chosen": 0.8597530126571655,
269
- "logits/rejected": 0.9205295443534851,
270
- "logps/chosen": -427.3262634277344,
271
- "logps/rejected": -458.7206115722656,
272
- "loss": 0.0589,
273
- "rewards/accuracies": 0.731249988079071,
274
- "rewards/chosen": -0.34658724069595337,
275
- "rewards/margins": 0.4338514804840088,
276
- "rewards/rejected": -0.7804387211799622,
277
  "step": 170
278
  },
279
  {
280
  "epoch": 0.38,
281
  "learning_rate": 3.920161866827889e-07,
282
- "logits/chosen": 0.8266959190368652,
283
- "logits/rejected": 1.00719153881073,
284
- "logps/chosen": -419.7898864746094,
285
- "logps/rejected": -456.51556396484375,
286
- "loss": 0.0524,
287
- "rewards/accuracies": 0.71875,
288
- "rewards/chosen": -0.4117317199707031,
289
- "rewards/margins": 0.3906904458999634,
290
- "rewards/rejected": -0.8024222254753113,
291
  "step": 180
292
  },
293
  {
294
  "epoch": 0.4,
295
  "learning_rate": 3.765821230985757e-07,
296
- "logits/chosen": 0.8708335757255554,
297
- "logits/rejected": 1.0347837209701538,
298
- "logps/chosen": -443.6575622558594,
299
- "logps/rejected": -437.6563415527344,
300
- "loss": 0.0526,
301
- "rewards/accuracies": 0.637499988079071,
302
- "rewards/chosen": -0.5604835152626038,
303
- "rewards/margins": 0.2939838469028473,
304
- "rewards/rejected": -0.8544673919677734,
305
  "step": 190
306
  },
307
  {
308
  "epoch": 0.42,
309
  "learning_rate": 3.604695382782159e-07,
310
- "logits/chosen": 0.6853333115577698,
311
- "logits/rejected": 0.8512023687362671,
312
- "logps/chosen": -467.18798828125,
313
- "logps/rejected": -483.9710388183594,
314
- "loss": 0.0508,
315
- "rewards/accuracies": 0.737500011920929,
316
- "rewards/chosen": -0.4629150331020355,
317
- "rewards/margins": 0.5629688501358032,
318
- "rewards/rejected": -1.0258839130401611,
319
  "step": 200
320
  },
321
  {
322
  "epoch": 0.42,
323
- "eval_logits/chosen": 0.6574095487594604,
324
- "eval_logits/rejected": 0.7278421521186829,
325
- "eval_logps/chosen": -421.04241943359375,
326
- "eval_logps/rejected": -479.5170593261719,
327
- "eval_loss": 0.05269741639494896,
328
- "eval_rewards/accuracies": 0.75,
329
- "eval_rewards/chosen": -0.37913212180137634,
330
- "eval_rewards/margins": 0.5233093500137329,
331
- "eval_rewards/rejected": -0.9024415016174316,
332
- "eval_runtime": 76.7299,
333
- "eval_samples_per_second": 26.065,
334
- "eval_steps_per_second": 0.417,
335
  "step": 200
336
  },
337
  {
338
  "epoch": 0.44,
339
  "learning_rate": 3.4376480090239047e-07,
340
- "logits/chosen": 0.6909562349319458,
341
- "logits/rejected": 0.8330052495002747,
342
- "logps/chosen": -424.20111083984375,
343
- "logps/rejected": -432.5106506347656,
344
- "loss": 0.0483,
345
- "rewards/accuracies": 0.6499999761581421,
346
- "rewards/chosen": -0.5690485239028931,
347
- "rewards/margins": 0.3404504656791687,
348
- "rewards/rejected": -0.9094989895820618,
349
  "step": 210
350
  },
351
  {
352
  "epoch": 0.46,
353
  "learning_rate": 3.265574537815398e-07,
354
- "logits/chosen": 0.8268566131591797,
355
- "logits/rejected": 0.9763669967651367,
356
- "logps/chosen": -479.2845153808594,
357
- "logps/rejected": -468.5574645996094,
358
- "loss": 0.0465,
359
- "rewards/accuracies": 0.71875,
360
- "rewards/chosen": -0.57017582654953,
361
- "rewards/margins": 0.44474053382873535,
362
- "rewards/rejected": -1.0149163007736206,
363
  "step": 220
364
  },
365
  {
366
  "epoch": 0.48,
367
  "learning_rate": 3.0893973387735683e-07,
368
- "logits/chosen": 0.7100130915641785,
369
- "logits/rejected": 0.8351715207099915,
370
- "logps/chosen": -458.81085205078125,
371
- "logps/rejected": -460.79168701171875,
372
- "loss": 0.046,
373
- "rewards/accuracies": 0.6875,
374
- "rewards/chosen": -0.6259957551956177,
375
- "rewards/margins": 0.4563576579093933,
376
- "rewards/rejected": -1.0823533535003662,
377
  "step": 230
378
  },
379
  {
380
  "epoch": 0.5,
381
  "learning_rate": 2.910060778827554e-07,
382
- "logits/chosen": 0.6708893179893494,
383
- "logits/rejected": 0.7649146318435669,
384
- "logps/chosen": -430.97418212890625,
385
- "logps/rejected": -484.947021484375,
386
- "loss": 0.0486,
387
- "rewards/accuracies": 0.65625,
388
- "rewards/chosen": -0.5872732400894165,
389
- "rewards/margins": 0.4288311004638672,
390
- "rewards/rejected": -1.0161044597625732,
391
  "step": 240
392
  },
393
  {
394
  "epoch": 0.52,
395
  "learning_rate": 2.7285261601056697e-07,
396
- "logits/chosen": 0.7758423686027527,
397
- "logits/rejected": 0.8830370903015137,
398
- "logps/chosen": -411.7647399902344,
399
- "logps/rejected": -453.8568420410156,
400
- "loss": 0.0463,
401
- "rewards/accuracies": 0.7562500238418579,
402
- "rewards/chosen": -0.47665682435035706,
403
- "rewards/margins": 0.5621976852416992,
404
- "rewards/rejected": -1.0388545989990234,
405
  "step": 250
406
  },
407
  {
408
  "epoch": 0.54,
409
  "learning_rate": 2.5457665670441937e-07,
410
- "logits/chosen": 1.0591604709625244,
411
- "logits/rejected": 1.314805269241333,
412
- "logps/chosen": -472.56103515625,
413
- "logps/rejected": -468.9657287597656,
414
- "loss": 0.0459,
415
- "rewards/accuracies": 0.6187499761581421,
416
- "rewards/chosen": -0.782352089881897,
417
- "rewards/margins": 0.3404228389263153,
418
- "rewards/rejected": -1.1227748394012451,
419
  "step": 260
420
  },
421
  {
422
  "epoch": 0.57,
423
  "learning_rate": 2.3627616503391812e-07,
424
- "logits/chosen": 1.548477292060852,
425
- "logits/rejected": 1.7389554977416992,
426
- "logps/chosen": -492.27032470703125,
427
- "logps/rejected": -555.7271728515625,
428
- "loss": 0.0394,
429
- "rewards/accuracies": 0.7124999761581421,
430
- "rewards/chosen": -0.8911805152893066,
431
- "rewards/margins": 0.5339128375053406,
432
- "rewards/rejected": -1.425093412399292,
433
  "step": 270
434
  },
435
  {
436
  "epoch": 0.59,
437
  "learning_rate": 2.1804923757009882e-07,
438
- "logits/chosen": 1.4875777959823608,
439
- "logits/rejected": 1.5765650272369385,
440
- "logps/chosen": -429.2174377441406,
441
- "logps/rejected": -485.6429138183594,
442
- "loss": 0.0435,
443
- "rewards/accuracies": 0.7250000238418579,
444
- "rewards/chosen": -0.7169326543807983,
445
- "rewards/margins": 0.48180657625198364,
446
- "rewards/rejected": -1.1987392902374268,
447
  "step": 280
448
  },
449
  {
450
  "epoch": 0.61,
451
  "learning_rate": 1.9999357655598891e-07,
452
- "logits/chosen": 1.1693575382232666,
453
- "logits/rejected": 1.4192606210708618,
454
- "logps/chosen": -445.72900390625,
455
- "logps/rejected": -474.2784118652344,
456
- "loss": 0.0478,
457
- "rewards/accuracies": 0.737500011920929,
458
- "rewards/chosen": -0.500573992729187,
459
- "rewards/margins": 0.5597209930419922,
460
- "rewards/rejected": -1.0602951049804688,
461
  "step": 290
462
  },
463
  {
464
  "epoch": 0.63,
465
  "learning_rate": 1.8220596619089573e-07,
466
- "logits/chosen": 1.2039165496826172,
467
- "logits/rejected": 1.3679600954055786,
468
- "logps/chosen": -392.41912841796875,
469
- "logps/rejected": -423.9827575683594,
470
- "loss": 0.0492,
471
- "rewards/accuracies": 0.6875,
472
- "rewards/chosen": -0.4298545718193054,
473
- "rewards/margins": 0.4661535620689392,
474
- "rewards/rejected": -0.8960081338882446,
475
  "step": 300
476
  },
477
  {
478
  "epoch": 0.63,
479
- "eval_logits/chosen": 1.3642895221710205,
480
- "eval_logits/rejected": 1.4837121963500977,
481
- "eval_logps/chosen": -427.3528137207031,
482
- "eval_logps/rejected": -493.0536193847656,
483
- "eval_loss": 0.050642818212509155,
484
- "eval_rewards/accuracies": 0.734375,
485
- "eval_rewards/chosen": -0.4422356188297272,
486
- "eval_rewards/margins": 0.5955713987350464,
487
- "eval_rewards/rejected": -1.0378071069717407,
488
- "eval_runtime": 75.0333,
489
- "eval_samples_per_second": 26.655,
490
- "eval_steps_per_second": 0.426,
491
  "step": 300
492
  },
493
  {
494
  "epoch": 0.65,
495
  "learning_rate": 1.647817538357072e-07,
496
- "logits/chosen": 1.291404128074646,
497
- "logits/rejected": 1.4620802402496338,
498
- "logps/chosen": -446.38311767578125,
499
- "logps/rejected": -491.62811279296875,
500
- "loss": 0.0512,
501
- "rewards/accuracies": 0.762499988079071,
502
- "rewards/chosen": -0.4551282525062561,
503
- "rewards/margins": 0.6054805517196655,
504
- "rewards/rejected": -1.0606087446212769,
505
  "step": 310
506
  },
507
  {
508
  "epoch": 0.67,
509
  "learning_rate": 1.478143389201113e-07,
510
- "logits/chosen": 1.319111943244934,
511
- "logits/rejected": 1.5712411403656006,
512
- "logps/chosen": -444.0741271972656,
513
- "logps/rejected": -458.99298095703125,
514
- "loss": 0.0454,
515
- "rewards/accuracies": 0.706250011920929,
516
- "rewards/chosen": -0.5400988459587097,
517
- "rewards/margins": 0.5210468173027039,
518
- "rewards/rejected": -1.0611456632614136,
519
  "step": 320
520
  },
521
  {
522
  "epoch": 0.69,
523
  "learning_rate": 1.3139467229135998e-07,
524
- "logits/chosen": 1.5040777921676636,
525
- "logits/rejected": 1.5720586776733398,
526
- "logps/chosen": -422.38690185546875,
527
- "logps/rejected": -500.0401306152344,
528
- "loss": 0.0435,
529
- "rewards/accuracies": 0.6937500238418579,
530
- "rewards/chosen": -0.6113966107368469,
531
- "rewards/margins": 0.5554958581924438,
532
- "rewards/rejected": -1.166892409324646,
533
  "step": 330
534
  },
535
  {
536
  "epoch": 0.71,
537
  "learning_rate": 1.1561076868822755e-07,
538
- "logits/chosen": 1.5266200304031372,
539
- "logits/rejected": 1.7858022451400757,
540
- "logps/chosen": -456.5145568847656,
541
- "logps/rejected": -480.37335205078125,
542
- "loss": 0.0449,
543
- "rewards/accuracies": 0.71875,
544
- "rewards/chosen": -0.7167869210243225,
545
- "rewards/margins": 0.5133916139602661,
546
- "rewards/rejected": -1.2301785945892334,
547
  "step": 340
548
  },
549
  {
550
  "epoch": 0.73,
551
  "learning_rate": 1.0054723495346482e-07,
552
- "logits/chosen": 1.6522409915924072,
553
- "logits/rejected": 1.7957807779312134,
554
- "logps/chosen": -439.47265625,
555
- "logps/rejected": -470.72796630859375,
556
- "loss": 0.0376,
557
- "rewards/accuracies": 0.6499999761581421,
558
- "rewards/chosen": -0.892612636089325,
559
- "rewards/margins": 0.40467318892478943,
560
- "rewards/rejected": -1.297285795211792,
561
  "step": 350
562
  },
563
  {
564
  "epoch": 0.75,
565
  "learning_rate": 8.628481651367875e-08,
566
- "logits/chosen": 1.7138694524765015,
567
- "logits/rejected": 1.9002339839935303,
568
- "logps/chosen": -415.7076110839844,
569
- "logps/rejected": -466.66314697265625,
570
- "loss": 0.0395,
571
  "rewards/accuracies": 0.706250011920929,
572
- "rewards/chosen": -0.7421653866767883,
573
- "rewards/margins": 0.5101168155670166,
574
- "rewards/rejected": -1.2522823810577393,
575
  "step": 360
576
  },
577
  {
578
  "epoch": 0.77,
579
  "learning_rate": 7.289996455765748e-08,
580
- "logits/chosen": 1.679660439491272,
581
- "logits/rejected": 1.772728681564331,
582
- "logps/chosen": -477.29107666015625,
583
- "logps/rejected": -513.1658935546875,
584
- "loss": 0.0405,
585
- "rewards/accuracies": 0.7250000238418579,
586
- "rewards/chosen": -0.7037874460220337,
587
- "rewards/margins": 0.599014937877655,
588
- "rewards/rejected": -1.302802324295044,
589
  "step": 370
590
  },
591
  {
592
  "epoch": 0.8,
593
  "learning_rate": 6.046442623320145e-08,
594
- "logits/chosen": 1.7673553228378296,
595
- "logits/rejected": 1.7649829387664795,
596
- "logps/chosen": -432.1739807128906,
597
- "logps/rejected": -481.89666748046875,
598
- "loss": 0.0433,
599
- "rewards/accuracies": 0.7749999761581421,
600
- "rewards/chosen": -0.6910613775253296,
601
- "rewards/margins": 0.5233997106552124,
602
- "rewards/rejected": -1.214461088180542,
603
  "step": 380
604
  },
605
  {
606
  "epoch": 0.82,
607
  "learning_rate": 4.904486005914027e-08,
608
- "logits/chosen": 1.4528627395629883,
609
- "logits/rejected": 1.6894763708114624,
610
- "logps/chosen": -459.02642822265625,
611
- "logps/rejected": -503.07427978515625,
612
- "loss": 0.0423,
613
- "rewards/accuracies": 0.762499988079071,
614
- "rewards/chosen": -0.6205865144729614,
615
- "rewards/margins": 0.7107428312301636,
616
- "rewards/rejected": -1.3313294649124146,
617
  "step": 390
618
  },
619
  {
620
  "epoch": 0.84,
621
  "learning_rate": 3.8702478614051345e-08,
622
- "logits/chosen": 1.6400655508041382,
623
- "logits/rejected": 1.8003590106964111,
624
- "logps/chosen": -445.6006774902344,
625
- "logps/rejected": -512.8395385742188,
626
- "loss": 0.0478,
627
- "rewards/accuracies": 0.7437499761581421,
628
- "rewards/chosen": -0.6654289960861206,
629
- "rewards/margins": 0.6264350414276123,
630
- "rewards/rejected": -1.291864037513733,
631
  "step": 400
632
  },
633
  {
634
  "epoch": 0.84,
635
- "eval_logits/chosen": 1.811805009841919,
636
- "eval_logits/rejected": 1.948449730873108,
637
- "eval_logps/chosen": -453.7436218261719,
638
- "eval_logps/rejected": -519.9530029296875,
639
- "eval_loss": 0.045155834406614304,
640
- "eval_rewards/accuracies": 0.74609375,
641
- "eval_rewards/chosen": -0.7061434984207153,
642
- "eval_rewards/margins": 0.6006576418876648,
643
- "eval_rewards/rejected": -1.3068010807037354,
644
- "eval_runtime": 75.4934,
645
- "eval_samples_per_second": 26.492,
646
- "eval_steps_per_second": 0.424,
647
  "step": 400
648
  },
649
  {
650
  "epoch": 0.86,
651
  "learning_rate": 2.9492720416985e-08,
652
- "logits/chosen": 1.6983802318572998,
653
- "logits/rejected": 1.7938108444213867,
654
- "logps/chosen": -442.48760986328125,
655
- "logps/rejected": -477.904296875,
656
- "loss": 0.0408,
657
  "rewards/accuracies": 0.706250011920929,
658
- "rewards/chosen": -0.7524789571762085,
659
- "rewards/margins": 0.49356669187545776,
660
- "rewards/rejected": -1.246045708656311,
661
  "step": 410
662
  },
663
  {
664
  "epoch": 0.88,
665
  "learning_rate": 2.1464952759020856e-08,
666
- "logits/chosen": 1.7237422466278076,
667
- "logits/rejected": 1.9007956981658936,
668
- "logps/chosen": -422.75701904296875,
669
- "logps/rejected": -464.2802734375,
670
- "loss": 0.0424,
671
- "rewards/accuracies": 0.7124999761581421,
672
- "rewards/chosen": -0.697801411151886,
673
- "rewards/margins": 0.4890449047088623,
674
- "rewards/rejected": -1.186846375465393,
675
  "step": 420
676
  },
677
  {
678
  "epoch": 0.9,
679
  "learning_rate": 1.4662207078575684e-08,
680
- "logits/chosen": 1.5331242084503174,
681
- "logits/rejected": 1.664502501487732,
682
- "logps/chosen": -487.17724609375,
683
- "logps/rejected": -510.3055725097656,
684
- "loss": 0.0473,
685
- "rewards/accuracies": 0.737500011920929,
686
- "rewards/chosen": -0.713259756565094,
687
- "rewards/margins": 0.5690262913703918,
688
- "rewards/rejected": -1.2822860479354858,
689
  "step": 430
690
  },
691
  {
692
  "epoch": 0.92,
693
  "learning_rate": 9.12094829893642e-09,
694
- "logits/chosen": 1.6383097171783447,
695
- "logits/rejected": 1.7805635929107666,
696
- "logps/chosen": -468.48553466796875,
697
- "logps/rejected": -478.580810546875,
698
- "loss": 0.0439,
699
- "rewards/accuracies": 0.731249988079071,
700
- "rewards/chosen": -0.7043701410293579,
701
- "rewards/margins": 0.5650184750556946,
702
- "rewards/rejected": -1.2693886756896973,
703
  "step": 440
704
  },
705
  {
706
  "epoch": 0.94,
707
  "learning_rate": 4.8708793644441086e-09,
708
- "logits/chosen": 1.4979596138000488,
709
- "logits/rejected": 1.7661205530166626,
710
- "logps/chosen": -489.6907653808594,
711
- "logps/rejected": -506.7139587402344,
712
- "loss": 0.0428,
713
- "rewards/accuracies": 0.75,
714
- "rewards/chosen": -0.7196102142333984,
715
- "rewards/margins": 0.5808975696563721,
716
- "rewards/rejected": -1.3005077838897705,
717
  "step": 450
718
  },
719
  {
720
  "epoch": 0.96,
721
  "learning_rate": 1.9347820230782295e-09,
722
- "logits/chosen": 1.6144044399261475,
723
- "logits/rejected": 1.834363341331482,
724
- "logps/chosen": -439.77972412109375,
725
- "logps/rejected": -465.7396545410156,
726
- "loss": 0.0413,
727
- "rewards/accuracies": 0.7437499761581421,
728
- "rewards/chosen": -0.6626710295677185,
729
- "rewards/margins": 0.5204571485519409,
730
- "rewards/rejected": -1.1831282377243042,
731
  "step": 460
732
  },
733
  {
734
  "epoch": 0.98,
735
  "learning_rate": 3.2839470889836627e-10,
736
- "logits/chosen": 1.475067138671875,
737
- "logits/rejected": 1.8053594827651978,
738
- "logps/chosen": -474.4951171875,
739
- "logps/rejected": -483.27410888671875,
740
- "loss": 0.0451,
741
  "rewards/accuracies": 0.75,
742
- "rewards/chosen": -0.6129671335220337,
743
- "rewards/margins": 0.5990576148033142,
744
- "rewards/rejected": -1.2120248079299927,
745
  "step": 470
746
  },
747
  {
748
  "epoch": 1.0,
749
  "step": 477,
750
  "total_flos": 0.0,
751
- "train_loss": 0.05715055298255425,
752
- "train_runtime": 4410.411,
753
- "train_samples_per_second": 13.861,
754
  "train_steps_per_second": 0.108
755
  }
756
  ],
 
11
  {
12
  "epoch": 0.0,
13
  "learning_rate": 1.0416666666666666e-08,
14
+ "logits/chosen": 0.01849743165075779,
15
+ "logits/rejected": 0.013860300183296204,
16
+ "logps/chosen": -318.92303466796875,
17
+ "logps/rejected": -327.4117126464844,
18
+ "loss": 0.0872,
19
  "rewards/accuracies": 0.0,
20
  "rewards/chosen": 0.0,
21
  "rewards/margins": 0.0,
 
25
  {
26
  "epoch": 0.02,
27
  "learning_rate": 1.0416666666666667e-07,
28
+ "logits/chosen": 0.0165844839066267,
29
+ "logits/rejected": 0.029045505449175835,
30
+ "logps/chosen": -380.119384765625,
31
+ "logps/rejected": -372.70452880859375,
32
+ "loss": 0.0916,
33
+ "rewards/accuracies": 0.4930555522441864,
34
+ "rewards/chosen": 0.00031676876824349165,
35
+ "rewards/margins": 0.0008045767317526042,
36
+ "rewards/rejected": -0.00048780813813209534,
37
  "step": 10
38
  },
39
  {
40
  "epoch": 0.04,
41
  "learning_rate": 2.0833333333333333e-07,
42
+ "logits/chosen": -0.01443287543952465,
43
+ "logits/rejected": 0.01765434443950653,
44
+ "logps/chosen": -396.4976501464844,
45
+ "logps/rejected": -366.0671691894531,
46
+ "loss": 0.0929,
47
+ "rewards/accuracies": 0.581250011920929,
48
+ "rewards/chosen": 0.000257034320384264,
49
+ "rewards/margins": 0.0013006285298615694,
50
+ "rewards/rejected": -0.0010435942094773054,
51
  "step": 20
52
  },
53
  {
54
  "epoch": 0.06,
55
  "learning_rate": 3.1249999999999997e-07,
56
+ "logits/chosen": 0.037671297788619995,
57
+ "logits/rejected": 0.06698160618543625,
58
+ "logps/chosen": -374.0677795410156,
59
+ "logps/rejected": -360.3742370605469,
60
+ "loss": 0.0849,
61
+ "rewards/accuracies": 0.637499988079071,
62
+ "rewards/chosen": -0.0024321433156728745,
63
+ "rewards/margins": 0.003862987505272031,
64
+ "rewards/rejected": -0.006295130588114262,
65
  "step": 30
66
  },
67
  {
68
  "epoch": 0.08,
69
  "learning_rate": 4.1666666666666667e-07,
70
+ "logits/chosen": -0.016021814197301865,
71
+ "logits/rejected": 0.040130265057086945,
72
+ "logps/chosen": -384.62115478515625,
73
+ "logps/rejected": -369.37591552734375,
74
+ "loss": 0.0899,
75
+ "rewards/accuracies": 0.6499999761581421,
76
+ "rewards/chosen": -0.005014514084905386,
77
+ "rewards/margins": 0.00654798885807395,
78
+ "rewards/rejected": -0.01156250387430191,
79
  "step": 40
80
  },
81
  {
82
  "epoch": 0.1,
83
  "learning_rate": 4.999731868769026e-07,
84
+ "logits/chosen": 0.021576542407274246,
85
+ "logits/rejected": 0.04092331975698471,
86
+ "logps/chosen": -395.0044860839844,
87
+ "logps/rejected": -385.6026306152344,
88
+ "loss": 0.0905,
89
  "rewards/accuracies": 0.65625,
90
+ "rewards/chosen": -0.011928597465157509,
91
+ "rewards/margins": 0.01728428527712822,
92
+ "rewards/rejected": -0.02921288087964058,
93
  "step": 50
94
  },
95
  {
96
  "epoch": 0.13,
97
  "learning_rate": 4.990353313429303e-07,
98
+ "logits/chosen": 0.09396852552890778,
99
+ "logits/rejected": 0.177364319562912,
100
+ "logps/chosen": -373.46978759765625,
101
+ "logps/rejected": -350.2561950683594,
102
+ "loss": 0.0896,
103
+ "rewards/accuracies": 0.675000011920929,
104
+ "rewards/chosen": -0.022122707217931747,
105
+ "rewards/margins": 0.04510267823934555,
106
+ "rewards/rejected": -0.067225381731987,
107
  "step": 60
108
  },
109
  {
110
  "epoch": 0.15,
111
  "learning_rate": 4.967625656594781e-07,
112
+ "logits/chosen": 0.09231746941804886,
113
+ "logits/rejected": 0.10504136979579926,
114
+ "logps/chosen": -380.4566955566406,
115
+ "logps/rejected": -384.76495361328125,
116
+ "loss": 0.0895,
117
+ "rewards/accuracies": 0.675000011920929,
118
+ "rewards/chosen": -0.020214151591062546,
119
+ "rewards/margins": 0.044125162065029144,
120
+ "rewards/rejected": -0.06433931738138199,
121
  "step": 70
122
  },
123
  {
124
  "epoch": 0.17,
125
  "learning_rate": 4.93167072587771e-07,
126
+ "logits/chosen": 0.1812177449464798,
127
+ "logits/rejected": 0.2344866693019867,
128
+ "logps/chosen": -373.54779052734375,
129
+ "logps/rejected": -344.9815673828125,
130
+ "loss": 0.0887,
131
+ "rewards/accuracies": 0.706250011920929,
132
+ "rewards/chosen": -0.003499386366456747,
133
+ "rewards/margins": 0.11121924966573715,
134
+ "rewards/rejected": -0.11471863090991974,
135
  "step": 80
136
  },
137
  {
138
  "epoch": 0.19,
139
  "learning_rate": 4.882681251368548e-07,
140
+ "logits/chosen": 0.23078179359436035,
141
+ "logits/rejected": 0.3160688281059265,
142
+ "logps/chosen": -398.22735595703125,
143
+ "logps/rejected": -354.7359619140625,
144
+ "loss": 0.0854,
145
  "rewards/accuracies": 0.6875,
146
+ "rewards/chosen": -0.03982505947351456,
147
+ "rewards/margins": 0.12135788053274155,
148
+ "rewards/rejected": -0.1611829400062561,
149
  "step": 90
150
  },
151
  {
152
  "epoch": 0.21,
153
  "learning_rate": 4.820919832540181e-07,
154
+ "logits/chosen": 0.33522385358810425,
155
+ "logits/rejected": 0.34693339467048645,
156
+ "logps/chosen": -373.6068115234375,
157
+ "logps/rejected": -393.63311767578125,
158
+ "loss": 0.09,
159
+ "rewards/accuracies": 0.7250000238418579,
160
+ "rewards/chosen": -0.05229802802205086,
161
+ "rewards/margins": 0.1304590255022049,
162
+ "rewards/rejected": -0.18275703489780426,
163
  "step": 100
164
  },
165
  {
166
  "epoch": 0.21,
167
+ "eval_logits/chosen": 0.49261584877967834,
168
+ "eval_logits/rejected": 0.5302599668502808,
169
+ "eval_logps/chosen": -392.5748291015625,
170
+ "eval_logps/rejected": -418.8423767089844,
171
+ "eval_loss": 0.08443526923656464,
172
+ "eval_rewards/accuracies": 0.69921875,
173
+ "eval_rewards/chosen": -0.09445539116859436,
174
+ "eval_rewards/margins": 0.20123936235904694,
175
+ "eval_rewards/rejected": -0.2956947684288025,
176
+ "eval_runtime": 75.5045,
177
+ "eval_samples_per_second": 26.488,
178
+ "eval_steps_per_second": 0.424,
179
  "step": 100
180
  },
181
  {
182
  "epoch": 0.23,
183
  "learning_rate": 4.7467175306295647e-07,
184
+ "logits/chosen": 0.5233359336853027,
185
+ "logits/rejected": 0.5924205780029297,
186
+ "logps/chosen": -409.8135681152344,
187
+ "logps/rejected": -400.6418151855469,
188
+ "loss": 0.0775,
189
+ "rewards/accuracies": 0.699999988079071,
190
+ "rewards/chosen": -0.17791931331157684,
191
+ "rewards/margins": 0.2254853993654251,
192
+ "rewards/rejected": -0.40340471267700195,
193
  "step": 110
194
  },
195
  {
196
  "epoch": 0.25,
197
  "learning_rate": 4.6604720940421207e-07,
198
+ "logits/chosen": 0.6610409021377563,
199
+ "logits/rejected": 0.8009072542190552,
200
+ "logps/chosen": -459.3719787597656,
201
+ "logps/rejected": -480.128662109375,
202
+ "loss": 0.0697,
203
+ "rewards/accuracies": 0.762499988079071,
204
+ "rewards/chosen": -0.2562519609928131,
205
+ "rewards/margins": 0.2973101735115051,
206
+ "rewards/rejected": -0.5535621643066406,
207
  "step": 120
208
  },
209
  {
210
  "epoch": 0.27,
211
  "learning_rate": 4.5626458262912735e-07,
212
+ "logits/chosen": 0.8142817616462708,
213
+ "logits/rejected": 1.0136159658432007,
214
+ "logps/chosen": -453.57037353515625,
215
+ "logps/rejected": -438.6094665527344,
216
+ "loss": 0.0557,
217
+ "rewards/accuracies": 0.65625,
218
+ "rewards/chosen": -0.45035696029663086,
219
+ "rewards/margins": 0.2075636386871338,
220
+ "rewards/rejected": -0.6579206585884094,
221
  "step": 130
222
  },
223
  {
224
  "epoch": 0.29,
225
  "learning_rate": 4.453763107901675e-07,
226
+ "logits/chosen": 0.9267638325691223,
227
+ "logits/rejected": 0.9543718099594116,
228
+ "logps/chosen": -426.4134826660156,
229
+ "logps/rejected": -436.49261474609375,
230
+ "loss": 0.06,
231
+ "rewards/accuracies": 0.7562500238418579,
232
+ "rewards/chosen": -0.33891427516937256,
233
+ "rewards/margins": 0.302972674369812,
234
+ "rewards/rejected": -0.6418868899345398,
235
  "step": 140
236
  },
237
  {
238
  "epoch": 0.31,
239
  "learning_rate": 4.3344075855595097e-07,
240
+ "logits/chosen": 0.834929347038269,
241
+ "logits/rejected": 1.0096248388290405,
242
+ "logps/chosen": -383.9637756347656,
243
+ "logps/rejected": -392.84912109375,
244
+ "loss": 0.0588,
245
+ "rewards/accuracies": 0.706250011920929,
246
+ "rewards/chosen": -0.2390960454940796,
247
+ "rewards/margins": 0.35297515988349915,
248
+ "rewards/rejected": -0.5920711755752563,
249
  "step": 150
250
  },
251
  {
252
  "epoch": 0.33,
253
  "learning_rate": 4.2052190435769554e-07,
254
+ "logits/chosen": 1.0894076824188232,
255
+ "logits/rejected": 1.2157137393951416,
256
+ "logps/chosen": -429.09857177734375,
257
+ "logps/rejected": -461.9745178222656,
258
+ "loss": 0.0509,
259
+ "rewards/accuracies": 0.71875,
260
+ "rewards/chosen": -0.5552287101745605,
261
+ "rewards/margins": 0.3786623775959015,
262
+ "rewards/rejected": -0.9338911175727844,
263
  "step": 160
264
  },
265
  {
266
  "epoch": 0.36,
267
  "learning_rate": 4.0668899744407567e-07,
268
+ "logits/chosen": 0.9078506231307983,
269
+ "logits/rejected": 1.0372017621994019,
270
+ "logps/chosen": -482.3373107910156,
271
+ "logps/rejected": -479.88916015625,
272
+ "loss": 0.0479,
273
+ "rewards/accuracies": 0.6625000238418579,
274
+ "rewards/chosen": -0.505352795124054,
275
+ "rewards/margins": 0.26132458448410034,
276
+ "rewards/rejected": -0.7666773796081543,
277
  "step": 170
278
  },
279
  {
280
  "epoch": 0.38,
281
  "learning_rate": 3.920161866827889e-07,
282
+ "logits/chosen": 0.80833500623703,
283
+ "logits/rejected": 0.8488121032714844,
284
+ "logps/chosen": -413.3409118652344,
285
+ "logps/rejected": -438.3705139160156,
286
+ "loss": 0.0476,
287
+ "rewards/accuracies": 0.6875,
288
+ "rewards/chosen": -0.4049296975135803,
289
+ "rewards/margins": 0.3900560736656189,
290
+ "rewards/rejected": -0.7949857115745544,
291
  "step": 180
292
  },
293
  {
294
  "epoch": 0.4,
295
  "learning_rate": 3.765821230985757e-07,
296
+ "logits/chosen": 0.9091412425041199,
297
+ "logits/rejected": 1.0051593780517578,
298
+ "logps/chosen": -395.74383544921875,
299
+ "logps/rejected": -402.8367919921875,
300
+ "loss": 0.0478,
301
+ "rewards/accuracies": 0.7124999761581421,
302
+ "rewards/chosen": -0.4961649775505066,
303
+ "rewards/margins": 0.3637959361076355,
304
+ "rewards/rejected": -0.8599609136581421,
305
  "step": 190
306
  },
307
  {
308
  "epoch": 0.42,
309
  "learning_rate": 3.604695382782159e-07,
310
+ "logits/chosen": 1.0421111583709717,
311
+ "logits/rejected": 1.1686071157455444,
312
+ "logps/chosen": -422.24224853515625,
313
+ "logps/rejected": -469.1251525878906,
314
+ "loss": 0.0405,
315
+ "rewards/accuracies": 0.7437499761581421,
316
+ "rewards/chosen": -0.7005800008773804,
317
+ "rewards/margins": 0.46449971199035645,
318
+ "rewards/rejected": -1.1650797128677368,
319
  "step": 200
320
  },
321
  {
322
  "epoch": 0.42,
323
+ "eval_logits/chosen": 1.1859312057495117,
324
+ "eval_logits/rejected": 1.2733540534973145,
325
+ "eval_logps/chosen": -449.3788757324219,
326
+ "eval_logps/rejected": -505.84661865234375,
327
+ "eval_loss": 0.045209601521492004,
328
+ "eval_rewards/accuracies": 0.75390625,
329
+ "eval_rewards/chosen": -0.6624964475631714,
330
+ "eval_rewards/margins": 0.5032405257225037,
331
+ "eval_rewards/rejected": -1.1657369136810303,
332
+ "eval_runtime": 75.0855,
333
+ "eval_samples_per_second": 26.636,
334
+ "eval_steps_per_second": 0.426,
335
  "step": 200
336
  },
337
  {
338
  "epoch": 0.44,
339
  "learning_rate": 3.4376480090239047e-07,
340
+ "logits/chosen": 0.9289053082466125,
341
+ "logits/rejected": 1.0322377681732178,
342
+ "logps/chosen": -454.09521484375,
343
+ "logps/rejected": -484.48956298828125,
344
+ "loss": 0.0428,
345
+ "rewards/accuracies": 0.7250000238418579,
346
+ "rewards/chosen": -0.5330354571342468,
347
+ "rewards/margins": 0.47441625595092773,
348
+ "rewards/rejected": -1.0074517726898193,
349
  "step": 210
350
  },
351
  {
352
  "epoch": 0.46,
353
  "learning_rate": 3.265574537815398e-07,
354
+ "logits/chosen": 0.6325788497924805,
355
+ "logits/rejected": 0.8454742431640625,
356
+ "logps/chosen": -443.6888732910156,
357
+ "logps/rejected": -444.2510681152344,
358
+ "loss": 0.051,
359
+ "rewards/accuracies": 0.7250000238418579,
360
+ "rewards/chosen": -0.4299241006374359,
361
+ "rewards/margins": 0.41193485260009766,
362
+ "rewards/rejected": -0.8418590426445007,
363
  "step": 220
364
  },
365
  {
366
  "epoch": 0.48,
367
  "learning_rate": 3.0893973387735683e-07,
368
+ "logits/chosen": 0.8997888565063477,
369
+ "logits/rejected": 0.9853512048721313,
370
+ "logps/chosen": -413.89520263671875,
371
+ "logps/rejected": -458.99676513671875,
372
+ "loss": 0.0525,
373
+ "rewards/accuracies": 0.731249988079071,
374
+ "rewards/chosen": -0.5308324694633484,
375
+ "rewards/margins": 0.4597201943397522,
376
+ "rewards/rejected": -0.9905527830123901,
377
  "step": 230
378
  },
379
  {
380
  "epoch": 0.5,
381
  "learning_rate": 2.910060778827554e-07,
382
+ "logits/chosen": 1.0547417402267456,
383
+ "logits/rejected": 1.1306800842285156,
384
+ "logps/chosen": -493.91790771484375,
385
+ "logps/rejected": -539.1799926757812,
386
+ "loss": 0.0471,
387
+ "rewards/accuracies": 0.7124999761581421,
388
+ "rewards/chosen": -0.6113244295120239,
389
+ "rewards/margins": 0.5182110667228699,
390
+ "rewards/rejected": -1.1295355558395386,
391
  "step": 240
392
  },
393
  {
394
  "epoch": 0.52,
395
  "learning_rate": 2.7285261601056697e-07,
396
+ "logits/chosen": 1.2281643152236938,
397
+ "logits/rejected": 1.359076976776123,
398
+ "logps/chosen": -466.77001953125,
399
+ "logps/rejected": -483.91259765625,
400
+ "loss": 0.0419,
401
+ "rewards/accuracies": 0.6625000238418579,
402
+ "rewards/chosen": -0.7258759140968323,
403
+ "rewards/margins": 0.42711353302001953,
404
+ "rewards/rejected": -1.152989387512207,
405
  "step": 250
406
  },
407
  {
408
  "epoch": 0.54,
409
  "learning_rate": 2.5457665670441937e-07,
410
+ "logits/chosen": 1.2255347967147827,
411
+ "logits/rejected": 1.462003469467163,
412
+ "logps/chosen": -491.76190185546875,
413
+ "logps/rejected": -505.47161865234375,
414
+ "loss": 0.0451,
415
+ "rewards/accuracies": 0.7124999761581421,
416
+ "rewards/chosen": -0.7059242725372314,
417
+ "rewards/margins": 0.6359472274780273,
418
+ "rewards/rejected": -1.3418715000152588,
419
  "step": 260
420
  },
421
  {
422
  "epoch": 0.57,
423
  "learning_rate": 2.3627616503391812e-07,
424
+ "logits/chosen": 1.3674428462982178,
425
+ "logits/rejected": 1.578064203262329,
426
+ "logps/chosen": -486.397216796875,
427
+ "logps/rejected": -492.1827087402344,
428
+ "loss": 0.0472,
429
+ "rewards/accuracies": 0.6937500238418579,
430
+ "rewards/chosen": -0.7773429155349731,
431
+ "rewards/margins": 0.38945746421813965,
432
+ "rewards/rejected": -1.1668003797531128,
433
  "step": 270
434
  },
435
  {
436
  "epoch": 0.59,
437
  "learning_rate": 2.1804923757009882e-07,
438
+ "logits/chosen": 1.366081953048706,
439
+ "logits/rejected": 1.5207383632659912,
440
+ "logps/chosen": -477.0743103027344,
441
+ "logps/rejected": -530.8953857421875,
442
+ "loss": 0.0445,
443
+ "rewards/accuracies": 0.675000011920929,
444
+ "rewards/chosen": -0.8941423296928406,
445
+ "rewards/margins": 0.4790104925632477,
446
+ "rewards/rejected": -1.3731528520584106,
447
  "step": 280
448
  },
449
  {
450
  "epoch": 0.61,
451
  "learning_rate": 1.9999357655598891e-07,
452
+ "logits/chosen": 1.2689809799194336,
453
+ "logits/rejected": 1.4011085033416748,
454
+ "logps/chosen": -438.982421875,
455
+ "logps/rejected": -469.45703125,
456
+ "loss": 0.0464,
457
+ "rewards/accuracies": 0.7124999761581421,
458
+ "rewards/chosen": -0.62468022108078,
459
+ "rewards/margins": 0.513271689414978,
460
+ "rewards/rejected": -1.1379519701004028,
461
  "step": 290
462
  },
463
  {
464
  "epoch": 0.63,
465
  "learning_rate": 1.8220596619089573e-07,
466
+ "logits/chosen": 1.1505718231201172,
467
+ "logits/rejected": 1.4240622520446777,
468
+ "logps/chosen": -458.03631591796875,
469
+ "logps/rejected": -443.11712646484375,
470
+ "loss": 0.0479,
471
+ "rewards/accuracies": 0.6625000238418579,
472
+ "rewards/chosen": -0.6710134148597717,
473
+ "rewards/margins": 0.39567166566848755,
474
+ "rewards/rejected": -1.0666849613189697,
475
  "step": 300
476
  },
477
  {
478
  "epoch": 0.63,
479
+ "eval_logits/chosen": 1.2982094287872314,
480
+ "eval_logits/rejected": 1.409311056137085,
481
+ "eval_logps/chosen": -435.2132568359375,
482
+ "eval_logps/rejected": -501.30841064453125,
483
+ "eval_loss": 0.047696553170681,
484
+ "eval_rewards/accuracies": 0.73828125,
485
+ "eval_rewards/chosen": -0.5208398699760437,
486
+ "eval_rewards/margins": 0.5995149612426758,
487
+ "eval_rewards/rejected": -1.1203548908233643,
488
+ "eval_runtime": 75.296,
489
+ "eval_samples_per_second": 26.562,
490
+ "eval_steps_per_second": 0.425,
491
  "step": 300
492
  },
493
  {
494
  "epoch": 0.65,
495
  "learning_rate": 1.647817538357072e-07,
496
+ "logits/chosen": 1.2780801057815552,
497
+ "logits/rejected": 1.3399560451507568,
498
+ "logps/chosen": -475.42413330078125,
499
+ "logps/rejected": -517.4520263671875,
500
+ "loss": 0.0478,
501
+ "rewards/accuracies": 0.6499999761581421,
502
+ "rewards/chosen": -0.7529923319816589,
503
+ "rewards/margins": 0.4368392825126648,
504
+ "rewards/rejected": -1.1898316144943237,
505
  "step": 310
506
  },
507
  {
508
  "epoch": 0.67,
509
  "learning_rate": 1.478143389201113e-07,
510
+ "logits/chosen": 1.198677897453308,
511
+ "logits/rejected": 1.4085700511932373,
512
+ "logps/chosen": -498.35711669921875,
513
+ "logps/rejected": -497.4380798339844,
514
+ "loss": 0.0424,
515
+ "rewards/accuracies": 0.65625,
516
+ "rewards/chosen": -0.6401562690734863,
517
+ "rewards/margins": 0.48012202978134155,
518
+ "rewards/rejected": -1.1202783584594727,
519
  "step": 320
520
  },
521
  {
522
  "epoch": 0.69,
523
  "learning_rate": 1.3139467229135998e-07,
524
+ "logits/chosen": 1.2183105945587158,
525
+ "logits/rejected": 1.2747819423675537,
526
+ "logps/chosen": -442.5284118652344,
527
+ "logps/rejected": -533.216796875,
528
+ "loss": 0.0454,
529
+ "rewards/accuracies": 0.737500011920929,
530
+ "rewards/chosen": -0.5910875201225281,
531
+ "rewards/margins": 0.5799761414527893,
532
+ "rewards/rejected": -1.1710636615753174,
533
  "step": 330
534
  },
535
  {
536
  "epoch": 0.71,
537
  "learning_rate": 1.1561076868822755e-07,
538
+ "logits/chosen": 1.203604817390442,
539
+ "logits/rejected": 1.1832085847854614,
540
+ "logps/chosen": -441.4521484375,
541
+ "logps/rejected": -512.8982543945312,
542
+ "loss": 0.0428,
543
+ "rewards/accuracies": 0.699999988079071,
544
+ "rewards/chosen": -0.7571262121200562,
545
+ "rewards/margins": 0.4640630781650543,
546
+ "rewards/rejected": -1.221189260482788,
547
  "step": 340
548
  },
549
  {
550
  "epoch": 0.73,
551
  "learning_rate": 1.0054723495346482e-07,
552
+ "logits/chosen": 1.3052194118499756,
553
+ "logits/rejected": 1.382683515548706,
554
+ "logps/chosen": -465.3661193847656,
555
+ "logps/rejected": -528.7847290039062,
556
+ "loss": 0.0412,
557
+ "rewards/accuracies": 0.737500011920929,
558
+ "rewards/chosen": -0.7757940292358398,
559
+ "rewards/margins": 0.4744884967803955,
560
+ "rewards/rejected": -1.2502825260162354,
561
  "step": 350
562
  },
563
  {
564
  "epoch": 0.75,
565
  "learning_rate": 8.628481651367875e-08,
566
+ "logits/chosen": 1.1976938247680664,
567
+ "logits/rejected": 1.432969331741333,
568
+ "logps/chosen": -491.15771484375,
569
+ "logps/rejected": -515.0520629882812,
570
+ "loss": 0.0446,
571
  "rewards/accuracies": 0.706250011920929,
572
+ "rewards/chosen": -0.6491819620132446,
573
+ "rewards/margins": 0.6244359612464905,
574
+ "rewards/rejected": -1.2736178636550903,
575
  "step": 360
576
  },
577
  {
578
  "epoch": 0.77,
579
  "learning_rate": 7.289996455765748e-08,
580
+ "logits/chosen": 1.192779541015625,
581
+ "logits/rejected": 1.324210524559021,
582
+ "logps/chosen": -504.5486755371094,
583
+ "logps/rejected": -508.7030334472656,
584
+ "loss": 0.0435,
585
+ "rewards/accuracies": 0.699999988079071,
586
+ "rewards/chosen": -0.7155844569206238,
587
+ "rewards/margins": 0.5151349306106567,
588
+ "rewards/rejected": -1.2307194471359253,
589
  "step": 370
590
  },
591
  {
592
  "epoch": 0.8,
593
  "learning_rate": 6.046442623320145e-08,
594
+ "logits/chosen": 1.223356008529663,
595
+ "logits/rejected": 1.4434764385223389,
596
+ "logps/chosen": -474.7169494628906,
597
+ "logps/rejected": -518.0782470703125,
598
+ "loss": 0.0476,
599
+ "rewards/accuracies": 0.737500011920929,
600
+ "rewards/chosen": -0.6729675531387329,
601
+ "rewards/margins": 0.6387326717376709,
602
+ "rewards/rejected": -1.3117002248764038,
603
  "step": 380
604
  },
605
  {
606
  "epoch": 0.82,
607
  "learning_rate": 4.904486005914027e-08,
608
+ "logits/chosen": 1.3060978651046753,
609
+ "logits/rejected": 1.4896109104156494,
610
+ "logps/chosen": -470.46661376953125,
611
+ "logps/rejected": -502.4981384277344,
612
+ "loss": 0.0482,
613
+ "rewards/accuracies": 0.7437499761581421,
614
+ "rewards/chosen": -0.6783354878425598,
615
+ "rewards/margins": 0.5045996904373169,
616
+ "rewards/rejected": -1.1829349994659424,
617
  "step": 390
618
  },
619
  {
620
  "epoch": 0.84,
621
  "learning_rate": 3.8702478614051345e-08,
622
+ "logits/chosen": 1.3413165807724,
623
+ "logits/rejected": 1.4800562858581543,
624
+ "logps/chosen": -450.84844970703125,
625
+ "logps/rejected": -509.7266540527344,
626
+ "loss": 0.0457,
627
+ "rewards/accuracies": 0.65625,
628
+ "rewards/chosen": -0.7674819231033325,
629
+ "rewards/margins": 0.4173991084098816,
630
+ "rewards/rejected": -1.1848809719085693,
631
  "step": 400
632
  },
633
  {
634
  "epoch": 0.84,
635
+ "eval_logits/chosen": 1.491492748260498,
636
+ "eval_logits/rejected": 1.6154029369354248,
637
+ "eval_logps/chosen": -448.419677734375,
638
+ "eval_logps/rejected": -518.3443603515625,
639
+ "eval_loss": 0.044891636818647385,
640
+ "eval_rewards/accuracies": 0.73828125,
641
+ "eval_rewards/chosen": -0.6529037952423096,
642
+ "eval_rewards/margins": 0.6378109455108643,
643
+ "eval_rewards/rejected": -1.2907147407531738,
644
+ "eval_runtime": 74.6873,
645
+ "eval_samples_per_second": 26.778,
646
+ "eval_steps_per_second": 0.428,
647
  "step": 400
648
  },
649
  {
650
  "epoch": 0.86,
651
  "learning_rate": 2.9492720416985e-08,
652
+ "logits/chosen": 1.3658090829849243,
653
+ "logits/rejected": 1.523946762084961,
654
+ "logps/chosen": -461.0426330566406,
655
+ "logps/rejected": -491.6429138183594,
656
+ "loss": 0.045,
657
  "rewards/accuracies": 0.706250011920929,
658
+ "rewards/chosen": -0.6857269406318665,
659
+ "rewards/margins": 0.5137700438499451,
660
+ "rewards/rejected": -1.1994969844818115,
661
  "step": 410
662
  },
663
  {
664
  "epoch": 0.88,
665
  "learning_rate": 2.1464952759020856e-08,
666
+ "logits/chosen": 1.3796783685684204,
667
+ "logits/rejected": 1.5178402662277222,
668
+ "logps/chosen": -454.60455322265625,
669
+ "logps/rejected": -483.65704345703125,
670
+ "loss": 0.0418,
671
+ "rewards/accuracies": 0.768750011920929,
672
+ "rewards/chosen": -0.6705530285835266,
673
+ "rewards/margins": 0.604373574256897,
674
+ "rewards/rejected": -1.2749265432357788,
675
  "step": 420
676
  },
677
  {
678
  "epoch": 0.9,
679
  "learning_rate": 1.4662207078575684e-08,
680
+ "logits/chosen": 1.334680199623108,
681
+ "logits/rejected": 1.4741976261138916,
682
+ "logps/chosen": -504.280029296875,
683
+ "logps/rejected": -529.8871459960938,
684
+ "loss": 0.0453,
685
+ "rewards/accuracies": 0.699999988079071,
686
+ "rewards/chosen": -0.7305961847305298,
687
+ "rewards/margins": 0.5881385207176208,
688
+ "rewards/rejected": -1.3187347650527954,
689
  "step": 430
690
  },
691
  {
692
  "epoch": 0.92,
693
  "learning_rate": 9.12094829893642e-09,
694
+ "logits/chosen": 1.3827157020568848,
695
+ "logits/rejected": 1.5478546619415283,
696
+ "logps/chosen": -453.01171875,
697
+ "logps/rejected": -480.3030700683594,
698
+ "loss": 0.0414,
699
+ "rewards/accuracies": 0.699999988079071,
700
+ "rewards/chosen": -0.7755357027053833,
701
+ "rewards/margins": 0.5378071069717407,
702
+ "rewards/rejected": -1.313342809677124,
703
  "step": 440
704
  },
705
  {
706
  "epoch": 0.94,
707
  "learning_rate": 4.8708793644441086e-09,
708
+ "logits/chosen": 1.2280631065368652,
709
+ "logits/rejected": 1.454526662826538,
710
+ "logps/chosen": -487.4305114746094,
711
+ "logps/rejected": -500.71087646484375,
712
+ "loss": 0.0425,
713
+ "rewards/accuracies": 0.65625,
714
+ "rewards/chosen": -0.6377500295639038,
715
+ "rewards/margins": 0.5590785145759583,
716
+ "rewards/rejected": -1.1968284845352173,
717
  "step": 450
718
  },
719
  {
720
  "epoch": 0.96,
721
  "learning_rate": 1.9347820230782295e-09,
722
+ "logits/chosen": 1.336721658706665,
723
+ "logits/rejected": 1.4986612796783447,
724
+ "logps/chosen": -455.5997619628906,
725
+ "logps/rejected": -474.46038818359375,
726
+ "loss": 0.0425,
727
+ "rewards/accuracies": 0.7124999761581421,
728
+ "rewards/chosen": -0.7689257264137268,
729
+ "rewards/margins": 0.4747004508972168,
730
+ "rewards/rejected": -1.243626356124878,
731
  "step": 460
732
  },
733
  {
734
  "epoch": 0.98,
735
  "learning_rate": 3.2839470889836627e-10,
736
+ "logits/chosen": 1.2109500169754028,
737
+ "logits/rejected": 1.3351854085922241,
738
+ "logps/chosen": -490.6439514160156,
739
+ "logps/rejected": -541.4273681640625,
740
+ "loss": 0.0421,
741
  "rewards/accuracies": 0.75,
742
+ "rewards/chosen": -0.7248164415359497,
743
+ "rewards/margins": 0.548802375793457,
744
+ "rewards/rejected": -1.2736186981201172,
745
  "step": 470
746
  },
747
  {
748
  "epoch": 1.0,
749
  "step": 477,
750
  "total_flos": 0.0,
751
+ "train_loss": 0.0564979040210352,
752
+ "train_runtime": 4410.0999,
753
+ "train_samples_per_second": 13.862,
754
  "train_steps_per_second": 0.108
755
  }
756
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83255af7dbd2cea8368e0e7405c859e40ac92e8bf2f57a4290284d554cd32666
3
- size 6520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33b5326d4ea988e8ae29143a1ab2dfc0048f16de81f7d0de6e419d974560da26
3
+ size 5944