ehzoah commited on
Commit
1aef2a0
·
verified ·
1 Parent(s): 7ed622c

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +1,65 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: meta-llama/Llama-3.2-1B
4
+ tags:
5
+ - alignment-handbook
6
+ - generated_from_trainer
7
+ datasets:
8
+ - HuggingFaceH4/ultrachat_200k
9
+ model-index:
10
+ - name: Llama-3.2-1B-sft-full
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Llama-3.2-1B-sft-full
18
+
19
+ This model is a fine-tuned version of [/workspace/jihaozhe/models/Llama-3.2-1B](https://huggingface.co//workspace/jihaozhe/models/Llama-3.2-1B) on the HuggingFaceH4/ultrachat_200k dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.2660
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 8
46
+ - total_train_batch_size: 128
47
+ - total_eval_batch_size: 64
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 1
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:-----:|:----:|:---------------:|
57
+ | 1.2488 | 1.0 | 951 | 1.2660 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.44.2
63
+ - Pytorch 2.4.1+cu121
64
+ - Datasets 3.0.0
65
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 1.266036868095398,
4
+ "eval_runtime": 32.4102,
5
+ "eval_samples": 23110,
6
+ "eval_samples_per_second": 415.24,
7
+ "eval_steps_per_second": 6.51,
8
+ "total_flos": 101091718987776.0,
9
+ "train_loss": 1.289618753484371,
10
+ "train_runtime": 1098.6048,
11
+ "train_samples": 207865,
12
+ "train_samples_per_second": 110.718,
13
+ "train_steps_per_second": 0.866
14
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/jihaozhe/models/Llama-3.2-1B",
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
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 32.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": true,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.44.2",
34
+ "use_cache": true,
35
+ "vocab_size": 128256
36
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 1.266036868095398,
4
+ "eval_runtime": 32.4102,
5
+ "eval_samples": 23110,
6
+ "eval_samples_per_second": 415.24,
7
+ "eval_steps_per_second": 6.51
8
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.44.2"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f5afbac3b4943fa0be90fe222198b8f203ce0a5efad8211831167dee99db1e4
3
+ size 2471645608
runs/Oct10_13-03-19_node090/events.out.tfevents.1728565974.node090.645.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a459c02589738e5aee3f792f5535a3ea1d0c583d932532411feedd9bfea6c9f
3
+ size 46658
runs/Oct10_13-03-19_node090/events.out.tfevents.1728567108.node090.645.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9e45a4f2acd92ba9c63692901ccd34f1761d655ebc58470749ded15c0423dd
3
+ size 359
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|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 ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% 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 %}",
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 ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 101091718987776.0,
4
+ "train_loss": 1.289618753484371,
5
+ "train_runtime": 1098.6048,
6
+ "train_samples": 207865,
7
+ "train_samples_per_second": 110.718,
8
+ "train_steps_per_second": 0.866
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1387 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 951,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0010515247108307045,
13
+ "grad_norm": 9.591360424317704,
14
+ "learning_rate": 2.0833333333333333e-07,
15
+ "loss": 1.5585,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.005257623554153523,
20
+ "grad_norm": 9.792129596772575,
21
+ "learning_rate": 1.0416666666666667e-06,
22
+ "loss": 1.5717,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.010515247108307046,
27
+ "grad_norm": 3.5907937606092246,
28
+ "learning_rate": 2.0833333333333334e-06,
29
+ "loss": 1.54,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.015772870662460567,
34
+ "grad_norm": 2.305935396467309,
35
+ "learning_rate": 3.125e-06,
36
+ "loss": 1.5164,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.02103049421661409,
41
+ "grad_norm": 1.3430988630406788,
42
+ "learning_rate": 4.166666666666667e-06,
43
+ "loss": 1.4398,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.026288117770767613,
48
+ "grad_norm": 1.3395602302159622,
49
+ "learning_rate": 5.208333333333334e-06,
50
+ "loss": 1.4374,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.031545741324921134,
55
+ "grad_norm": 0.927990494487892,
56
+ "learning_rate": 6.25e-06,
57
+ "loss": 1.3952,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.03680336487907466,
62
+ "grad_norm": 0.817869963107523,
63
+ "learning_rate": 7.291666666666667e-06,
64
+ "loss": 1.3688,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.04206098843322818,
69
+ "grad_norm": 0.8099795395904227,
70
+ "learning_rate": 8.333333333333334e-06,
71
+ "loss": 1.3543,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.0473186119873817,
76
+ "grad_norm": 0.8196989977897423,
77
+ "learning_rate": 9.375000000000001e-06,
78
+ "loss": 1.4065,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.052576235541535225,
83
+ "grad_norm": 0.7891645835706297,
84
+ "learning_rate": 1.0416666666666668e-05,
85
+ "loss": 1.3719,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.05783385909568875,
90
+ "grad_norm": 0.7730662990445142,
91
+ "learning_rate": 1.1458333333333333e-05,
92
+ "loss": 1.3534,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.06309148264984227,
97
+ "grad_norm": 0.8436428208666454,
98
+ "learning_rate": 1.25e-05,
99
+ "loss": 1.3484,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.0683491062039958,
104
+ "grad_norm": 0.930633139226441,
105
+ "learning_rate": 1.3541666666666668e-05,
106
+ "loss": 1.3339,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.07360672975814932,
111
+ "grad_norm": 1.2035603215763095,
112
+ "learning_rate": 1.4583333333333333e-05,
113
+ "loss": 1.3577,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.07886435331230283,
118
+ "grad_norm": 0.9963124148010385,
119
+ "learning_rate": 1.5625e-05,
120
+ "loss": 1.3504,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.08412197686645637,
125
+ "grad_norm": 0.7705000485956546,
126
+ "learning_rate": 1.6666666666666667e-05,
127
+ "loss": 1.3316,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.08937960042060988,
132
+ "grad_norm": 0.892949375851743,
133
+ "learning_rate": 1.7708333333333335e-05,
134
+ "loss": 1.3289,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.0946372239747634,
139
+ "grad_norm": 0.909849658521525,
140
+ "learning_rate": 1.8750000000000002e-05,
141
+ "loss": 1.3311,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.09989484752891693,
146
+ "grad_norm": 0.8255721604143701,
147
+ "learning_rate": 1.979166666666667e-05,
148
+ "loss": 1.3224,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.10515247108307045,
153
+ "grad_norm": 0.8253137907707107,
154
+ "learning_rate": 1.9998919935516768e-05,
155
+ "loss": 1.3291,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.11041009463722397,
160
+ "grad_norm": 0.8322397994562853,
161
+ "learning_rate": 1.999453257340926e-05,
162
+ "loss": 1.321,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.1156677181913775,
167
+ "grad_norm": 0.8169700972120059,
168
+ "learning_rate": 1.9986771889316172e-05,
169
+ "loss": 1.3145,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.12092534174553102,
174
+ "grad_norm": 0.8054378165910604,
175
+ "learning_rate": 1.9975640502598243e-05,
176
+ "loss": 1.3537,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.12618296529968454,
181
+ "grad_norm": 0.8851185792466449,
182
+ "learning_rate": 1.9961142170284762e-05,
183
+ "loss": 1.3081,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.13144058885383805,
188
+ "grad_norm": 0.7983608745240434,
189
+ "learning_rate": 1.9943281785805483e-05,
190
+ "loss": 1.3235,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.1366982124079916,
195
+ "grad_norm": 0.8101924460502825,
196
+ "learning_rate": 1.9922065377339037e-05,
197
+ "loss": 1.3234,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.14195583596214512,
202
+ "grad_norm": 0.8181918475547033,
203
+ "learning_rate": 1.98975001057783e-05,
204
+ "loss": 1.3275,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.14721345951629863,
209
+ "grad_norm": 0.8204094295073951,
210
+ "learning_rate": 1.986959426231349e-05,
211
+ "loss": 1.3191,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.15247108307045215,
216
+ "grad_norm": 0.8193214439419285,
217
+ "learning_rate": 1.983835726563373e-05,
218
+ "loss": 1.3151,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.15772870662460567,
223
+ "grad_norm": 0.8008496299830612,
224
+ "learning_rate": 1.9803799658748096e-05,
225
+ "loss": 1.3173,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.16298633017875921,
230
+ "grad_norm": 0.8976369540265376,
231
+ "learning_rate": 1.976593310542718e-05,
232
+ "loss": 1.3193,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.16824395373291273,
237
+ "grad_norm": 0.8219320759522418,
238
+ "learning_rate": 1.9724770386266363e-05,
239
+ "loss": 1.3074,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.17350157728706625,
244
+ "grad_norm": 0.7917666416050304,
245
+ "learning_rate": 1.968032539437215e-05,
246
+ "loss": 1.3229,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.17875920084121977,
251
+ "grad_norm": 0.8468899498707804,
252
+ "learning_rate": 1.963261313067302e-05,
253
+ "loss": 1.3053,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.18401682439537329,
258
+ "grad_norm": 0.7826255604907222,
259
+ "learning_rate": 1.958164969885636e-05,
260
+ "loss": 1.2994,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.1892744479495268,
265
+ "grad_norm": 0.7854651229191463,
266
+ "learning_rate": 1.9527452299933192e-05,
267
+ "loss": 1.2933,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.19453207150368035,
272
+ "grad_norm": 0.8335518596689603,
273
+ "learning_rate": 1.9470039226432562e-05,
274
+ "loss": 1.3053,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.19978969505783387,
279
+ "grad_norm": 0.7925970741738505,
280
+ "learning_rate": 1.9409429856227487e-05,
281
+ "loss": 1.3118,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.20504731861198738,
286
+ "grad_norm": 0.9022667633817576,
287
+ "learning_rate": 1.934564464599461e-05,
288
+ "loss": 1.3006,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.2103049421661409,
293
+ "grad_norm": 0.7846381821366918,
294
+ "learning_rate": 1.9278705124309724e-05,
295
+ "loss": 1.3019,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.21556256572029442,
300
+ "grad_norm": 0.8523088106258838,
301
+ "learning_rate": 1.9208633884381528e-05,
302
+ "loss": 1.3096,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.22082018927444794,
307
+ "grad_norm": 0.7773410227959319,
308
+ "learning_rate": 1.913545457642601e-05,
309
+ "loss": 1.3292,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.22607781282860148,
314
+ "grad_norm": 0.7700372006553495,
315
+ "learning_rate": 1.9059191899684154e-05,
316
+ "loss": 1.3039,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.231335436382755,
321
+ "grad_norm": 0.888501634972992,
322
+ "learning_rate": 1.8979871594085482e-05,
323
+ "loss": 1.2877,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.23659305993690852,
328
+ "grad_norm": 1.1002462859379447,
329
+ "learning_rate": 1.8897520431560435e-05,
330
+ "loss": 1.3015,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.24185068349106204,
335
+ "grad_norm": 0.8737204056440837,
336
+ "learning_rate": 1.881216620700437e-05,
337
+ "loss": 1.3115,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.24710830704521555,
342
+ "grad_norm": 0.789475981373434,
343
+ "learning_rate": 1.872383772889634e-05,
344
+ "loss": 1.3046,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.25236593059936907,
349
+ "grad_norm": 0.7857837110627846,
350
+ "learning_rate": 1.863256480957574e-05,
351
+ "loss": 1.314,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.2576235541535226,
356
+ "grad_norm": 0.8735939515101088,
357
+ "learning_rate": 1.853837825518014e-05,
358
+ "loss": 1.2965,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.2628811777076761,
363
+ "grad_norm": 0.8274285162573444,
364
+ "learning_rate": 1.844130985524771e-05,
365
+ "loss": 1.2847,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.26813880126182965,
370
+ "grad_norm": 0.9655358070442068,
371
+ "learning_rate": 1.83413923719877e-05,
372
+ "loss": 1.3033,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.2733964248159832,
377
+ "grad_norm": 0.784933865330852,
378
+ "learning_rate": 1.8238659529222672e-05,
379
+ "loss": 1.2964,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.2786540483701367,
384
+ "grad_norm": 0.8072089928871935,
385
+ "learning_rate": 1.813314600100612e-05,
386
+ "loss": 1.3,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.28391167192429023,
391
+ "grad_norm": 0.7600500534210821,
392
+ "learning_rate": 1.802488739991941e-05,
393
+ "loss": 1.2897,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.2891692954784437,
398
+ "grad_norm": 0.7716489846603405,
399
+ "learning_rate": 1.7913920265051947e-05,
400
+ "loss": 1.2994,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.29442691903259727,
405
+ "grad_norm": 0.8439416659266935,
406
+ "learning_rate": 1.7800282049668593e-05,
407
+ "loss": 1.3146,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.2996845425867508,
412
+ "grad_norm": 0.7413366975663128,
413
+ "learning_rate": 1.7684011108568593e-05,
414
+ "loss": 1.3157,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.3049421661409043,
419
+ "grad_norm": 0.9324094146103826,
420
+ "learning_rate": 1.7565146685140168e-05,
421
+ "loss": 1.2944,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.31019978969505785,
426
+ "grad_norm": 0.7497525070350954,
427
+ "learning_rate": 1.7443728898115228e-05,
428
+ "loss": 1.3041,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.31545741324921134,
433
+ "grad_norm": 0.7274267632257158,
434
+ "learning_rate": 1.7319798728028617e-05,
435
+ "loss": 1.2855,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.3207150368033649,
440
+ "grad_norm": 0.7306525895599777,
441
+ "learning_rate": 1.7193398003386514e-05,
442
+ "loss": 1.2967,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.32597266035751843,
447
+ "grad_norm": 0.7718504682998596,
448
+ "learning_rate": 1.7064569386548586e-05,
449
+ "loss": 1.3116,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.3312302839116719,
454
+ "grad_norm": 0.7002164572114049,
455
+ "learning_rate": 1.6933356359328756e-05,
456
+ "loss": 1.2812,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.33648790746582546,
461
+ "grad_norm": 0.757112323690967,
462
+ "learning_rate": 1.679980320831934e-05,
463
+ "loss": 1.2654,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.34174553101997895,
468
+ "grad_norm": 0.7509591301953,
469
+ "learning_rate": 1.6663955009943603e-05,
470
+ "loss": 1.2755,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.3470031545741325,
475
+ "grad_norm": 0.7896423206563724,
476
+ "learning_rate": 1.6525857615241686e-05,
477
+ "loss": 1.291,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.352260778128286,
482
+ "grad_norm": 0.8538357892614057,
483
+ "learning_rate": 1.6385557634395138e-05,
484
+ "loss": 1.3,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.35751840168243953,
489
+ "grad_norm": 0.8257603179264333,
490
+ "learning_rate": 1.624310242099518e-05,
491
+ "loss": 1.2825,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.3627760252365931,
496
+ "grad_norm": 0.7506565139625698,
497
+ "learning_rate": 1.609854005606009e-05,
498
+ "loss": 1.2903,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.36803364879074657,
503
+ "grad_norm": 0.7962631813094616,
504
+ "learning_rate": 1.5951919331807052e-05,
505
+ "loss": 1.32,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.3732912723449001,
510
+ "grad_norm": 0.7846004527594455,
511
+ "learning_rate": 1.5803289735183952e-05,
512
+ "loss": 1.3094,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.3785488958990536,
517
+ "grad_norm": 0.7529193912570731,
518
+ "learning_rate": 1.565270143116672e-05,
519
+ "loss": 1.3097,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.38380651945320715,
524
+ "grad_norm": 0.8450472817355228,
525
+ "learning_rate": 1.5500205245827814e-05,
526
+ "loss": 1.2954,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.3890641430073607,
531
+ "grad_norm": 0.7884988874909659,
532
+ "learning_rate": 1.5345852649181555e-05,
533
+ "loss": 1.2774,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.3943217665615142,
538
+ "grad_norm": 0.7181038933510216,
539
+ "learning_rate": 1.5189695737812153e-05,
540
+ "loss": 1.2788,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.39957939011566773,
545
+ "grad_norm": 0.7398759340722635,
546
+ "learning_rate": 1.503178721729022e-05,
547
+ "loss": 1.2825,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.4048370136698212,
552
+ "grad_norm": 0.6946338532175111,
553
+ "learning_rate": 1.4872180384383772e-05,
554
+ "loss": 1.2945,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.41009463722397477,
559
+ "grad_norm": 0.7312230396618198,
560
+ "learning_rate": 1.4710929109069674e-05,
561
+ "loss": 1.2774,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.4153522607781283,
566
+ "grad_norm": 0.685269793573933,
567
+ "learning_rate": 1.4548087816351616e-05,
568
+ "loss": 1.2691,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.4206098843322818,
573
+ "grad_norm": 0.7367025121344211,
574
+ "learning_rate": 1.4383711467890776e-05,
575
+ "loss": 1.3029,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.42586750788643535,
580
+ "grad_norm": 0.954670307639884,
581
+ "learning_rate": 1.4217855543455323e-05,
582
+ "loss": 1.2846,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.43112513144058884,
587
+ "grad_norm": 0.7884436143443709,
588
+ "learning_rate": 1.4050576022195084e-05,
589
+ "loss": 1.2686,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.4363827549947424,
594
+ "grad_norm": 0.6923648258189327,
595
+ "learning_rate": 1.3881929363747628e-05,
596
+ "loss": 1.2717,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.4416403785488959,
601
+ "grad_norm": 0.7131098366130528,
602
+ "learning_rate": 1.3711972489182208e-05,
603
+ "loss": 1.2968,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.4468980021030494,
608
+ "grad_norm": 0.7320310034272568,
609
+ "learning_rate": 1.3540762761787938e-05,
610
+ "loss": 1.2829,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.45215562565720296,
615
+ "grad_norm": 0.7327893476336677,
616
+ "learning_rate": 1.3368357967712726e-05,
617
+ "loss": 1.2877,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.45741324921135645,
622
+ "grad_norm": 0.6970014096675695,
623
+ "learning_rate": 1.3194816296459483e-05,
624
+ "loss": 1.2871,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.46267087276551,
629
+ "grad_norm": 0.7014388522833548,
630
+ "learning_rate": 1.302019632124619e-05,
631
+ "loss": 1.2897,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.4679284963196635,
636
+ "grad_norm": 0.6970153763179125,
637
+ "learning_rate": 1.2844556979236463e-05,
638
+ "loss": 1.2714,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.47318611987381703,
643
+ "grad_norm": 0.7162117080997548,
644
+ "learning_rate": 1.2667957551647263e-05,
645
+ "loss": 1.2705,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.4784437434279706,
650
+ "grad_norm": 0.7402201632812351,
651
+ "learning_rate": 1.24904576437405e-05,
652
+ "loss": 1.2654,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.48370136698212407,
657
+ "grad_norm": 1.0567871681807486,
658
+ "learning_rate": 1.2312117164705267e-05,
659
+ "loss": 1.2784,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.4889589905362776,
664
+ "grad_norm": 0.7383322032141622,
665
+ "learning_rate": 1.213299630743747e-05,
666
+ "loss": 1.2574,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.4942166140904311,
671
+ "grad_norm": 0.7402615331947396,
672
+ "learning_rate": 1.1953155528223728e-05,
673
+ "loss": 1.2861,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.49947423764458465,
678
+ "grad_norm": 0.7073342447220505,
679
+ "learning_rate": 1.1772655526336367e-05,
680
+ "loss": 1.2899,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.5047318611987381,
685
+ "grad_norm": 0.6966270957094003,
686
+ "learning_rate": 1.1591557223546394e-05,
687
+ "loss": 1.2607,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.5099894847528917,
692
+ "grad_norm": 0.6995026613750213,
693
+ "learning_rate": 1.1409921743561383e-05,
694
+ "loss": 1.285,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.5152471083070452,
699
+ "grad_norm": 0.677915660036085,
700
+ "learning_rate": 1.1227810391395199e-05,
701
+ "loss": 1.2787,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.5205047318611987,
706
+ "grad_norm": 0.694058172582696,
707
+ "learning_rate": 1.1045284632676535e-05,
708
+ "loss": 1.2817,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.5257623554153522,
713
+ "grad_norm": 0.6977571213673606,
714
+ "learning_rate": 1.0862406072903224e-05,
715
+ "loss": 1.269,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.5310199789695058,
720
+ "grad_norm": 0.709669977534319,
721
+ "learning_rate": 1.067923643664936e-05,
722
+ "loss": 1.2569,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.5362776025236593,
727
+ "grad_norm": 0.700607260206098,
728
+ "learning_rate": 1.0495837546732224e-05,
729
+ "loss": 1.2722,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.5415352260778128,
734
+ "grad_norm": 0.6965062537462676,
735
+ "learning_rate": 1.031227130334604e-05,
736
+ "loss": 1.2689,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.5467928496319664,
741
+ "grad_norm": 0.6975551930599063,
742
+ "learning_rate": 1.0128599663169629e-05,
743
+ "loss": 1.3171,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.5520504731861199,
748
+ "grad_norm": 0.6835553883087109,
749
+ "learning_rate": 9.944884618454996e-06,
750
+ "loss": 1.2616,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.5573080967402734,
755
+ "grad_norm": 0.6932270302779978,
756
+ "learning_rate": 9.761188176103902e-06,
757
+ "loss": 1.2842,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.562565720294427,
762
+ "grad_norm": 0.7523295705383632,
763
+ "learning_rate": 9.577572336739491e-06,
764
+ "loss": 1.276,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.5678233438485805,
769
+ "grad_norm": 0.7410406370549468,
770
+ "learning_rate": 9.394099073780066e-06,
771
+ "loss": 1.2451,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.573080967402734,
776
+ "grad_norm": 0.6626519082062838,
777
+ "learning_rate": 9.210830312521991e-06,
778
+ "loss": 1.2505,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.5783385909568874,
783
+ "grad_norm": 0.678178932637677,
784
+ "learning_rate": 9.027827909238902e-06,
785
+ "loss": 1.2884,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.583596214511041,
790
+ "grad_norm": 0.6964235915302415,
791
+ "learning_rate": 8.84515363030414e-06,
792
+ "loss": 1.2674,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.5888538380651945,
797
+ "grad_norm": 0.7295327929832226,
798
+ "learning_rate": 8.662869131343607e-06,
799
+ "loss": 1.2606,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.594111461619348,
804
+ "grad_norm": 0.6671644394075068,
805
+ "learning_rate": 8.481035936425928e-06,
806
+ "loss": 1.2631,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.5993690851735016,
811
+ "grad_norm": 0.6918129382316475,
812
+ "learning_rate": 8.299715417297072e-06,
813
+ "loss": 1.2733,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.6046267087276551,
818
+ "grad_norm": 0.7648575778497364,
819
+ "learning_rate": 8.118968772666338e-06,
820
+ "loss": 1.2768,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.6098843322818086,
825
+ "grad_norm": 0.6660976751002976,
826
+ "learning_rate": 7.938857007550797e-06,
827
+ "loss": 1.2712,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.6151419558359621,
832
+ "grad_norm": 0.8206761231157318,
833
+ "learning_rate": 7.759440912685043e-06,
834
+ "loss": 1.2629,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.6203995793901157,
839
+ "grad_norm": 0.6781893460495839,
840
+ "learning_rate": 7.580781044003324e-06,
841
+ "loss": 1.2928,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.6256572029442692,
846
+ "grad_norm": 0.7043738811990014,
847
+ "learning_rate": 7.402937702200905e-06,
848
+ "loss": 1.2565,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.6309148264984227,
853
+ "grad_norm": 0.6676378108729303,
854
+ "learning_rate": 7.225970912381557e-06,
855
+ "loss": 1.2441,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.6361724500525763,
860
+ "grad_norm": 0.7086319165657909,
861
+ "learning_rate": 7.04994040379809e-06,
862
+ "loss": 1.2526,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.6414300736067298,
867
+ "grad_norm": 0.6584513029407596,
868
+ "learning_rate": 6.874905589692734e-06,
869
+ "loss": 1.2689,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.6466876971608833,
874
+ "grad_norm": 0.6556498134167102,
875
+ "learning_rate": 6.700925547244173e-06,
876
+ "loss": 1.254,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.6519453207150369,
881
+ "grad_norm": 0.7317497625816267,
882
+ "learning_rate": 6.528058997627995e-06,
883
+ "loss": 1.2773,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.6572029442691903,
888
+ "grad_norm": 0.6943495622984553,
889
+ "learning_rate": 6.356364286197341e-06,
890
+ "loss": 1.2774,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.6624605678233438,
895
+ "grad_norm": 0.6557703327216338,
896
+ "learning_rate": 6.18589936279034e-06,
897
+ "loss": 1.2561,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.6677181913774973,
902
+ "grad_norm": 0.7479106302240468,
903
+ "learning_rate": 6.016721762171098e-06,
904
+ "loss": 1.2592,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.6729758149316509,
909
+ "grad_norm": 0.6501670860792287,
910
+ "learning_rate": 5.848888584610727e-06,
911
+ "loss": 1.2647,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.6782334384858044,
916
+ "grad_norm": 0.6750656043866252,
917
+ "learning_rate": 5.6824564766150724e-06,
918
+ "loss": 1.2687,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.6834910620399579,
923
+ "grad_norm": 0.707162362118668,
924
+ "learning_rate": 5.51748161180554e-06,
925
+ "loss": 1.2658,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.6887486855941115,
930
+ "grad_norm": 0.638182422688773,
931
+ "learning_rate": 5.354019671959601e-06,
932
+ "loss": 1.2618,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.694006309148265,
937
+ "grad_norm": 0.6799258857804185,
938
+ "learning_rate": 5.192125828217203e-06,
939
+ "loss": 1.265,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.6992639327024185,
944
+ "grad_norm": 0.6614260729055945,
945
+ "learning_rate": 5.0318547224596525e-06,
946
+ "loss": 1.2726,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.704521556256572,
951
+ "grad_norm": 0.6571261971890797,
952
+ "learning_rate": 4.873260448867004e-06,
953
+ "loss": 1.2635,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.7097791798107256,
958
+ "grad_norm": 0.6434154288185444,
959
+ "learning_rate": 4.716396535660412e-06,
960
+ "loss": 1.2571,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.7150368033648791,
965
+ "grad_norm": 0.6507843588939136,
966
+ "learning_rate": 4.5613159270354455e-06,
967
+ "loss": 1.2768,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.7202944269190326,
972
+ "grad_norm": 0.6888038425645421,
973
+ "learning_rate": 4.408070965292534e-06,
974
+ "loss": 1.2729,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.7255520504731862,
979
+ "grad_norm": 0.6548677910438372,
980
+ "learning_rate": 4.256713373170565e-06,
981
+ "loss": 1.2754,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.7308096740273397,
986
+ "grad_norm": 0.6924489060189015,
987
+ "learning_rate": 4.107294236389603e-06,
988
+ "loss": 1.2428,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.7360672975814931,
993
+ "grad_norm": 0.675766971656018,
994
+ "learning_rate": 3.959863986408593e-06,
995
+ "loss": 1.2422,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.7413249211356467,
1000
+ "grad_norm": 0.6759780214552317,
1001
+ "learning_rate": 3.8144723834039076e-06,
1002
+ "loss": 1.2596,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.7465825446898002,
1007
+ "grad_norm": 0.6577848370025432,
1008
+ "learning_rate": 3.671168499474449e-06,
1009
+ "loss": 1.2653,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.7518401682439537,
1014
+ "grad_norm": 0.6816662338694881,
1015
+ "learning_rate": 3.5300007020789997e-06,
1016
+ "loss": 1.2612,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.7570977917981072,
1021
+ "grad_norm": 0.6412644189429695,
1022
+ "learning_rate": 3.3910166377113894e-06,
1023
+ "loss": 1.2606,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.7623554153522608,
1028
+ "grad_norm": 0.6489342949048617,
1029
+ "learning_rate": 3.2542632158190135e-06,
1030
+ "loss": 1.2499,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.7676130389064143,
1035
+ "grad_norm": 0.6305858451193405,
1036
+ "learning_rate": 3.119786592970102e-06,
1037
+ "loss": 1.2368,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.7728706624605678,
1042
+ "grad_norm": 0.6601632070842128,
1043
+ "learning_rate": 2.9876321572751143e-06,
1044
+ "loss": 1.2826,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.7781282860147214,
1049
+ "grad_norm": 0.6512679140886882,
1050
+ "learning_rate": 2.8578445130674835e-06,
1051
+ "loss": 1.2509,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.7833859095688749,
1056
+ "grad_norm": 0.662446849135675,
1057
+ "learning_rate": 2.7304674658489104e-06,
1058
+ "loss": 1.2593,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.7886435331230284,
1063
+ "grad_norm": 0.6503725043711072,
1064
+ "learning_rate": 2.6055440075042793e-06,
1065
+ "loss": 1.2696,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.7939011566771819,
1070
+ "grad_norm": 0.6349030168998883,
1071
+ "learning_rate": 2.4831163017911687e-06,
1072
+ "loss": 1.2458,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.7991587802313355,
1077
+ "grad_norm": 0.6296499888770365,
1078
+ "learning_rate": 2.3632256701088817e-06,
1079
+ "loss": 1.2581,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.804416403785489,
1084
+ "grad_norm": 0.6477912073667947,
1085
+ "learning_rate": 2.2459125775517854e-06,
1086
+ "loss": 1.2614,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.8096740273396424,
1091
+ "grad_norm": 0.6340147585135972,
1092
+ "learning_rate": 2.1312166192516593e-06,
1093
+ "loss": 1.2707,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.814931650893796,
1098
+ "grad_norm": 0.6535117628009195,
1099
+ "learning_rate": 2.019176507013677e-06,
1100
+ "loss": 1.2586,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 0.8201892744479495,
1105
+ "grad_norm": 0.6467399510691909,
1106
+ "learning_rate": 1.9098300562505266e-06,
1107
+ "loss": 1.2548,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 0.825446898002103,
1112
+ "grad_norm": 0.6237075846859721,
1113
+ "learning_rate": 1.8032141732190722e-06,
1114
+ "loss": 1.26,
1115
+ "step": 785
1116
+ },
1117
+ {
1118
+ "epoch": 0.8307045215562566,
1119
+ "grad_norm": 0.6374095389974708,
1120
+ "learning_rate": 1.6993648425638797e-06,
1121
+ "loss": 1.2605,
1122
+ "step": 790
1123
+ },
1124
+ {
1125
+ "epoch": 0.8359621451104101,
1126
+ "grad_norm": 0.6326077447290254,
1127
+ "learning_rate": 1.5983171151717924e-06,
1128
+ "loss": 1.2701,
1129
+ "step": 795
1130
+ },
1131
+ {
1132
+ "epoch": 0.8412197686645636,
1133
+ "grad_norm": 0.6299244980807773,
1134
+ "learning_rate": 1.5001050963416718e-06,
1135
+ "loss": 1.2427,
1136
+ "step": 800
1137
+ },
1138
+ {
1139
+ "epoch": 0.8464773922187171,
1140
+ "grad_norm": 0.6281934013360307,
1141
+ "learning_rate": 1.404761934273291e-06,
1142
+ "loss": 1.2635,
1143
+ "step": 805
1144
+ },
1145
+ {
1146
+ "epoch": 0.8517350157728707,
1147
+ "grad_norm": 0.6374294536071755,
1148
+ "learning_rate": 1.3123198088792577e-06,
1149
+ "loss": 1.2717,
1150
+ "step": 810
1151
+ },
1152
+ {
1153
+ "epoch": 0.8569926393270242,
1154
+ "grad_norm": 0.6298699771941692,
1155
+ "learning_rate": 1.222809920923761e-06,
1156
+ "loss": 1.2499,
1157
+ "step": 815
1158
+ },
1159
+ {
1160
+ "epoch": 0.8622502628811777,
1161
+ "grad_norm": 0.6359419744147026,
1162
+ "learning_rate": 1.1362624814917843e-06,
1163
+ "loss": 1.2552,
1164
+ "step": 820
1165
+ },
1166
+ {
1167
+ "epoch": 0.8675078864353313,
1168
+ "grad_norm": 0.6285813274381151,
1169
+ "learning_rate": 1.0527067017923654e-06,
1170
+ "loss": 1.2737,
1171
+ "step": 825
1172
+ },
1173
+ {
1174
+ "epoch": 0.8727655099894848,
1175
+ "grad_norm": 0.6210713562517961,
1176
+ "learning_rate": 9.721707832993232e-07,
1177
+ "loss": 1.2663,
1178
+ "step": 830
1179
+ },
1180
+ {
1181
+ "epoch": 0.8780231335436383,
1182
+ "grad_norm": 0.6645416418213763,
1183
+ "learning_rate": 8.946819082327829e-07,
1184
+ "loss": 1.2581,
1185
+ "step": 835
1186
+ },
1187
+ {
1188
+ "epoch": 0.8832807570977917,
1189
+ "grad_norm": 0.6251751866944497,
1190
+ "learning_rate": 8.202662303847298e-07,
1191
+ "loss": 1.2519,
1192
+ "step": 840
1193
+ },
1194
+ {
1195
+ "epoch": 0.8885383806519453,
1196
+ "grad_norm": 0.6431790207111582,
1197
+ "learning_rate": 7.48948866291661e-07,
1198
+ "loss": 1.2614,
1199
+ "step": 845
1200
+ },
1201
+ {
1202
+ "epoch": 0.8937960042060988,
1203
+ "grad_norm": 0.6384407054635708,
1204
+ "learning_rate": 6.80753886757336e-07,
1205
+ "loss": 1.2722,
1206
+ "step": 850
1207
+ },
1208
+ {
1209
+ "epoch": 0.8990536277602523,
1210
+ "grad_norm": 0.631430226459749,
1211
+ "learning_rate": 6.157043087284797e-07,
1212
+ "loss": 1.2587,
1213
+ "step": 855
1214
+ },
1215
+ {
1216
+ "epoch": 0.9043112513144059,
1217
+ "grad_norm": 0.631843611779411,
1218
+ "learning_rate": 5.538220875261736e-07,
1219
+ "loss": 1.2481,
1220
+ "step": 860
1221
+ },
1222
+ {
1223
+ "epoch": 0.9095688748685594,
1224
+ "grad_norm": 0.6250494334708813,
1225
+ "learning_rate": 4.951281094355708e-07,
1226
+ "loss": 1.2552,
1227
+ "step": 865
1228
+ },
1229
+ {
1230
+ "epoch": 0.9148264984227129,
1231
+ "grad_norm": 0.6300532606909163,
1232
+ "learning_rate": 4.396421846564236e-07,
1233
+ "loss": 1.2536,
1234
+ "step": 870
1235
+ },
1236
+ {
1237
+ "epoch": 0.9200841219768665,
1238
+ "grad_norm": 0.6200012582073006,
1239
+ "learning_rate": 3.8738304061681107e-07,
1240
+ "loss": 1.2694,
1241
+ "step": 875
1242
+ },
1243
+ {
1244
+ "epoch": 0.92534174553102,
1245
+ "grad_norm": 0.6324403821172889,
1246
+ "learning_rate": 3.3836831565231877e-07,
1247
+ "loss": 1.2545,
1248
+ "step": 880
1249
+ },
1250
+ {
1251
+ "epoch": 0.9305993690851735,
1252
+ "grad_norm": 0.6325686488791483,
1253
+ "learning_rate": 2.926145530528002e-07,
1254
+ "loss": 1.2531,
1255
+ "step": 885
1256
+ },
1257
+ {
1258
+ "epoch": 0.935856992639327,
1259
+ "grad_norm": 0.6373731914514896,
1260
+ "learning_rate": 2.501371954787479e-07,
1261
+ "loss": 1.2648,
1262
+ "step": 890
1263
+ },
1264
+ {
1265
+ "epoch": 0.9411146161934806,
1266
+ "grad_norm": 0.6255593953506046,
1267
+ "learning_rate": 2.109505797491318e-07,
1268
+ "loss": 1.2392,
1269
+ "step": 895
1270
+ },
1271
+ {
1272
+ "epoch": 0.9463722397476341,
1273
+ "grad_norm": 0.6353907042408413,
1274
+ "learning_rate": 1.7506793200248507e-07,
1275
+ "loss": 1.2633,
1276
+ "step": 900
1277
+ },
1278
+ {
1279
+ "epoch": 0.9516298633017876,
1280
+ "grad_norm": 0.6307207707434458,
1281
+ "learning_rate": 1.4250136323285868e-07,
1282
+ "loss": 1.2603,
1283
+ "step": 905
1284
+ },
1285
+ {
1286
+ "epoch": 0.9568874868559412,
1287
+ "grad_norm": 0.6277705175750871,
1288
+ "learning_rate": 1.1326186520215888e-07,
1289
+ "loss": 1.2453,
1290
+ "step": 910
1291
+ },
1292
+ {
1293
+ "epoch": 0.9621451104100947,
1294
+ "grad_norm": 0.6031775390358434,
1295
+ "learning_rate": 8.735930673024806e-08,
1296
+ "loss": 1.2544,
1297
+ "step": 915
1298
+ },
1299
+ {
1300
+ "epoch": 0.9674027339642481,
1301
+ "grad_norm": 0.6189714576376613,
1302
+ "learning_rate": 6.480243036404598e-08,
1303
+ "loss": 1.2661,
1304
+ "step": 920
1305
+ },
1306
+ {
1307
+ "epoch": 0.9726603575184016,
1308
+ "grad_norm": 0.6219922382476483,
1309
+ "learning_rate": 4.5598849426777833e-08,
1310
+ "loss": 1.2418,
1311
+ "step": 925
1312
+ },
1313
+ {
1314
+ "epoch": 0.9779179810725552,
1315
+ "grad_norm": 0.6188912441406357,
1316
+ "learning_rate": 2.9755045448351948e-08,
1317
+ "loss": 1.2471,
1318
+ "step": 930
1319
+ },
1320
+ {
1321
+ "epoch": 0.9831756046267087,
1322
+ "grad_norm": 0.6241442557644146,
1323
+ "learning_rate": 1.7276365977730858e-08,
1324
+ "loss": 1.2591,
1325
+ "step": 935
1326
+ },
1327
+ {
1328
+ "epoch": 0.9884332281808622,
1329
+ "grad_norm": 0.6148942917091785,
1330
+ "learning_rate": 8.167022778045042e-09,
1331
+ "loss": 1.2783,
1332
+ "step": 940
1333
+ },
1334
+ {
1335
+ "epoch": 0.9936908517350158,
1336
+ "grad_norm": 0.6142845224019251,
1337
+ "learning_rate": 2.430090405054486e-09,
1338
+ "loss": 1.2311,
1339
+ "step": 945
1340
+ },
1341
+ {
1342
+ "epoch": 0.9989484752891693,
1343
+ "grad_norm": 0.6318778333420784,
1344
+ "learning_rate": 6.750516943321295e-11,
1345
+ "loss": 1.2488,
1346
+ "step": 950
1347
+ },
1348
+ {
1349
+ "epoch": 1.0,
1350
+ "eval_loss": 1.266036868095398,
1351
+ "eval_runtime": 32.6481,
1352
+ "eval_samples_per_second": 412.213,
1353
+ "eval_steps_per_second": 6.463,
1354
+ "step": 951
1355
+ },
1356
+ {
1357
+ "epoch": 1.0,
1358
+ "step": 951,
1359
+ "total_flos": 101091718987776.0,
1360
+ "train_loss": 1.289618753484371,
1361
+ "train_runtime": 1098.6048,
1362
+ "train_samples_per_second": 110.718,
1363
+ "train_steps_per_second": 0.866
1364
+ }
1365
+ ],
1366
+ "logging_steps": 5,
1367
+ "max_steps": 951,
1368
+ "num_input_tokens_seen": 0,
1369
+ "num_train_epochs": 1,
1370
+ "save_steps": 100,
1371
+ "stateful_callbacks": {
1372
+ "TrainerControl": {
1373
+ "args": {
1374
+ "should_epoch_stop": false,
1375
+ "should_evaluate": false,
1376
+ "should_log": false,
1377
+ "should_save": true,
1378
+ "should_training_stop": true
1379
+ },
1380
+ "attributes": {}
1381
+ }
1382
+ },
1383
+ "total_flos": 101091718987776.0,
1384
+ "train_batch_size": 16,
1385
+ "trial_name": null,
1386
+ "trial_params": null
1387
+ }
training.log ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad56a6636d13f4470133ef5791d4e1cb448469ce8e05a3d4a8e9e873c798438
3
+ size 6968