alvarobartt HF staff commited on
Commit
163245e
1 Parent(s): f6fcf45

Training in progress, epoch 0

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google/gemma-2-9b-it
3
+ datasets:
4
+ - generator
5
+ library_name: peft
6
+ license: gemma
7
+ tags:
8
+ - trl
9
+ - sft
10
+ - generated_from_trainer
11
+ model-index:
12
+ - name: gemma-2-9b-it-lora-magicoder
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # gemma-2-9b-it-lora-magicoder
20
+
21
+ This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on the alvarobartt/Magicoder-OAI dataset.
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: 0.0002
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 32
48
+ - total_eval_batch_size: 32
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 3
53
+
54
+ ### Training results
55
+
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - PEFT 0.12.0
61
+ - Transformers 4.44.2
62
+ - Pytorch 2.3.0+cu121
63
+ - Datasets 3.0.0
64
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-2-2b-it",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.01,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "q_proj",
25
+ "v_proj",
26
+ "o_proj",
27
+ "k_proj",
28
+ "down_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d5e52b5668436977b4675922d9a5540ecdfc875c8488911bbe650cec148de2
3
+ size 41582088
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.997420464316423,
3
+ "total_flos": 1.7624457120055296e+16,
4
+ "train_loss": 0.4506890232783245,
5
+ "train_runtime": 9589.9992,
6
+ "train_samples": 67677,
7
+ "train_samples_per_second": 5.818,
8
+ "train_steps_per_second": 0.182
9
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/gemma-2-9b-it",
3
+ "architectures": [
4
+ "Gemma2ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": 50.0,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": 30.0,
13
+ "head_dim": 256,
14
+ "hidden_act": "gelu_pytorch_tanh",
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 3584,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 14336,
19
+ "max_position_embeddings": 8192,
20
+ "model_type": "gemma2",
21
+ "num_attention_heads": 16,
22
+ "num_hidden_layers": 42,
23
+ "num_key_value_heads": 8,
24
+ "pad_token_id": 0,
25
+ "query_pre_attn_scalar": 256,
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_theta": 10000.0,
28
+ "sliding_window": 4096,
29
+ "sliding_window_size": 4096,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.44.2",
32
+ "use_cache": true,
33
+ "vocab_size": 256000
34
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
3
+ size 17525357
tokenizer_config.json ADDED
@@ -0,0 +1,2013 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "5": {
46
+ "content": "<2mass>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "7": {
62
+ "content": "<unused0>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "8": {
70
+ "content": "<unused1>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "9": {
78
+ "content": "<unused2>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "10": {
86
+ "content": "<unused3>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "11": {
94
+ "content": "<unused4>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "12": {
102
+ "content": "<unused5>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "13": {
110
+ "content": "<unused6>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "14": {
118
+ "content": "<unused7>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "15": {
126
+ "content": "<unused8>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "16": {
134
+ "content": "<unused9>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "17": {
142
+ "content": "<unused10>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "18": {
150
+ "content": "<unused11>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "19": {
158
+ "content": "<unused12>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "20": {
166
+ "content": "<unused13>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "21": {
174
+ "content": "<unused14>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "22": {
182
+ "content": "<unused15>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "23": {
190
+ "content": "<unused16>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "24": {
198
+ "content": "<unused17>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "25": {
206
+ "content": "<unused18>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "26": {
214
+ "content": "<unused19>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "27": {
222
+ "content": "<unused20>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "28": {
230
+ "content": "<unused21>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "29": {
238
+ "content": "<unused22>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "30": {
246
+ "content": "<unused23>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "31": {
254
+ "content": "<unused24>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "32": {
262
+ "content": "<unused25>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "33": {
270
+ "content": "<unused26>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "34": {
278
+ "content": "<unused27>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "35": {
286
+ "content": "<unused28>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "36": {
294
+ "content": "<unused29>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "37": {
302
+ "content": "<unused30>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<unused31>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "<unused32>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<unused33>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "41": {
334
+ "content": "<unused34>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "42": {
342
+ "content": "<unused35>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "43": {
350
+ "content": "<unused36>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "44": {
358
+ "content": "<unused37>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "45": {
366
+ "content": "<unused38>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "46": {
374
+ "content": "<unused39>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "47": {
382
+ "content": "<unused40>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "48": {
390
+ "content": "<unused41>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "49": {
398
+ "content": "<unused42>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "50": {
406
+ "content": "<unused43>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "51": {
414
+ "content": "<unused44>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "52": {
422
+ "content": "<unused45>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "53": {
430
+ "content": "<unused46>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "54": {
438
+ "content": "<unused47>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "55": {
446
+ "content": "<unused48>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "56": {
454
+ "content": "<unused49>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "57": {
462
+ "content": "<unused50>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "58": {
470
+ "content": "<unused51>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "59": {
478
+ "content": "<unused52>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "60": {
486
+ "content": "<unused53>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "61": {
494
+ "content": "<unused54>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "62": {
502
+ "content": "<unused55>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "63": {
510
+ "content": "<unused56>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "64": {
518
+ "content": "<unused57>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "65": {
526
+ "content": "<unused58>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "66": {
534
+ "content": "<unused59>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "67": {
542
+ "content": "<unused60>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "68": {
550
+ "content": "<unused61>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "69": {
558
+ "content": "<unused62>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "70": {
566
+ "content": "<unused63>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "71": {
574
+ "content": "<unused64>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "72": {
582
+ "content": "<unused65>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "73": {
590
+ "content": "<unused66>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "74": {
598
+ "content": "<unused67>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "75": {
606
+ "content": "<unused68>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "76": {
614
+ "content": "<unused69>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "77": {
622
+ "content": "<unused70>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "78": {
630
+ "content": "<unused71>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "79": {
638
+ "content": "<unused72>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "80": {
646
+ "content": "<unused73>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "81": {
654
+ "content": "<unused74>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "82": {
662
+ "content": "<unused75>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "83": {
670
+ "content": "<unused76>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "84": {
678
+ "content": "<unused77>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "85": {
686
+ "content": "<unused78>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "86": {
694
+ "content": "<unused79>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "87": {
702
+ "content": "<unused80>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "88": {
710
+ "content": "<unused81>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "89": {
718
+ "content": "<unused82>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "90": {
726
+ "content": "<unused83>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "91": {
734
+ "content": "<unused84>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "92": {
742
+ "content": "<unused85>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "93": {
750
+ "content": "<unused86>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "94": {
758
+ "content": "<unused87>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "95": {
766
+ "content": "<unused88>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "96": {
774
+ "content": "<unused89>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "97": {
782
+ "content": "<unused90>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "98": {
790
+ "content": "<unused91>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "99": {
798
+ "content": "<unused92>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "100": {
806
+ "content": "<unused93>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "101": {
814
+ "content": "<unused94>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "102": {
822
+ "content": "<unused95>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "103": {
830
+ "content": "<unused96>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "104": {
838
+ "content": "<unused97>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "105": {
846
+ "content": "<unused98>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "108": {
870
+ "content": "\n",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "109": {
878
+ "content": "\n\n",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "110": {
886
+ "content": "\n\n\n",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
+ },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": false
1060
+ },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": false
1068
+ },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": false
1076
+ },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": false
1084
+ },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false
1092
+ },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": false
1100
+ },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": false
1108
+ },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": false
1116
+ },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": false
1124
+ },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": false
1132
+ },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": false
1140
+ },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": false
1148
+ },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": false
1156
+ },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false
1164
+ },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": false
1172
+ },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": false
1180
+ },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": false
1188
+ },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": false
1196
+ },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": false
1204
+ },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": false
1212
+ },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": false
1220
+ },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": false
1228
+ },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false
1236
+ },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": false
1244
+ },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": false
1268
+ },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": false
1276
+ },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": false
1284
+ },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": false
1292
+ },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": false
1300
+ },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false
1308
+ },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": false
1316
+ },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": false
1324
+ },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": false
1332
+ },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": false
1340
+ },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": false
1348
+ },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": false
1356
+ },
1357
+ "169": {
1358
+ "content": "<table>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": false
1364
+ },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": false
1372
+ },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false
1380
+ },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": false
1388
+ },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": false
1396
+ },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": false
1404
+ },
1405
+ "175": {
1406
+ "content": "<th>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": false
1412
+ },
1413
+ "176": {
1414
+ "content": "<td>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": false
1420
+ },
1421
+ "177": {
1422
+ "content": "</table>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": false
1428
+ },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": false
1436
+ },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": false
1444
+ },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false
1452
+ },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": false
1460
+ },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": false
1468
+ },
1469
+ "183": {
1470
+ "content": "</th>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "184": {
1478
+ "content": "</td>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false
1524
+ },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": false
1532
+ },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": false
1540
+ },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": false
1548
+ },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": false
1556
+ },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": false
1564
+ },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "200": {
1606
+ "content": "<em>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ },
1613
+ "201": {
1614
+ "content": "<b>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": false
1620
+ },
1621
+ "202": {
1622
+ "content": "<i>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": false
1628
+ },
1629
+ "203": {
1630
+ "content": "<u>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": false
1636
+ },
1637
+ "204": {
1638
+ "content": "<s>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": false
1644
+ },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": false
1652
+ },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": false
1660
+ },
1661
+ "207": {
1662
+ "content": "<code>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false
1668
+ },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": false
1676
+ },
1677
+ "209": {
1678
+ "content": "</em>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": false
1684
+ },
1685
+ "210": {
1686
+ "content": "</b>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": false
1692
+ },
1693
+ "211": {
1694
+ "content": "</i>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": false
1700
+ },
1701
+ "212": {
1702
+ "content": "</u>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": false
1708
+ },
1709
+ "213": {
1710
+ "content": "</s>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": false
1716
+ },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": false
1724
+ },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": false
1732
+ },
1733
+ "216": {
1734
+ "content": "</code>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false
1740
+ },
1741
+ "255968": {
1742
+ "content": "[toxicity=0]",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": false
1748
+ },
1749
+ "255969": {
1750
+ "content": "\t\t",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": false
1756
+ },
1757
+ "255970": {
1758
+ "content": "\t\t\t",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": false
1764
+ },
1765
+ "255971": {
1766
+ "content": "\t\t\t\t",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": false
1772
+ },
1773
+ "255972": {
1774
+ "content": "\t\t\t\t\t",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": false
1780
+ },
1781
+ "255973": {
1782
+ "content": "\t\t\t\t\t\t",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": false
1788
+ },
1789
+ "255974": {
1790
+ "content": "\t\t\t\t\t\t\t",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": false
1796
+ },
1797
+ "255975": {
1798
+ "content": "\t\t\t\t\t\t\t\t",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": false
1804
+ },
1805
+ "255976": {
1806
+ "content": "\t\t\t\t\t\t\t\t\t",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": false
1812
+ },
1813
+ "255977": {
1814
+ "content": "\t\t\t\t\t\t\t\t\t\t",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": false
1820
+ },
1821
+ "255978": {
1822
+ "content": "\t\t\t\t\t\t\t\t\t\t\t",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": false
1828
+ },
1829
+ "255979": {
1830
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": false
1836
+ },
1837
+ "255980": {
1838
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": false
1844
+ },
1845
+ "255981": {
1846
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": false
1852
+ },
1853
+ "255982": {
1854
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": false
1860
+ },
1861
+ "255983": {
1862
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": false
1868
+ },
1869
+ "255984": {
1870
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": false
1876
+ },
1877
+ "255985": {
1878
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": false
1884
+ },
1885
+ "255986": {
1886
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": false
1892
+ },
1893
+ "255987": {
1894
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": false
1900
+ },
1901
+ "255988": {
1902
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": false
1908
+ },
1909
+ "255989": {
1910
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": false
1916
+ },
1917
+ "255990": {
1918
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": false
1924
+ },
1925
+ "255991": {
1926
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": false
1932
+ },
1933
+ "255992": {
1934
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": false
1940
+ },
1941
+ "255993": {
1942
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": false
1948
+ },
1949
+ "255994": {
1950
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": false
1956
+ },
1957
+ "255995": {
1958
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": false
1964
+ },
1965
+ "255996": {
1966
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": false
1972
+ },
1973
+ "255997": {
1974
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": false
1980
+ },
1981
+ "255998": {
1982
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": false
1988
+ },
1989
+ "255999": {
1990
+ "content": "<unused99>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": false
1996
+ }
1997
+ },
1998
+ "additional_special_tokens": [
1999
+ "<start_of_turn>",
2000
+ "<end_of_turn>"
2001
+ ],
2002
+ "bos_token": "<bos>",
2003
+ "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
2004
+ "clean_up_tokenization_spaces": false,
2005
+ "eos_token": "<eos>",
2006
+ "model_max_length": 2048,
2007
+ "pad_token": "<pad>",
2008
+ "sp_model_kwargs": {},
2009
+ "spaces_between_special_tokens": false,
2010
+ "tokenizer_class": "GemmaTokenizer",
2011
+ "unk_token": "<unk>",
2012
+ "use_default_system_prompt": false
2013
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.997420464316423,
3
+ "total_flos": 1.7624457120055296e+16,
4
+ "train_loss": 0.4506890232783245,
5
+ "train_runtime": 9589.9992,
6
+ "train_samples": 67677,
7
+ "train_samples_per_second": 5.818,
8
+ "train_steps_per_second": 0.182
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,1260 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.997420464316423,
5
+ "eval_steps": 500,
6
+ "global_step": 1743,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017196904557179708,
13
+ "grad_norm": 1.236184773002013,
14
+ "learning_rate": 1.1428571428571429e-05,
15
+ "loss": 1.185,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.034393809114359415,
20
+ "grad_norm": 0.5456076333168367,
21
+ "learning_rate": 2.2857142857142858e-05,
22
+ "loss": 1.0131,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.051590713671539126,
27
+ "grad_norm": 0.35549053304697176,
28
+ "learning_rate": 3.428571428571429e-05,
29
+ "loss": 0.8296,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.06878761822871883,
34
+ "grad_norm": 0.254673976618386,
35
+ "learning_rate": 4.5714285714285716e-05,
36
+ "loss": 0.7454,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.08598452278589853,
41
+ "grad_norm": 0.23070603652224944,
42
+ "learning_rate": 5.714285714285714e-05,
43
+ "loss": 0.6662,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.10318142734307825,
48
+ "grad_norm": 0.17478929504818824,
49
+ "learning_rate": 6.857142857142858e-05,
50
+ "loss": 0.596,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.12037833190025796,
55
+ "grad_norm": 0.1561819886139925,
56
+ "learning_rate": 8e-05,
57
+ "loss": 0.578,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.13757523645743766,
62
+ "grad_norm": 0.20767032014128362,
63
+ "learning_rate": 9.142857142857143e-05,
64
+ "loss": 0.56,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.15477214101461736,
69
+ "grad_norm": 0.1783753453274605,
70
+ "learning_rate": 0.00010285714285714286,
71
+ "loss": 0.5486,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.17196904557179707,
76
+ "grad_norm": 0.21780447055549776,
77
+ "learning_rate": 0.00011428571428571428,
78
+ "loss": 0.5442,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.18916595012897677,
83
+ "grad_norm": 0.17636411695201717,
84
+ "learning_rate": 0.00012571428571428572,
85
+ "loss": 0.5336,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2063628546861565,
90
+ "grad_norm": 0.17514613701190404,
91
+ "learning_rate": 0.00013714285714285716,
92
+ "loss": 0.5267,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.2235597592433362,
97
+ "grad_norm": 0.19025963821244604,
98
+ "learning_rate": 0.00014857142857142857,
99
+ "loss": 0.5274,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.2407566638005159,
104
+ "grad_norm": 0.18019488365092756,
105
+ "learning_rate": 0.00016,
106
+ "loss": 0.5166,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.2579535683576956,
111
+ "grad_norm": 0.17880762343061918,
112
+ "learning_rate": 0.00017142857142857143,
113
+ "loss": 0.5203,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.2751504729148753,
118
+ "grad_norm": 0.18388862726424096,
119
+ "learning_rate": 0.00018285714285714286,
120
+ "loss": 0.5224,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.292347377472055,
125
+ "grad_norm": 0.16430698379785788,
126
+ "learning_rate": 0.0001942857142857143,
127
+ "loss": 0.5188,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.30954428202923473,
132
+ "grad_norm": 0.15725107599349494,
133
+ "learning_rate": 0.00019999498219234568,
134
+ "loss": 0.516,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.32674118658641443,
139
+ "grad_norm": 0.15173489549988936,
140
+ "learning_rate": 0.0001999548427524678,
141
+ "loss": 0.5058,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.34393809114359414,
146
+ "grad_norm": 0.16657669365074929,
147
+ "learning_rate": 0.0001998745799852668,
148
+ "loss": 0.5072,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.36113499570077384,
153
+ "grad_norm": 0.14245522126193838,
154
+ "learning_rate": 0.00019975422610938462,
155
+ "loss": 0.5092,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.37833190025795355,
160
+ "grad_norm": 0.14204763106782423,
161
+ "learning_rate": 0.00019959382943661704,
162
+ "loss": 0.5124,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.39552880481513325,
167
+ "grad_norm": 0.14674244927319882,
168
+ "learning_rate": 0.00019939345435252088,
169
+ "loss": 0.515,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.412725709372313,
174
+ "grad_norm": 0.13843089052767493,
175
+ "learning_rate": 0.00019915318129056853,
176
+ "loss": 0.4994,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.4299226139294927,
181
+ "grad_norm": 0.146900895726969,
182
+ "learning_rate": 0.00019887310669986085,
183
+ "loss": 0.5052,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.4471195184866724,
188
+ "grad_norm": 0.14008859218618483,
189
+ "learning_rate": 0.00019855334300641114,
190
+ "loss": 0.5041,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.4643164230438521,
195
+ "grad_norm": 0.18809570469767778,
196
+ "learning_rate": 0.0001981940185680156,
197
+ "loss": 0.4978,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.4815133276010318,
202
+ "grad_norm": 0.14104099043343712,
203
+ "learning_rate": 0.00019779527762272877,
204
+ "loss": 0.5001,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.49871023215821153,
209
+ "grad_norm": 0.13804026353342516,
210
+ "learning_rate": 0.0001973572802309642,
211
+ "loss": 0.4885,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.5159071367153912,
216
+ "grad_norm": 0.14300868500069924,
217
+ "learning_rate": 0.00019688020221124376,
218
+ "loss": 0.495,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.5331040412725709,
223
+ "grad_norm": 0.14885187886758067,
224
+ "learning_rate": 0.00019636423506962181,
225
+ "loss": 0.4963,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5503009458297506,
230
+ "grad_norm": 0.13442343336925347,
231
+ "learning_rate": 0.00019580958592281167,
232
+ "loss": 0.4924,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5674978503869303,
237
+ "grad_norm": 0.13673211813600614,
238
+ "learning_rate": 0.00019521647741504604,
239
+ "loss": 0.5004,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.58469475494411,
244
+ "grad_norm": 0.13956825916960136,
245
+ "learning_rate": 0.00019458514762870426,
246
+ "loss": 0.485,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.6018916595012898,
251
+ "grad_norm": 0.14073396199862337,
252
+ "learning_rate": 0.0001939158499887428,
253
+ "loss": 0.4933,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6190885640584695,
258
+ "grad_norm": 0.13603301551856595,
259
+ "learning_rate": 0.00019320885316096654,
260
+ "loss": 0.4938,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6362854686156492,
265
+ "grad_norm": 0.1420552122294903,
266
+ "learning_rate": 0.00019246444094418255,
267
+ "loss": 0.4786,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6534823731728289,
272
+ "grad_norm": 0.1414519600117056,
273
+ "learning_rate": 0.00019168291215627926,
274
+ "loss": 0.4926,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.6706792777300086,
279
+ "grad_norm": 0.13984821923297133,
280
+ "learning_rate": 0.00019086458051427622,
281
+ "loss": 0.4911,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.6878761822871883,
286
+ "grad_norm": 0.13752756195301288,
287
+ "learning_rate": 0.00019000977450839393,
288
+ "loss": 0.4827,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.705073086844368,
293
+ "grad_norm": 0.13335244333926366,
294
+ "learning_rate": 0.00018911883727019285,
295
+ "loss": 0.4898,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.7222699914015477,
300
+ "grad_norm": 0.13230952803690713,
301
+ "learning_rate": 0.0001881921264348355,
302
+ "loss": 0.4854,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.7394668959587274,
307
+ "grad_norm": 0.13478694398925248,
308
+ "learning_rate": 0.00018723001399752653,
309
+ "loss": 0.4897,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.7566638005159071,
314
+ "grad_norm": 0.1442034436213339,
315
+ "learning_rate": 0.0001862328861641883,
316
+ "loss": 0.4822,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.7738607050730868,
321
+ "grad_norm": 0.13449084966209246,
322
+ "learning_rate": 0.00018520114319643235,
323
+ "loss": 0.4886,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.7910576096302665,
328
+ "grad_norm": 0.1312938599246684,
329
+ "learning_rate": 0.0001841351992508885,
330
+ "loss": 0.4786,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.8082545141874462,
335
+ "grad_norm": 0.12664552711595364,
336
+ "learning_rate": 0.0001830354822129564,
337
+ "loss": 0.4882,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.825451418744626,
342
+ "grad_norm": 0.134819817437524,
343
+ "learning_rate": 0.00018190243352504597,
344
+ "loss": 0.48,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.8426483233018057,
349
+ "grad_norm": 0.14466404063388616,
350
+ "learning_rate": 0.00018073650800937624,
351
+ "loss": 0.4809,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.8598452278589854,
356
+ "grad_norm": 0.13311350418133092,
357
+ "learning_rate": 0.00017953817368540292,
358
+ "loss": 0.4834,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.8770421324161651,
363
+ "grad_norm": 0.13856027344204028,
364
+ "learning_rate": 0.0001783079115819486,
365
+ "loss": 0.4913,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.8942390369733448,
370
+ "grad_norm": 0.12870004634007948,
371
+ "learning_rate": 0.00017704621554411084,
372
+ "loss": 0.4827,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.9114359415305245,
377
+ "grad_norm": 0.12894303718503525,
378
+ "learning_rate": 0.0001757535920350255,
379
+ "loss": 0.4768,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.9286328460877042,
384
+ "grad_norm": 0.13086927730335407,
385
+ "learning_rate": 0.0001744305599325652,
386
+ "loss": 0.4857,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.945829750644884,
391
+ "grad_norm": 0.12929634161460313,
392
+ "learning_rate": 0.00017307765032105406,
393
+ "loss": 0.4883,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.9630266552020637,
398
+ "grad_norm": 0.13721669025539573,
399
+ "learning_rate": 0.00017169540627808274,
400
+ "loss": 0.4875,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.9802235597592434,
405
+ "grad_norm": 0.1285154415557853,
406
+ "learning_rate": 0.00017028438265650933,
407
+ "loss": 0.4821,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.9974204643164231,
412
+ "grad_norm": 0.13060285124046392,
413
+ "learning_rate": 0.0001688451458617332,
414
+ "loss": 0.4796,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 1.0146173688736027,
419
+ "grad_norm": 0.136066972815243,
420
+ "learning_rate": 0.00016737827362433164,
421
+ "loss": 0.4527,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 1.0318142734307825,
426
+ "grad_norm": 0.1366031218446295,
427
+ "learning_rate": 0.0001658843547681506,
428
+ "loss": 0.4484,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 1.049011177987962,
433
+ "grad_norm": 0.1378157386033563,
434
+ "learning_rate": 0.000164363988973942,
435
+ "loss": 0.4465,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 1.0662080825451419,
440
+ "grad_norm": 0.1435554531245416,
441
+ "learning_rate": 0.00016281778653864316,
442
+ "loss": 0.4415,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 1.0834049871023215,
447
+ "grad_norm": 0.14661925606567783,
448
+ "learning_rate": 0.00016124636813039502,
449
+ "loss": 0.441,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 1.1006018916595013,
454
+ "grad_norm": 0.13987832152903712,
455
+ "learning_rate": 0.0001596503645393966,
456
+ "loss": 0.4359,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 1.117798796216681,
461
+ "grad_norm": 0.14735126394013195,
462
+ "learning_rate": 0.0001580304164246968,
463
+ "loss": 0.4473,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 1.1349957007738607,
468
+ "grad_norm": 0.1429953902523938,
469
+ "learning_rate": 0.0001563871740570245,
470
+ "loss": 0.4451,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 1.1521926053310405,
475
+ "grad_norm": 0.1459735378688384,
476
+ "learning_rate": 0.00015472129705776047,
477
+ "loss": 0.4422,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 1.16938950988822,
482
+ "grad_norm": 0.14561658254102702,
483
+ "learning_rate": 0.00015303345413415564,
484
+ "loss": 0.4409,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 1.1865864144454,
489
+ "grad_norm": 0.14737248104484174,
490
+ "learning_rate": 0.00015132432281090256,
491
+ "loss": 0.4419,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 1.2037833190025795,
496
+ "grad_norm": 0.15311335569967213,
497
+ "learning_rate": 0.0001495945891581668,
498
+ "loss": 0.4419,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 1.2209802235597593,
503
+ "grad_norm": 0.14524361407042563,
504
+ "learning_rate": 0.00014784494751618853,
505
+ "loss": 0.4411,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 1.238177128116939,
510
+ "grad_norm": 0.14910830182050996,
511
+ "learning_rate": 0.0001460761002165645,
512
+ "loss": 0.4471,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 1.2553740326741187,
517
+ "grad_norm": 0.15226336213789984,
518
+ "learning_rate": 0.00014428875730032145,
519
+ "loss": 0.4423,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 1.2725709372312983,
524
+ "grad_norm": 0.15781539164450759,
525
+ "learning_rate": 0.00014248363623289574,
526
+ "loss": 0.4359,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 1.2897678417884781,
531
+ "grad_norm": 0.14138385096885275,
532
+ "learning_rate": 0.00014066146161613208,
533
+ "loss": 0.4414,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 1.3069647463456577,
538
+ "grad_norm": 0.14745231010770607,
539
+ "learning_rate": 0.00013882296489741783,
540
+ "loss": 0.4457,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 1.3241616509028376,
545
+ "grad_norm": 0.155323506204182,
546
+ "learning_rate": 0.00013696888407606952,
547
+ "loss": 0.4468,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 1.3413585554600171,
552
+ "grad_norm": 0.14906188336013929,
553
+ "learning_rate": 0.0001350999634070889,
554
+ "loss": 0.4561,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 1.358555460017197,
559
+ "grad_norm": 0.1509482546916061,
560
+ "learning_rate": 0.0001332169531024085,
561
+ "loss": 0.4488,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 1.3757523645743766,
566
+ "grad_norm": 0.1577110542147225,
567
+ "learning_rate": 0.00013132060902974554,
568
+ "loss": 0.4481,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 1.3929492691315564,
573
+ "grad_norm": 0.1519302579308639,
574
+ "learning_rate": 0.00012941169240918534,
575
+ "loss": 0.4434,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 1.410146173688736,
580
+ "grad_norm": 0.16574786040919845,
581
+ "learning_rate": 0.00012749096950761702,
582
+ "loss": 0.4422,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 1.4273430782459158,
587
+ "grad_norm": 0.14939058136631353,
588
+ "learning_rate": 0.00012555921133114247,
589
+ "loss": 0.4439,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 1.4445399828030954,
594
+ "grad_norm": 0.14433259289852834,
595
+ "learning_rate": 0.00012361719331558345,
596
+ "loss": 0.4412,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 1.4617368873602752,
601
+ "grad_norm": 0.14779220063991433,
602
+ "learning_rate": 0.00012166569501521017,
603
+ "loss": 0.444,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 1.4789337919174548,
608
+ "grad_norm": 0.15109790098843823,
609
+ "learning_rate": 0.00011970549978981715,
610
+ "loss": 0.4489,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 1.4961306964746346,
615
+ "grad_norm": 0.14824981470720835,
616
+ "learning_rate": 0.00011773739449027108,
617
+ "loss": 0.4377,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 1.5133276010318144,
622
+ "grad_norm": 0.14490199589122096,
623
+ "learning_rate": 0.00011576216914265734,
624
+ "loss": 0.4454,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 1.530524505588994,
629
+ "grad_norm": 0.14668336107167357,
630
+ "learning_rate": 0.00011378061663115222,
631
+ "loss": 0.4374,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 1.5477214101461736,
636
+ "grad_norm": 0.15306161877683747,
637
+ "learning_rate": 0.00011179353237974756,
638
+ "loss": 0.441,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 1.5649183147033534,
643
+ "grad_norm": 0.14629253984953647,
644
+ "learning_rate": 0.0001098017140329561,
645
+ "loss": 0.4402,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 1.5821152192605332,
650
+ "grad_norm": 0.15181211231388803,
651
+ "learning_rate": 0.00010780596113562514,
652
+ "loss": 0.4441,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 1.5993121238177128,
657
+ "grad_norm": 0.14895949287614227,
658
+ "learning_rate": 0.00010580707481198796,
659
+ "loss": 0.4415,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 1.6165090283748924,
664
+ "grad_norm": 0.14919588155250404,
665
+ "learning_rate": 0.00010380585744408065,
666
+ "loss": 0.4428,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 1.6337059329320722,
671
+ "grad_norm": 0.15195396903926595,
672
+ "learning_rate": 0.00010180311234965433,
673
+ "loss": 0.4338,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 1.650902837489252,
678
+ "grad_norm": 0.15192117531451788,
679
+ "learning_rate": 9.979964345971188e-05,
680
+ "loss": 0.445,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 1.6680997420464316,
685
+ "grad_norm": 0.14674515514268918,
686
+ "learning_rate": 9.779625499579805e-05,
687
+ "loss": 0.4416,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 1.6852966466036112,
692
+ "grad_norm": 0.14766438549971136,
693
+ "learning_rate": 9.579375114717351e-05,
694
+ "loss": 0.434,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 1.702493551160791,
699
+ "grad_norm": 0.14681911182175214,
700
+ "learning_rate": 9.379293574800154e-05,
701
+ "loss": 0.4363,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 1.7196904557179709,
706
+ "grad_norm": 0.1464492709373849,
707
+ "learning_rate": 9.179461195467714e-05,
708
+ "loss": 0.4353,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 1.7368873602751504,
713
+ "grad_norm": 0.15011221390319449,
714
+ "learning_rate": 8.979958192342862e-05,
715
+ "loss": 0.4445,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 1.75408426483233,
720
+ "grad_norm": 0.152429302734013,
721
+ "learning_rate": 8.780864648832022e-05,
722
+ "loss": 0.4404,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 1.7712811693895099,
727
+ "grad_norm": 0.14681226342261067,
728
+ "learning_rate": 8.58226048397857e-05,
729
+ "loss": 0.4435,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 1.7884780739466897,
734
+ "grad_norm": 0.15354804740449426,
735
+ "learning_rate": 8.384225420382185e-05,
736
+ "loss": 0.4377,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 1.8056749785038693,
741
+ "grad_norm": 0.15108728472484245,
742
+ "learning_rate": 8.186838952197018e-05,
743
+ "loss": 0.4344,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 1.8228718830610489,
748
+ "grad_norm": 0.14903695640608858,
749
+ "learning_rate": 7.990180313221596e-05,
750
+ "loss": 0.4381,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 1.8400687876182287,
755
+ "grad_norm": 0.14676064171835554,
756
+ "learning_rate": 7.794328445093208e-05,
757
+ "loss": 0.4379,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 1.8572656921754085,
762
+ "grad_norm": 0.15258822928003124,
763
+ "learning_rate": 7.599361965599606e-05,
764
+ "loss": 0.4426,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 1.874462596732588,
769
+ "grad_norm": 0.26094072520435535,
770
+ "learning_rate": 7.405359137120662e-05,
771
+ "loss": 0.4368,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 1.8916595012897677,
776
+ "grad_norm": 0.15223526485978567,
777
+ "learning_rate": 7.212397835212722e-05,
778
+ "loss": 0.4426,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 1.9088564058469477,
783
+ "grad_norm": 0.14158786202820334,
784
+ "learning_rate": 7.02055551734822e-05,
785
+ "loss": 0.4304,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 1.9260533104041273,
790
+ "grad_norm": 0.15562496727433017,
791
+ "learning_rate": 6.829909191823121e-05,
792
+ "loss": 0.4426,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 1.943250214961307,
797
+ "grad_norm": 0.14930981803960258,
798
+ "learning_rate": 6.640535386844679e-05,
799
+ "loss": 0.4418,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 1.9604471195184867,
804
+ "grad_norm": 0.1552156563224316,
805
+ "learning_rate": 6.452510119811895e-05,
806
+ "loss": 0.4367,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 1.9776440240756665,
811
+ "grad_norm": 0.19090518551388455,
812
+ "learning_rate": 6.26590886680103e-05,
813
+ "loss": 0.4303,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 1.9948409286328461,
818
+ "grad_norm": 0.1496699651502689,
819
+ "learning_rate": 6.0808065322683993e-05,
820
+ "loss": 0.4307,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 2.0120378331900257,
825
+ "grad_norm": 0.16615207318616432,
826
+ "learning_rate": 5.897277418982672e-05,
827
+ "loss": 0.3983,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 2.0292347377472053,
832
+ "grad_norm": 0.1652827612761684,
833
+ "learning_rate": 5.715395198198603e-05,
834
+ "loss": 0.3812,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 2.0464316423043853,
839
+ "grad_norm": 0.16911724923353538,
840
+ "learning_rate": 5.5352328800843724e-05,
841
+ "loss": 0.3766,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 2.063628546861565,
846
+ "grad_norm": 0.16951539871441879,
847
+ "learning_rate": 5.356862784414199e-05,
848
+ "loss": 0.3789,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 2.0808254514187445,
853
+ "grad_norm": 0.17010125437035936,
854
+ "learning_rate": 5.1803565115381694e-05,
855
+ "loss": 0.3783,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 2.098022355975924,
860
+ "grad_norm": 0.16860757374113347,
861
+ "learning_rate": 5.0057849136407874e-05,
862
+ "loss": 0.3815,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 2.115219260533104,
867
+ "grad_norm": 0.17279827710775011,
868
+ "learning_rate": 4.833218066299896e-05,
869
+ "loss": 0.3775,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 2.1324161650902838,
874
+ "grad_norm": 0.16772946452531912,
875
+ "learning_rate": 4.6627252403573085e-05,
876
+ "loss": 0.3719,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 2.1496130696474633,
881
+ "grad_norm": 0.17982428185526986,
882
+ "learning_rate": 4.4943748741124934e-05,
883
+ "loss": 0.3779,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 2.166809974204643,
888
+ "grad_norm": 0.18313593415470272,
889
+ "learning_rate": 4.328234545850442e-05,
890
+ "loss": 0.3836,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 2.184006878761823,
895
+ "grad_norm": 0.1725383341952266,
896
+ "learning_rate": 4.1643709467147615e-05,
897
+ "loss": 0.369,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 2.2012037833190026,
902
+ "grad_norm": 0.1971081873293993,
903
+ "learning_rate": 4.002849853936891e-05,
904
+ "loss": 0.3728,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 2.218400687876182,
909
+ "grad_norm": 0.17991148711708474,
910
+ "learning_rate": 3.843736104432137e-05,
911
+ "loss": 0.3804,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 2.235597592433362,
916
+ "grad_norm": 0.17934271418386846,
917
+ "learning_rate": 3.687093568773229e-05,
918
+ "loss": 0.3844,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 2.252794496990542,
923
+ "grad_norm": 0.17862554374418718,
924
+ "learning_rate": 3.532985125551715e-05,
925
+ "loss": 0.385,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 2.2699914015477214,
930
+ "grad_norm": 0.17397364598815349,
931
+ "learning_rate": 3.381472636137591e-05,
932
+ "loss": 0.3755,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 2.287188306104901,
937
+ "grad_norm": 0.18500269890886714,
938
+ "learning_rate": 3.2326169198472556e-05,
939
+ "loss": 0.384,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 2.304385210662081,
944
+ "grad_norm": 0.18186600816942164,
945
+ "learning_rate": 3.0864777295297376e-05,
946
+ "loss": 0.3726,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 2.3215821152192606,
951
+ "grad_norm": 0.17773737221105249,
952
+ "learning_rate": 2.9431137275810317e-05,
953
+ "loss": 0.3704,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 2.33877901977644,
958
+ "grad_norm": 0.18256211613697612,
959
+ "learning_rate": 2.8025824623961773e-05,
960
+ "loss": 0.3769,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 2.35597592433362,
965
+ "grad_norm": 0.18129287061779392,
966
+ "learning_rate": 2.664940345268483e-05,
967
+ "loss": 0.3766,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 2.3731728288908,
972
+ "grad_norm": 0.1785686917578723,
973
+ "learning_rate": 2.5302426277452172e-05,
974
+ "loss": 0.3701,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 2.3903697334479794,
979
+ "grad_norm": 0.19834019533954172,
980
+ "learning_rate": 2.398543379448832e-05,
981
+ "loss": 0.3768,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 2.407566638005159,
986
+ "grad_norm": 0.18177776105752433,
987
+ "learning_rate": 2.26989546637263e-05,
988
+ "loss": 0.3755,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 2.4247635425623386,
993
+ "grad_norm": 0.18362730161587285,
994
+ "learning_rate": 2.144350529659589e-05,
995
+ "loss": 0.368,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 2.4419604471195187,
1000
+ "grad_norm": 0.18330397808911847,
1001
+ "learning_rate": 2.021958964872851e-05,
1002
+ "loss": 0.3794,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 2.4591573516766982,
1007
+ "grad_norm": 0.19205219312460517,
1008
+ "learning_rate": 1.9027699017662194e-05,
1009
+ "loss": 0.3703,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 2.476354256233878,
1014
+ "grad_norm": 0.18216660996651907,
1015
+ "learning_rate": 1.7868311845627472e-05,
1016
+ "loss": 0.3754,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 2.4935511607910574,
1021
+ "grad_norm": 0.18809064927597854,
1022
+ "learning_rate": 1.6741893527493858e-05,
1023
+ "loss": 0.3707,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 2.5107480653482375,
1028
+ "grad_norm": 0.18562863684234907,
1029
+ "learning_rate": 1.564889622395349e-05,
1030
+ "loss": 0.3698,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 2.527944969905417,
1035
+ "grad_norm": 0.18350802969723742,
1036
+ "learning_rate": 1.4589758680017263e-05,
1037
+ "loss": 0.3733,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 2.5451418744625967,
1042
+ "grad_norm": 0.18684066406776073,
1043
+ "learning_rate": 1.356490604889622e-05,
1044
+ "loss": 0.3787,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 2.5623387790197762,
1049
+ "grad_norm": 0.1811515744478759,
1050
+ "learning_rate": 1.2574749721338874e-05,
1051
+ "loss": 0.3769,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 2.5795356835769563,
1056
+ "grad_norm": 0.18069550077179752,
1057
+ "learning_rate": 1.1619687160492953e-05,
1058
+ "loss": 0.3701,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 2.596732588134136,
1063
+ "grad_norm": 0.18462589607546182,
1064
+ "learning_rate": 1.0700101742357926e-05,
1065
+ "loss": 0.3744,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 2.6139294926913155,
1070
+ "grad_norm": 0.18712041177077796,
1071
+ "learning_rate": 9.816362601892326e-06,
1072
+ "loss": 0.3677,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 2.6311263972484955,
1077
+ "grad_norm": 0.18908434345209518,
1078
+ "learning_rate": 8.968824484837578e-06,
1079
+ "loss": 0.3685,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 2.648323301805675,
1084
+ "grad_norm": 0.1847336144413599,
1085
+ "learning_rate": 8.157827605317892e-06,
1086
+ "loss": 0.3713,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 2.6655202063628547,
1091
+ "grad_norm": 0.18269892602018764,
1092
+ "learning_rate": 7.383697509273424e-06,
1093
+ "loss": 0.367,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 2.6827171109200343,
1098
+ "grad_norm": 0.18647288570365314,
1099
+ "learning_rate": 6.646744943781325e-06,
1100
+ "loss": 0.3724,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 2.699914015477214,
1105
+ "grad_norm": 0.18698726008663819,
1106
+ "learning_rate": 5.947265732317408e-06,
1107
+ "loss": 0.3659,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 2.717110920034394,
1112
+ "grad_norm": 0.18309326292481923,
1113
+ "learning_rate": 5.285540656008303e-06,
1114
+ "loss": 0.3757,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 2.7343078245915735,
1119
+ "grad_norm": 0.18668212507421977,
1120
+ "learning_rate": 4.6618353409217386e-06,
1121
+ "loss": 0.3673,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 2.751504729148753,
1126
+ "grad_norm": 0.1840554864418513,
1127
+ "learning_rate": 4.076400151440485e-06,
1128
+ "loss": 0.367,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 2.768701633705933,
1133
+ "grad_norm": 0.1838274059601279,
1134
+ "learning_rate": 3.529470089762421e-06,
1135
+ "loss": 0.3676,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 2.7858985382631127,
1140
+ "grad_norm": 0.1905340116630113,
1141
+ "learning_rate": 3.021264701567206e-06,
1142
+ "loss": 0.3745,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 2.8030954428202923,
1147
+ "grad_norm": 0.1859751703399611,
1148
+ "learning_rate": 2.551987987887461e-06,
1149
+ "loss": 0.369,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 2.820292347377472,
1154
+ "grad_norm": 0.18905809126144052,
1155
+ "learning_rate": 2.1218283232198212e-06,
1156
+ "loss": 0.3774,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 2.8374892519346515,
1161
+ "grad_norm": 0.1853105742586414,
1162
+ "learning_rate": 1.7309583799086094e-06,
1163
+ "loss": 0.3726,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 2.8546861564918316,
1168
+ "grad_norm": 0.1840942740034349,
1169
+ "learning_rate": 1.3795350588327261e-06,
1170
+ "loss": 0.3779,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 2.871883061049011,
1175
+ "grad_norm": 0.18025938643579378,
1176
+ "learning_rate": 1.0676994264232854e-06,
1177
+ "loss": 0.3692,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 2.8890799656061907,
1182
+ "grad_norm": 0.18685969171459274,
1183
+ "learning_rate": 7.955766580375335e-07,
1184
+ "loss": 0.3688,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 2.9062768701633708,
1189
+ "grad_norm": 0.1830773378552538,
1190
+ "learning_rate": 5.632759877116422e-07,
1191
+ "loss": 0.3738,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 2.9234737747205504,
1196
+ "grad_norm": 0.18687096055320696,
1197
+ "learning_rate": 3.708906643125509e-07,
1198
+ "loss": 0.3754,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 2.94067067927773,
1203
+ "grad_norm": 0.18843515900821306,
1204
+ "learning_rate": 2.184979141065413e-07,
1205
+ "loss": 0.374,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 2.9578675838349096,
1210
+ "grad_norm": 0.1907738099777219,
1211
+ "learning_rate": 1.061589097595017e-07,
1212
+ "loss": 0.3719,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 2.9750644883920896,
1217
+ "grad_norm": 0.18629496289787387,
1218
+ "learning_rate": 3.3918745781291725e-08,
1219
+ "loss": 0.3734,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 2.992261392949269,
1224
+ "grad_norm": 0.1807736649886976,
1225
+ "learning_rate": 1.8064204241774462e-09,
1226
+ "loss": 0.3669,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 2.997420464316423,
1231
+ "step": 1743,
1232
+ "total_flos": 1.7624457120055296e+16,
1233
+ "train_loss": 0.4506890232783245,
1234
+ "train_runtime": 9589.9992,
1235
+ "train_samples_per_second": 5.818,
1236
+ "train_steps_per_second": 0.182
1237
+ }
1238
+ ],
1239
+ "logging_steps": 10,
1240
+ "max_steps": 1743,
1241
+ "num_input_tokens_seen": 0,
1242
+ "num_train_epochs": 3,
1243
+ "save_steps": 500,
1244
+ "stateful_callbacks": {
1245
+ "TrainerControl": {
1246
+ "args": {
1247
+ "should_epoch_stop": false,
1248
+ "should_evaluate": false,
1249
+ "should_log": false,
1250
+ "should_save": true,
1251
+ "should_training_stop": true
1252
+ },
1253
+ "attributes": {}
1254
+ }
1255
+ },
1256
+ "total_flos": 1.7624457120055296e+16,
1257
+ "train_batch_size": 4,
1258
+ "trial_name": null,
1259
+ "trial_params": null
1260
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec8059564270233c463911936512c79ec62b3b3bf31419a7cf3e709dbd672566
3
+ size 6904