HF中国镜像站's logo

Grogros
/
dmWM-llama-3.2-1B-Instruct-OWT-1WT-DistillationWM-Al4-WT-v4

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
Grogros commited on
Commit
2ccf930
·
verified ·
1 Parent(s): 8b346a9

Training in progress, step 5000, checkpoint

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. checkpoint-5000/config.json +40 -0
  3. checkpoint-5000/generation_config.json +12 -0
  4. checkpoint-5000/model.safetensors +3 -0
  5. checkpoint-5000/optimizer.pt +3 -0
  6. checkpoint-5000/rng_state.pth +3 -0
  7. checkpoint-5000/scheduler.pt +3 -0
  8. checkpoint-5000/special_tokens_map.json +26 -0
  9. checkpoint-5000/tokenizer.json +3 -0
  10. checkpoint-5000/tokenizer_config.json +2075 -0
  11. checkpoint-5000/trainer_state.json +3533 -0
  12. checkpoint-5000/training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-5000/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.46.3",
38
+ "use_cache": true,
39
+ "vocab_size": 128257
40
+ }
checkpoint-5000/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.46.3"
12
+ }
checkpoint-5000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ff0259c2ea4e6874e717af94e00181b8b79ab33718dc6036995cb88ef42772c
3
+ size 2471649704
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd521100d30e9c39feb6b26d62eee8ddee2b52ac28c9b4342fdaaa80402c3a79
3
+ size 3724602
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94cdb1df481c5e5c4c8f40760a34fc469800b5b61e209a0872d685354c83f1d2
3
+ size 14244
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2be67f6aac8e482bb2022409709d8774ffb125292c0c9cf025c0ae747f3a6d57
3
+ size 1064
checkpoint-5000/special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "[WM0]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
checkpoint-5000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f0419d282d3dfb298243a9bcaf3a09958ff5e7ae58addd8d84589350d692950
3
+ size 17210102
checkpoint-5000/tokenizer_config.json ADDED
@@ -0,0 +1,2075 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "[WM0]",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ }
2059
+ },
2060
+ "additional_special_tokens": [
2061
+ "[WM0]"
2062
+ ],
2063
+ "bos_token": "<|begin_of_text|>",
2064
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2065
+ "clean_up_tokenization_spaces": true,
2066
+ "eos_token": "<|eot_id|>",
2067
+ "model_input_names": [
2068
+ "input_ids",
2069
+ "attention_mask"
2070
+ ],
2071
+ "model_max_length": 131072,
2072
+ "pad_token": "<|eot_id|>",
2073
+ "padding_side": "left",
2074
+ "tokenizer_class": "PreTrainedTokenizerFast"
2075
+ }
checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,3533 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.002,
13
+ "grad_norm": 73.0,
14
+ "learning_rate": 4.0000000000000003e-07,
15
+ "loss": 8.3248,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.004,
20
+ "grad_norm": 67.5,
21
+ "learning_rate": 8.000000000000001e-07,
22
+ "loss": 8.3631,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.006,
27
+ "grad_norm": 187.0,
28
+ "learning_rate": 1.2000000000000002e-06,
29
+ "loss": 8.3584,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.008,
34
+ "grad_norm": 80.5,
35
+ "learning_rate": 1.6000000000000001e-06,
36
+ "loss": 8.3513,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.01,
41
+ "grad_norm": 215.0,
42
+ "learning_rate": 2.0000000000000003e-06,
43
+ "loss": 8.2452,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.012,
48
+ "grad_norm": 165.0,
49
+ "learning_rate": 2.4000000000000003e-06,
50
+ "loss": 8.0825,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.014,
55
+ "grad_norm": 173.0,
56
+ "learning_rate": 2.8000000000000003e-06,
57
+ "loss": 8.2549,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.016,
62
+ "grad_norm": 249.0,
63
+ "learning_rate": 3.2000000000000003e-06,
64
+ "loss": 8.1791,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.018,
69
+ "grad_norm": 50.5,
70
+ "learning_rate": 3.6000000000000003e-06,
71
+ "loss": 8.1629,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.02,
76
+ "grad_norm": 104.5,
77
+ "learning_rate": 4.000000000000001e-06,
78
+ "loss": 8.0528,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.022,
83
+ "grad_norm": 119.5,
84
+ "learning_rate": 4.4e-06,
85
+ "loss": 8.2228,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.024,
90
+ "grad_norm": 53.75,
91
+ "learning_rate": 4.800000000000001e-06,
92
+ "loss": 7.9952,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.026,
97
+ "grad_norm": 102.0,
98
+ "learning_rate": 5.2e-06,
99
+ "loss": 7.986,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.028,
104
+ "grad_norm": 140.0,
105
+ "learning_rate": 5.600000000000001e-06,
106
+ "loss": 7.891,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.03,
111
+ "grad_norm": 117.5,
112
+ "learning_rate": 6e-06,
113
+ "loss": 8.0424,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.032,
118
+ "grad_norm": 56.0,
119
+ "learning_rate": 6.4000000000000006e-06,
120
+ "loss": 7.9438,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.034,
125
+ "grad_norm": 75.5,
126
+ "learning_rate": 6.800000000000001e-06,
127
+ "loss": 7.7166,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.036,
132
+ "grad_norm": 78.0,
133
+ "learning_rate": 7.2000000000000005e-06,
134
+ "loss": 7.8447,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.038,
139
+ "grad_norm": 141.0,
140
+ "learning_rate": 7.600000000000001e-06,
141
+ "loss": 7.9219,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.04,
146
+ "grad_norm": 77.5,
147
+ "learning_rate": 8.000000000000001e-06,
148
+ "loss": 7.8696,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.042,
153
+ "grad_norm": 49.25,
154
+ "learning_rate": 8.400000000000001e-06,
155
+ "loss": 7.7408,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.044,
160
+ "grad_norm": 46.75,
161
+ "learning_rate": 8.8e-06,
162
+ "loss": 7.7317,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.046,
167
+ "grad_norm": 24.0,
168
+ "learning_rate": 9.200000000000002e-06,
169
+ "loss": 8.215,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.048,
174
+ "grad_norm": 47.25,
175
+ "learning_rate": 9.600000000000001e-06,
176
+ "loss": 7.7039,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.05,
181
+ "grad_norm": 50.0,
182
+ "learning_rate": 1e-05,
183
+ "loss": 7.733,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.052,
188
+ "grad_norm": 51.0,
189
+ "learning_rate": 1.04e-05,
190
+ "loss": 7.5944,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.054,
195
+ "grad_norm": 55.0,
196
+ "learning_rate": 1.0800000000000002e-05,
197
+ "loss": 7.732,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.056,
202
+ "grad_norm": 37.5,
203
+ "learning_rate": 1.1200000000000001e-05,
204
+ "loss": 7.7018,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.058,
209
+ "grad_norm": 51.75,
210
+ "learning_rate": 1.16e-05,
211
+ "loss": 7.6174,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.06,
216
+ "grad_norm": 55.25,
217
+ "learning_rate": 1.2e-05,
218
+ "loss": 7.6097,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.062,
223
+ "grad_norm": 35.25,
224
+ "learning_rate": 1.2400000000000002e-05,
225
+ "loss": 7.5878,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.064,
230
+ "grad_norm": 29.875,
231
+ "learning_rate": 1.2800000000000001e-05,
232
+ "loss": 7.3251,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.066,
237
+ "grad_norm": 43.25,
238
+ "learning_rate": 1.3200000000000002e-05,
239
+ "loss": 7.5595,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.068,
244
+ "grad_norm": 53.5,
245
+ "learning_rate": 1.3600000000000002e-05,
246
+ "loss": 7.4624,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.07,
251
+ "grad_norm": 20.625,
252
+ "learning_rate": 1.4e-05,
253
+ "loss": 7.4758,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.072,
258
+ "grad_norm": 49.0,
259
+ "learning_rate": 1.4400000000000001e-05,
260
+ "loss": 7.2372,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.074,
265
+ "grad_norm": 50.75,
266
+ "learning_rate": 1.48e-05,
267
+ "loss": 7.4876,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.076,
272
+ "grad_norm": 65.5,
273
+ "learning_rate": 1.5200000000000002e-05,
274
+ "loss": 7.3212,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.078,
279
+ "grad_norm": 652.0,
280
+ "learning_rate": 1.5600000000000003e-05,
281
+ "loss": 19.1508,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.08,
286
+ "grad_norm": 856.0,
287
+ "learning_rate": 1.6000000000000003e-05,
288
+ "loss": 18.5063,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.082,
293
+ "grad_norm": 596.0,
294
+ "learning_rate": 1.64e-05,
295
+ "loss": 10.6256,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.084,
300
+ "grad_norm": 37.0,
301
+ "learning_rate": 1.6800000000000002e-05,
302
+ "loss": 7.8094,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.086,
307
+ "grad_norm": 48.0,
308
+ "learning_rate": 1.72e-05,
309
+ "loss": 7.7601,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.088,
314
+ "grad_norm": 229.0,
315
+ "learning_rate": 1.76e-05,
316
+ "loss": 7.7771,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.09,
321
+ "grad_norm": 71.0,
322
+ "learning_rate": 1.8e-05,
323
+ "loss": 7.8224,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.092,
328
+ "grad_norm": 139.0,
329
+ "learning_rate": 1.8400000000000003e-05,
330
+ "loss": 7.6127,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.094,
335
+ "grad_norm": 132.0,
336
+ "learning_rate": 1.88e-05,
337
+ "loss": 7.3739,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.096,
342
+ "grad_norm": 69.5,
343
+ "learning_rate": 1.9200000000000003e-05,
344
+ "loss": 7.4963,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.098,
349
+ "grad_norm": 79.5,
350
+ "learning_rate": 1.9600000000000002e-05,
351
+ "loss": 8.3617,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.1,
356
+ "grad_norm": 149.0,
357
+ "learning_rate": 2e-05,
358
+ "loss": 7.6223,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.102,
363
+ "grad_norm": 123.5,
364
+ "learning_rate": 1.9999756307053947e-05,
365
+ "loss": 7.4552,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.104,
370
+ "grad_norm": 366.0,
371
+ "learning_rate": 1.9999025240093045e-05,
372
+ "loss": 8.0613,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.106,
377
+ "grad_norm": 105.0,
378
+ "learning_rate": 1.9997806834748455e-05,
379
+ "loss": 7.4435,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.108,
384
+ "grad_norm": 46.75,
385
+ "learning_rate": 1.9996101150403543e-05,
386
+ "loss": 7.2022,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.11,
391
+ "grad_norm": 274.0,
392
+ "learning_rate": 1.999390827019096e-05,
393
+ "loss": 7.4214,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.112,
398
+ "grad_norm": 152.0,
399
+ "learning_rate": 1.9991228300988586e-05,
400
+ "loss": 7.1869,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.114,
405
+ "grad_norm": 173.0,
406
+ "learning_rate": 1.9988061373414342e-05,
407
+ "loss": 7.0579,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.116,
412
+ "grad_norm": 284.0,
413
+ "learning_rate": 1.9984407641819812e-05,
414
+ "loss": 7.0003,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.118,
419
+ "grad_norm": 75.0,
420
+ "learning_rate": 1.9980267284282718e-05,
421
+ "loss": 6.7439,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.12,
426
+ "grad_norm": 71.5,
427
+ "learning_rate": 1.9975640502598243e-05,
428
+ "loss": 7.3533,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.122,
433
+ "grad_norm": 76.5,
434
+ "learning_rate": 1.9970527522269204e-05,
435
+ "loss": 7.6339,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.124,
440
+ "grad_norm": 47.5,
441
+ "learning_rate": 1.9964928592495046e-05,
442
+ "loss": 7.0495,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.126,
447
+ "grad_norm": 54.5,
448
+ "learning_rate": 1.9958843986159705e-05,
449
+ "loss": 7.0648,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.128,
454
+ "grad_norm": 63.75,
455
+ "learning_rate": 1.9952273999818312e-05,
456
+ "loss": 6.6651,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.13,
461
+ "grad_norm": 45.75,
462
+ "learning_rate": 1.9945218953682736e-05,
463
+ "loss": 6.6191,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.132,
468
+ "grad_norm": 79.0,
469
+ "learning_rate": 1.9937679191605964e-05,
470
+ "loss": 6.7345,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.134,
475
+ "grad_norm": 50.75,
476
+ "learning_rate": 1.992965508106537e-05,
477
+ "loss": 7.1927,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.136,
482
+ "grad_norm": 48.0,
483
+ "learning_rate": 1.9921147013144782e-05,
484
+ "loss": 7.0089,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.138,
489
+ "grad_norm": 42.5,
490
+ "learning_rate": 1.991215540251542e-05,
491
+ "loss": 6.7026,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.14,
496
+ "grad_norm": 64.0,
497
+ "learning_rate": 1.9902680687415704e-05,
498
+ "loss": 6.4639,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.142,
503
+ "grad_norm": 51.25,
504
+ "learning_rate": 1.9892723329629885e-05,
505
+ "loss": 6.4697,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.144,
510
+ "grad_norm": 68.5,
511
+ "learning_rate": 1.988228381446553e-05,
512
+ "loss": 6.5715,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.146,
517
+ "grad_norm": 95.5,
518
+ "learning_rate": 1.987136265072988e-05,
519
+ "loss": 6.8523,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.148,
524
+ "grad_norm": 60.75,
525
+ "learning_rate": 1.985996037070505e-05,
526
+ "loss": 6.4502,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.15,
531
+ "grad_norm": 52.5,
532
+ "learning_rate": 1.9848077530122083e-05,
533
+ "loss": 6.7715,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.152,
538
+ "grad_norm": 95.5,
539
+ "learning_rate": 1.983571470813386e-05,
540
+ "loss": 6.6155,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.154,
545
+ "grad_norm": 74.0,
546
+ "learning_rate": 1.982287250728689e-05,
547
+ "loss": 6.1734,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.156,
552
+ "grad_norm": 43.25,
553
+ "learning_rate": 1.9809551553491918e-05,
554
+ "loss": 6.3684,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.158,
559
+ "grad_norm": 65.0,
560
+ "learning_rate": 1.979575249599344e-05,
561
+ "loss": 6.6459,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.16,
566
+ "grad_norm": 52.0,
567
+ "learning_rate": 1.9781476007338058e-05,
568
+ "loss": 6.2982,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.162,
573
+ "grad_norm": 74.0,
574
+ "learning_rate": 1.9766722783341682e-05,
575
+ "loss": 6.3486,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.164,
580
+ "grad_norm": 28.5,
581
+ "learning_rate": 1.9751493543055634e-05,
582
+ "loss": 6.4404,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.166,
587
+ "grad_norm": 28.625,
588
+ "learning_rate": 1.9735789028731603e-05,
589
+ "loss": 6.3036,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.168,
594
+ "grad_norm": 42.0,
595
+ "learning_rate": 1.9719610005785466e-05,
596
+ "loss": 6.2275,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.17,
601
+ "grad_norm": 26.875,
602
+ "learning_rate": 1.9702957262759964e-05,
603
+ "loss": 6.1878,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.172,
608
+ "grad_norm": 22.625,
609
+ "learning_rate": 1.9685831611286312e-05,
610
+ "loss": 6.3158,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.174,
615
+ "grad_norm": 19.625,
616
+ "learning_rate": 1.9668233886044597e-05,
617
+ "loss": 6.2315,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.176,
622
+ "grad_norm": 235.0,
623
+ "learning_rate": 1.9650164944723116e-05,
624
+ "loss": 6.0065,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.178,
629
+ "grad_norm": 21.625,
630
+ "learning_rate": 1.9631625667976584e-05,
631
+ "loss": 5.8419,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.18,
636
+ "grad_norm": 58.25,
637
+ "learning_rate": 1.961261695938319e-05,
638
+ "loss": 6.3122,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.182,
643
+ "grad_norm": 40.75,
644
+ "learning_rate": 1.9593139745400575e-05,
645
+ "loss": 5.9193,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.184,
650
+ "grad_norm": 35.0,
651
+ "learning_rate": 1.9573194975320672e-05,
652
+ "loss": 5.975,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.186,
657
+ "grad_norm": 39.25,
658
+ "learning_rate": 1.9552783621223437e-05,
659
+ "loss": 6.1436,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.188,
664
+ "grad_norm": 64.5,
665
+ "learning_rate": 1.9531906677929472e-05,
666
+ "loss": 5.9109,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.19,
671
+ "grad_norm": 36.25,
672
+ "learning_rate": 1.9510565162951538e-05,
673
+ "loss": 5.8925,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.192,
678
+ "grad_norm": 57.75,
679
+ "learning_rate": 1.9488760116444966e-05,
680
+ "loss": 6.0097,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.194,
685
+ "grad_norm": 54.0,
686
+ "learning_rate": 1.9466492601156964e-05,
687
+ "loss": 5.9063,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.196,
692
+ "grad_norm": 28.875,
693
+ "learning_rate": 1.944376370237481e-05,
694
+ "loss": 5.7987,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.198,
699
+ "grad_norm": 45.0,
700
+ "learning_rate": 1.942057452787297e-05,
701
+ "loss": 6.1145,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.2,
706
+ "grad_norm": 55.25,
707
+ "learning_rate": 1.9396926207859085e-05,
708
+ "loss": 5.9971,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.202,
713
+ "grad_norm": 72.0,
714
+ "learning_rate": 1.937281989491892e-05,
715
+ "loss": 5.7074,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.204,
720
+ "grad_norm": 30.875,
721
+ "learning_rate": 1.9348256763960146e-05,
722
+ "loss": 5.7106,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.206,
727
+ "grad_norm": 37.5,
728
+ "learning_rate": 1.9323238012155125e-05,
729
+ "loss": 6.0611,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.208,
734
+ "grad_norm": 18.125,
735
+ "learning_rate": 1.9297764858882516e-05,
736
+ "loss": 5.9725,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.21,
741
+ "grad_norm": 74.5,
742
+ "learning_rate": 1.9271838545667876e-05,
743
+ "loss": 5.6651,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.212,
748
+ "grad_norm": 42.0,
749
+ "learning_rate": 1.9245460336123136e-05,
750
+ "loss": 5.6407,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.214,
755
+ "grad_norm": 27.875,
756
+ "learning_rate": 1.9218631515885007e-05,
757
+ "loss": 5.7474,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.216,
762
+ "grad_norm": 35.5,
763
+ "learning_rate": 1.9191353392552346e-05,
764
+ "loss": 5.7554,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.218,
769
+ "grad_norm": 36.75,
770
+ "learning_rate": 1.9163627295622397e-05,
771
+ "loss": 5.9383,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.22,
776
+ "grad_norm": 31.25,
777
+ "learning_rate": 1.913545457642601e-05,
778
+ "loss": 5.7704,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.222,
783
+ "grad_norm": 60.75,
784
+ "learning_rate": 1.910683660806177e-05,
785
+ "loss": 5.7273,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.224,
790
+ "grad_norm": 58.25,
791
+ "learning_rate": 1.907777478532909e-05,
792
+ "loss": 5.5201,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.226,
797
+ "grad_norm": 37.25,
798
+ "learning_rate": 1.9048270524660197e-05,
799
+ "loss": 5.6245,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.228,
804
+ "grad_norm": 62.25,
805
+ "learning_rate": 1.901832526405114e-05,
806
+ "loss": 5.5519,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.23,
811
+ "grad_norm": 36.5,
812
+ "learning_rate": 1.8987940462991673e-05,
813
+ "loss": 5.7053,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.232,
818
+ "grad_norm": 30.625,
819
+ "learning_rate": 1.895711760239413e-05,
820
+ "loss": 5.5692,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.234,
825
+ "grad_norm": 69.0,
826
+ "learning_rate": 1.892585818452126e-05,
827
+ "loss": 5.4042,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.236,
832
+ "grad_norm": 32.0,
833
+ "learning_rate": 1.889416373291298e-05,
834
+ "loss": 5.4639,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.238,
839
+ "grad_norm": 45.75,
840
+ "learning_rate": 1.8862035792312148e-05,
841
+ "loss": 5.5483,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.24,
846
+ "grad_norm": 31.0,
847
+ "learning_rate": 1.8829475928589272e-05,
848
+ "loss": 5.409,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.242,
853
+ "grad_norm": 45.75,
854
+ "learning_rate": 1.879648572866617e-05,
855
+ "loss": 5.5903,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.244,
860
+ "grad_norm": 26.625,
861
+ "learning_rate": 1.8763066800438638e-05,
862
+ "loss": 5.5818,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.246,
867
+ "grad_norm": 20.5,
868
+ "learning_rate": 1.8729220772698096e-05,
869
+ "loss": 5.5353,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.248,
874
+ "grad_norm": 28.875,
875
+ "learning_rate": 1.869494929505219e-05,
876
+ "loss": 5.4082,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.25,
881
+ "grad_norm": 44.5,
882
+ "learning_rate": 1.866025403784439e-05,
883
+ "loss": 5.3274,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.252,
888
+ "grad_norm": 29.75,
889
+ "learning_rate": 1.8625136692072577e-05,
890
+ "loss": 5.4699,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.254,
895
+ "grad_norm": 28.5,
896
+ "learning_rate": 1.8589598969306646e-05,
897
+ "loss": 5.5373,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.256,
902
+ "grad_norm": 36.0,
903
+ "learning_rate": 1.855364260160507e-05,
904
+ "loss": 5.4271,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.258,
909
+ "grad_norm": 32.75,
910
+ "learning_rate": 1.851726934143048e-05,
911
+ "loss": 5.3478,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.26,
916
+ "grad_norm": 28.5,
917
+ "learning_rate": 1.848048096156426e-05,
918
+ "loss": 5.4025,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.262,
923
+ "grad_norm": 67.0,
924
+ "learning_rate": 1.8443279255020153e-05,
925
+ "loss": 5.3553,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.264,
930
+ "grad_norm": 25.875,
931
+ "learning_rate": 1.8405666034956842e-05,
932
+ "loss": 5.2989,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.266,
937
+ "grad_norm": 31.5,
938
+ "learning_rate": 1.836764313458962e-05,
939
+ "loss": 5.5159,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.268,
944
+ "grad_norm": 35.0,
945
+ "learning_rate": 1.8329212407100996e-05,
946
+ "loss": 5.489,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 0.27,
951
+ "grad_norm": 35.0,
952
+ "learning_rate": 1.8290375725550417e-05,
953
+ "loss": 5.5776,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 0.272,
958
+ "grad_norm": 32.25,
959
+ "learning_rate": 1.8251134982782952e-05,
960
+ "loss": 5.4482,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 0.274,
965
+ "grad_norm": 44.25,
966
+ "learning_rate": 1.821149209133704e-05,
967
+ "loss": 5.2529,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 0.276,
972
+ "grad_norm": 33.25,
973
+ "learning_rate": 1.8171448983351284e-05,
974
+ "loss": 5.1984,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 0.278,
979
+ "grad_norm": 41.5,
980
+ "learning_rate": 1.8131007610470278e-05,
981
+ "loss": 5.4162,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 0.28,
986
+ "grad_norm": 32.75,
987
+ "learning_rate": 1.8090169943749477e-05,
988
+ "loss": 5.2605,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 0.282,
993
+ "grad_norm": 37.0,
994
+ "learning_rate": 1.804893797355914e-05,
995
+ "loss": 5.2973,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 0.284,
1000
+ "grad_norm": 20.375,
1001
+ "learning_rate": 1.8007313709487334e-05,
1002
+ "loss": 5.2563,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 0.286,
1007
+ "grad_norm": 27.75,
1008
+ "learning_rate": 1.7965299180241963e-05,
1009
+ "loss": 5.4026,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 0.288,
1014
+ "grad_norm": 29.75,
1015
+ "learning_rate": 1.792289643355191e-05,
1016
+ "loss": 5.2145,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 0.29,
1021
+ "grad_norm": 68.0,
1022
+ "learning_rate": 1.788010753606722e-05,
1023
+ "loss": 5.2717,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 0.292,
1028
+ "grad_norm": 36.75,
1029
+ "learning_rate": 1.78369345732584e-05,
1030
+ "loss": 5.3034,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 0.294,
1035
+ "grad_norm": 25.75,
1036
+ "learning_rate": 1.7793379649314743e-05,
1037
+ "loss": 5.2484,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 0.296,
1042
+ "grad_norm": 20.75,
1043
+ "learning_rate": 1.7749444887041797e-05,
1044
+ "loss": 5.2891,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 0.298,
1049
+ "grad_norm": 71.0,
1050
+ "learning_rate": 1.7705132427757895e-05,
1051
+ "loss": 5.2213,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 0.3,
1056
+ "grad_norm": 30.75,
1057
+ "learning_rate": 1.766044443118978e-05,
1058
+ "loss": 5.2227,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 0.302,
1063
+ "grad_norm": 18.0,
1064
+ "learning_rate": 1.761538307536737e-05,
1065
+ "loss": 5.1062,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 0.304,
1070
+ "grad_norm": 52.25,
1071
+ "learning_rate": 1.7569950556517566e-05,
1072
+ "loss": 5.2483,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 0.306,
1077
+ "grad_norm": 37.25,
1078
+ "learning_rate": 1.7524149088957244e-05,
1079
+ "loss": 5.1347,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 0.308,
1084
+ "grad_norm": 29.0,
1085
+ "learning_rate": 1.747798090498532e-05,
1086
+ "loss": 5.1357,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 0.31,
1091
+ "grad_norm": 32.75,
1092
+ "learning_rate": 1.7431448254773943e-05,
1093
+ "loss": 5.1755,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 0.312,
1098
+ "grad_norm": 23.875,
1099
+ "learning_rate": 1.7384553406258842e-05,
1100
+ "loss": 5.2023,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 0.314,
1105
+ "grad_norm": 32.75,
1106
+ "learning_rate": 1.7337298645028764e-05,
1107
+ "loss": 5.0585,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 0.316,
1112
+ "grad_norm": 35.0,
1113
+ "learning_rate": 1.7289686274214116e-05,
1114
+ "loss": 5.1915,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 0.318,
1119
+ "grad_norm": 20.25,
1120
+ "learning_rate": 1.7241718614374678e-05,
1121
+ "loss": 5.8571,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 0.32,
1126
+ "grad_norm": 54.5,
1127
+ "learning_rate": 1.7193398003386514e-05,
1128
+ "loss": 5.1132,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 0.322,
1133
+ "grad_norm": 32.5,
1134
+ "learning_rate": 1.7144726796328034e-05,
1135
+ "loss": 4.9946,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 0.324,
1140
+ "grad_norm": 27.5,
1141
+ "learning_rate": 1.709570736536521e-05,
1142
+ "loss": 5.1656,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 0.326,
1147
+ "grad_norm": 18.375,
1148
+ "learning_rate": 1.7046342099635948e-05,
1149
+ "loss": 5.0306,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 0.328,
1154
+ "grad_norm": 28.125,
1155
+ "learning_rate": 1.6996633405133656e-05,
1156
+ "loss": 5.0187,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 0.33,
1161
+ "grad_norm": 17.25,
1162
+ "learning_rate": 1.6946583704589973e-05,
1163
+ "loss": 4.882,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 0.332,
1168
+ "grad_norm": 36.25,
1169
+ "learning_rate": 1.68961954373567e-05,
1170
+ "loss": 5.034,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 0.334,
1175
+ "grad_norm": 32.5,
1176
+ "learning_rate": 1.684547105928689e-05,
1177
+ "loss": 5.0543,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 0.336,
1182
+ "grad_norm": 27.125,
1183
+ "learning_rate": 1.6794413042615168e-05,
1184
+ "loss": 5.0813,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 0.338,
1189
+ "grad_norm": 27.75,
1190
+ "learning_rate": 1.6743023875837233e-05,
1191
+ "loss": 4.9171,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 0.34,
1196
+ "grad_norm": 29.5,
1197
+ "learning_rate": 1.6691306063588583e-05,
1198
+ "loss": 4.8977,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 0.342,
1203
+ "grad_norm": 16.75,
1204
+ "learning_rate": 1.6639262126522417e-05,
1205
+ "loss": 5.0774,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 0.344,
1210
+ "grad_norm": 35.25,
1211
+ "learning_rate": 1.6586894601186804e-05,
1212
+ "loss": 4.8745,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 0.346,
1217
+ "grad_norm": 22.875,
1218
+ "learning_rate": 1.6534206039901057e-05,
1219
+ "loss": 4.916,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 0.348,
1224
+ "grad_norm": 33.25,
1225
+ "learning_rate": 1.6481199010631312e-05,
1226
+ "loss": 4.7888,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 0.35,
1231
+ "grad_norm": 24.875,
1232
+ "learning_rate": 1.6427876096865394e-05,
1233
+ "loss": 4.8202,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 0.352,
1238
+ "grad_norm": 29.0,
1239
+ "learning_rate": 1.63742398974869e-05,
1240
+ "loss": 4.9507,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 0.354,
1245
+ "grad_norm": 17.125,
1246
+ "learning_rate": 1.632029302664851e-05,
1247
+ "loss": 4.8427,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 0.356,
1252
+ "grad_norm": 13.4375,
1253
+ "learning_rate": 1.6266038113644605e-05,
1254
+ "loss": 4.9219,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 0.358,
1259
+ "grad_norm": 23.875,
1260
+ "learning_rate": 1.6211477802783105e-05,
1261
+ "loss": 4.872,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 0.36,
1266
+ "grad_norm": 35.0,
1267
+ "learning_rate": 1.6156614753256583e-05,
1268
+ "loss": 4.8772,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 0.362,
1273
+ "grad_norm": 37.75,
1274
+ "learning_rate": 1.610145163901268e-05,
1275
+ "loss": 5.006,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 0.364,
1280
+ "grad_norm": 14.5,
1281
+ "learning_rate": 1.6045991148623752e-05,
1282
+ "loss": 4.7875,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 0.366,
1287
+ "grad_norm": 19.875,
1288
+ "learning_rate": 1.599023598515586e-05,
1289
+ "loss": 4.8161,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 0.368,
1294
+ "grad_norm": 40.0,
1295
+ "learning_rate": 1.5934188866037017e-05,
1296
+ "loss": 4.9093,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 0.37,
1301
+ "grad_norm": 31.875,
1302
+ "learning_rate": 1.5877852522924733e-05,
1303
+ "loss": 4.9299,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 0.372,
1308
+ "grad_norm": 30.0,
1309
+ "learning_rate": 1.5821229701572897e-05,
1310
+ "loss": 4.8612,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 0.374,
1315
+ "grad_norm": 31.375,
1316
+ "learning_rate": 1.5764323161697933e-05,
1317
+ "loss": 4.695,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 0.376,
1322
+ "grad_norm": 27.625,
1323
+ "learning_rate": 1.570713567684432e-05,
1324
+ "loss": 4.7144,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 0.378,
1329
+ "grad_norm": 33.0,
1330
+ "learning_rate": 1.564967003424938e-05,
1331
+ "loss": 4.8024,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 0.38,
1336
+ "grad_norm": 49.0,
1337
+ "learning_rate": 1.5591929034707468e-05,
1338
+ "loss": 4.8129,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 0.382,
1343
+ "grad_norm": 26.625,
1344
+ "learning_rate": 1.553391549243344e-05,
1345
+ "loss": 4.715,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 0.384,
1350
+ "grad_norm": 24.875,
1351
+ "learning_rate": 1.5475632234925505e-05,
1352
+ "loss": 4.8748,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 0.386,
1357
+ "grad_norm": 21.0,
1358
+ "learning_rate": 1.54170821028274e-05,
1359
+ "loss": 4.7073,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 0.388,
1364
+ "grad_norm": 24.0,
1365
+ "learning_rate": 1.5358267949789968e-05,
1366
+ "loss": 4.7242,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 0.39,
1371
+ "grad_norm": 27.125,
1372
+ "learning_rate": 1.529919264233205e-05,
1373
+ "loss": 4.8106,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 0.392,
1378
+ "grad_norm": 23.375,
1379
+ "learning_rate": 1.5239859059700794e-05,
1380
+ "loss": 4.8798,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 0.394,
1385
+ "grad_norm": 32.25,
1386
+ "learning_rate": 1.5180270093731305e-05,
1387
+ "loss": 4.7666,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 0.396,
1392
+ "grad_norm": 26.25,
1393
+ "learning_rate": 1.5120428648705716e-05,
1394
+ "loss": 4.8219,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 0.398,
1399
+ "grad_norm": 19.25,
1400
+ "learning_rate": 1.5060337641211637e-05,
1401
+ "loss": 4.7776,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 0.4,
1406
+ "grad_norm": 34.0,
1407
+ "learning_rate": 1.5000000000000002e-05,
1408
+ "loss": 4.8236,
1409
+ "step": 2000
1410
+ },
1411
+ {
1412
+ "epoch": 0.402,
1413
+ "grad_norm": 27.25,
1414
+ "learning_rate": 1.493941866584231e-05,
1415
+ "loss": 4.851,
1416
+ "step": 2010
1417
+ },
1418
+ {
1419
+ "epoch": 0.404,
1420
+ "grad_norm": 18.875,
1421
+ "learning_rate": 1.4878596591387329e-05,
1422
+ "loss": 4.7347,
1423
+ "step": 2020
1424
+ },
1425
+ {
1426
+ "epoch": 0.406,
1427
+ "grad_norm": 30.25,
1428
+ "learning_rate": 1.4817536741017153e-05,
1429
+ "loss": 4.6261,
1430
+ "step": 2030
1431
+ },
1432
+ {
1433
+ "epoch": 0.408,
1434
+ "grad_norm": 17.125,
1435
+ "learning_rate": 1.4756242090702756e-05,
1436
+ "loss": 4.5948,
1437
+ "step": 2040
1438
+ },
1439
+ {
1440
+ "epoch": 0.41,
1441
+ "grad_norm": 29.25,
1442
+ "learning_rate": 1.469471562785891e-05,
1443
+ "loss": 4.7584,
1444
+ "step": 2050
1445
+ },
1446
+ {
1447
+ "epoch": 0.412,
1448
+ "grad_norm": 25.125,
1449
+ "learning_rate": 1.463296035119862e-05,
1450
+ "loss": 4.7002,
1451
+ "step": 2060
1452
+ },
1453
+ {
1454
+ "epoch": 0.414,
1455
+ "grad_norm": 29.375,
1456
+ "learning_rate": 1.4570979270586944e-05,
1457
+ "loss": 4.6799,
1458
+ "step": 2070
1459
+ },
1460
+ {
1461
+ "epoch": 0.416,
1462
+ "grad_norm": 16.625,
1463
+ "learning_rate": 1.4508775406894308e-05,
1464
+ "loss": 4.6549,
1465
+ "step": 2080
1466
+ },
1467
+ {
1468
+ "epoch": 0.418,
1469
+ "grad_norm": 11.6875,
1470
+ "learning_rate": 1.4446351791849276e-05,
1471
+ "loss": 4.6667,
1472
+ "step": 2090
1473
+ },
1474
+ {
1475
+ "epoch": 0.42,
1476
+ "grad_norm": 15.875,
1477
+ "learning_rate": 1.4383711467890776e-05,
1478
+ "loss": 4.5594,
1479
+ "step": 2100
1480
+ },
1481
+ {
1482
+ "epoch": 0.422,
1483
+ "grad_norm": 14.75,
1484
+ "learning_rate": 1.4320857488019826e-05,
1485
+ "loss": 4.5978,
1486
+ "step": 2110
1487
+ },
1488
+ {
1489
+ "epoch": 0.424,
1490
+ "grad_norm": 28.125,
1491
+ "learning_rate": 1.4257792915650728e-05,
1492
+ "loss": 4.6384,
1493
+ "step": 2120
1494
+ },
1495
+ {
1496
+ "epoch": 0.426,
1497
+ "grad_norm": 22.25,
1498
+ "learning_rate": 1.4194520824461773e-05,
1499
+ "loss": 4.5903,
1500
+ "step": 2130
1501
+ },
1502
+ {
1503
+ "epoch": 0.428,
1504
+ "grad_norm": 27.0,
1505
+ "learning_rate": 1.413104429824542e-05,
1506
+ "loss": 4.5688,
1507
+ "step": 2140
1508
+ },
1509
+ {
1510
+ "epoch": 0.43,
1511
+ "grad_norm": 24.5,
1512
+ "learning_rate": 1.4067366430758004e-05,
1513
+ "loss": 4.5982,
1514
+ "step": 2150
1515
+ },
1516
+ {
1517
+ "epoch": 0.432,
1518
+ "grad_norm": 25.875,
1519
+ "learning_rate": 1.4003490325568953e-05,
1520
+ "loss": 4.6178,
1521
+ "step": 2160
1522
+ },
1523
+ {
1524
+ "epoch": 0.434,
1525
+ "grad_norm": 17.125,
1526
+ "learning_rate": 1.3939419095909513e-05,
1527
+ "loss": 4.5533,
1528
+ "step": 2170
1529
+ },
1530
+ {
1531
+ "epoch": 0.436,
1532
+ "grad_norm": 27.625,
1533
+ "learning_rate": 1.3875155864521031e-05,
1534
+ "loss": 4.6748,
1535
+ "step": 2180
1536
+ },
1537
+ {
1538
+ "epoch": 0.438,
1539
+ "grad_norm": 14.5625,
1540
+ "learning_rate": 1.3810703763502744e-05,
1541
+ "loss": 4.5406,
1542
+ "step": 2190
1543
+ },
1544
+ {
1545
+ "epoch": 0.44,
1546
+ "grad_norm": 32.25,
1547
+ "learning_rate": 1.3746065934159123e-05,
1548
+ "loss": 4.6164,
1549
+ "step": 2200
1550
+ },
1551
+ {
1552
+ "epoch": 0.442,
1553
+ "grad_norm": 15.0,
1554
+ "learning_rate": 1.3681245526846782e-05,
1555
+ "loss": 4.5947,
1556
+ "step": 2210
1557
+ },
1558
+ {
1559
+ "epoch": 0.444,
1560
+ "grad_norm": 14.8125,
1561
+ "learning_rate": 1.3616245700820922e-05,
1562
+ "loss": 4.5651,
1563
+ "step": 2220
1564
+ },
1565
+ {
1566
+ "epoch": 0.446,
1567
+ "grad_norm": 17.5,
1568
+ "learning_rate": 1.3551069624081372e-05,
1569
+ "loss": 4.6423,
1570
+ "step": 2230
1571
+ },
1572
+ {
1573
+ "epoch": 0.448,
1574
+ "grad_norm": 13.875,
1575
+ "learning_rate": 1.3485720473218153e-05,
1576
+ "loss": 4.51,
1577
+ "step": 2240
1578
+ },
1579
+ {
1580
+ "epoch": 0.45,
1581
+ "grad_norm": 19.75,
1582
+ "learning_rate": 1.342020143325669e-05,
1583
+ "loss": 4.462,
1584
+ "step": 2250
1585
+ },
1586
+ {
1587
+ "epoch": 0.452,
1588
+ "grad_norm": 22.25,
1589
+ "learning_rate": 1.3354515697502552e-05,
1590
+ "loss": 4.4713,
1591
+ "step": 2260
1592
+ },
1593
+ {
1594
+ "epoch": 0.454,
1595
+ "grad_norm": 17.375,
1596
+ "learning_rate": 1.3288666467385834e-05,
1597
+ "loss": 4.4095,
1598
+ "step": 2270
1599
+ },
1600
+ {
1601
+ "epoch": 0.456,
1602
+ "grad_norm": 32.0,
1603
+ "learning_rate": 1.3222656952305113e-05,
1604
+ "loss": 4.3921,
1605
+ "step": 2280
1606
+ },
1607
+ {
1608
+ "epoch": 0.458,
1609
+ "grad_norm": 14.625,
1610
+ "learning_rate": 1.3156490369471026e-05,
1611
+ "loss": 4.5529,
1612
+ "step": 2290
1613
+ },
1614
+ {
1615
+ "epoch": 0.46,
1616
+ "grad_norm": 25.125,
1617
+ "learning_rate": 1.3090169943749475e-05,
1618
+ "loss": 4.5369,
1619
+ "step": 2300
1620
+ },
1621
+ {
1622
+ "epoch": 0.462,
1623
+ "grad_norm": 26.5,
1624
+ "learning_rate": 1.3023698907504447e-05,
1625
+ "loss": 4.4793,
1626
+ "step": 2310
1627
+ },
1628
+ {
1629
+ "epoch": 0.464,
1630
+ "grad_norm": 24.25,
1631
+ "learning_rate": 1.2957080500440469e-05,
1632
+ "loss": 4.4755,
1633
+ "step": 2320
1634
+ },
1635
+ {
1636
+ "epoch": 0.466,
1637
+ "grad_norm": 37.25,
1638
+ "learning_rate": 1.2890317969444716e-05,
1639
+ "loss": 4.6139,
1640
+ "step": 2330
1641
+ },
1642
+ {
1643
+ "epoch": 0.468,
1644
+ "grad_norm": 21.0,
1645
+ "learning_rate": 1.2823414568428767e-05,
1646
+ "loss": 4.5247,
1647
+ "step": 2340
1648
+ },
1649
+ {
1650
+ "epoch": 0.47,
1651
+ "grad_norm": 18.5,
1652
+ "learning_rate": 1.2756373558169992e-05,
1653
+ "loss": 4.4874,
1654
+ "step": 2350
1655
+ },
1656
+ {
1657
+ "epoch": 0.472,
1658
+ "grad_norm": 16.125,
1659
+ "learning_rate": 1.2689198206152657e-05,
1660
+ "loss": 4.4495,
1661
+ "step": 2360
1662
+ },
1663
+ {
1664
+ "epoch": 0.474,
1665
+ "grad_norm": 17.5,
1666
+ "learning_rate": 1.2621891786408648e-05,
1667
+ "loss": 4.5414,
1668
+ "step": 2370
1669
+ },
1670
+ {
1671
+ "epoch": 0.476,
1672
+ "grad_norm": 21.5,
1673
+ "learning_rate": 1.2554457579357906e-05,
1674
+ "loss": 4.5677,
1675
+ "step": 2380
1676
+ },
1677
+ {
1678
+ "epoch": 0.478,
1679
+ "grad_norm": 12.5,
1680
+ "learning_rate": 1.2486898871648552e-05,
1681
+ "loss": 4.4325,
1682
+ "step": 2390
1683
+ },
1684
+ {
1685
+ "epoch": 0.48,
1686
+ "grad_norm": 16.625,
1687
+ "learning_rate": 1.2419218955996677e-05,
1688
+ "loss": 4.4975,
1689
+ "step": 2400
1690
+ },
1691
+ {
1692
+ "epoch": 0.482,
1693
+ "grad_norm": 19.5,
1694
+ "learning_rate": 1.23514211310259e-05,
1695
+ "loss": 4.4956,
1696
+ "step": 2410
1697
+ },
1698
+ {
1699
+ "epoch": 0.484,
1700
+ "grad_norm": 12.8125,
1701
+ "learning_rate": 1.2283508701106559e-05,
1702
+ "loss": 4.4802,
1703
+ "step": 2420
1704
+ },
1705
+ {
1706
+ "epoch": 0.486,
1707
+ "grad_norm": 24.0,
1708
+ "learning_rate": 1.2215484976194675e-05,
1709
+ "loss": 4.4064,
1710
+ "step": 2430
1711
+ },
1712
+ {
1713
+ "epoch": 0.488,
1714
+ "grad_norm": 17.25,
1715
+ "learning_rate": 1.2147353271670634e-05,
1716
+ "loss": 4.4023,
1717
+ "step": 2440
1718
+ },
1719
+ {
1720
+ "epoch": 0.49,
1721
+ "grad_norm": 25.125,
1722
+ "learning_rate": 1.2079116908177592e-05,
1723
+ "loss": 4.473,
1724
+ "step": 2450
1725
+ },
1726
+ {
1727
+ "epoch": 0.492,
1728
+ "grad_norm": 23.5,
1729
+ "learning_rate": 1.2010779211459649e-05,
1730
+ "loss": 4.5529,
1731
+ "step": 2460
1732
+ },
1733
+ {
1734
+ "epoch": 0.494,
1735
+ "grad_norm": 22.375,
1736
+ "learning_rate": 1.194234351219972e-05,
1737
+ "loss": 4.4448,
1738
+ "step": 2470
1739
+ },
1740
+ {
1741
+ "epoch": 0.496,
1742
+ "grad_norm": 14.75,
1743
+ "learning_rate": 1.187381314585725e-05,
1744
+ "loss": 4.4725,
1745
+ "step": 2480
1746
+ },
1747
+ {
1748
+ "epoch": 0.498,
1749
+ "grad_norm": 14.125,
1750
+ "learning_rate": 1.1805191452505602e-05,
1751
+ "loss": 4.6705,
1752
+ "step": 2490
1753
+ },
1754
+ {
1755
+ "epoch": 0.5,
1756
+ "grad_norm": 24.5,
1757
+ "learning_rate": 1.1736481776669307e-05,
1758
+ "loss": 4.479,
1759
+ "step": 2500
1760
+ },
1761
+ {
1762
+ "epoch": 0.502,
1763
+ "grad_norm": 14.75,
1764
+ "learning_rate": 1.1667687467161025e-05,
1765
+ "loss": 4.4704,
1766
+ "step": 2510
1767
+ },
1768
+ {
1769
+ "epoch": 0.504,
1770
+ "grad_norm": 26.625,
1771
+ "learning_rate": 1.159881187691835e-05,
1772
+ "loss": 4.4934,
1773
+ "step": 2520
1774
+ },
1775
+ {
1776
+ "epoch": 0.506,
1777
+ "grad_norm": 18.0,
1778
+ "learning_rate": 1.1529858362840383e-05,
1779
+ "loss": 4.518,
1780
+ "step": 2530
1781
+ },
1782
+ {
1783
+ "epoch": 0.508,
1784
+ "grad_norm": 16.125,
1785
+ "learning_rate": 1.1460830285624119e-05,
1786
+ "loss": 4.5856,
1787
+ "step": 2540
1788
+ },
1789
+ {
1790
+ "epoch": 0.51,
1791
+ "grad_norm": 14.875,
1792
+ "learning_rate": 1.1391731009600655e-05,
1793
+ "loss": 4.5185,
1794
+ "step": 2550
1795
+ },
1796
+ {
1797
+ "epoch": 0.512,
1798
+ "grad_norm": 18.625,
1799
+ "learning_rate": 1.1322563902571227e-05,
1800
+ "loss": 4.3523,
1801
+ "step": 2560
1802
+ },
1803
+ {
1804
+ "epoch": 0.514,
1805
+ "grad_norm": 24.625,
1806
+ "learning_rate": 1.1253332335643043e-05,
1807
+ "loss": 4.4494,
1808
+ "step": 2570
1809
+ },
1810
+ {
1811
+ "epoch": 0.516,
1812
+ "grad_norm": 25.75,
1813
+ "learning_rate": 1.1184039683065014e-05,
1814
+ "loss": 4.4413,
1815
+ "step": 2580
1816
+ },
1817
+ {
1818
+ "epoch": 0.518,
1819
+ "grad_norm": 24.25,
1820
+ "learning_rate": 1.1114689322063255e-05,
1821
+ "loss": 4.4768,
1822
+ "step": 2590
1823
+ },
1824
+ {
1825
+ "epoch": 0.52,
1826
+ "grad_norm": 20.875,
1827
+ "learning_rate": 1.1045284632676535e-05,
1828
+ "loss": 4.4839,
1829
+ "step": 2600
1830
+ },
1831
+ {
1832
+ "epoch": 0.522,
1833
+ "grad_norm": 20.375,
1834
+ "learning_rate": 1.0975828997591496e-05,
1835
+ "loss": 4.4481,
1836
+ "step": 2610
1837
+ },
1838
+ {
1839
+ "epoch": 0.524,
1840
+ "grad_norm": 13.875,
1841
+ "learning_rate": 1.0906325801977804e-05,
1842
+ "loss": 4.3335,
1843
+ "step": 2620
1844
+ },
1845
+ {
1846
+ "epoch": 0.526,
1847
+ "grad_norm": 12.375,
1848
+ "learning_rate": 1.083677843332316e-05,
1849
+ "loss": 4.4381,
1850
+ "step": 2630
1851
+ },
1852
+ {
1853
+ "epoch": 0.528,
1854
+ "grad_norm": 17.625,
1855
+ "learning_rate": 1.0767190281268187e-05,
1856
+ "loss": 4.4477,
1857
+ "step": 2640
1858
+ },
1859
+ {
1860
+ "epoch": 0.53,
1861
+ "grad_norm": 23.625,
1862
+ "learning_rate": 1.0697564737441254e-05,
1863
+ "loss": 4.3895,
1864
+ "step": 2650
1865
+ },
1866
+ {
1867
+ "epoch": 0.532,
1868
+ "grad_norm": 24.625,
1869
+ "learning_rate": 1.0627905195293135e-05,
1870
+ "loss": 4.4668,
1871
+ "step": 2660
1872
+ },
1873
+ {
1874
+ "epoch": 0.534,
1875
+ "grad_norm": 17.5,
1876
+ "learning_rate": 1.055821504993164e-05,
1877
+ "loss": 4.2632,
1878
+ "step": 2670
1879
+ },
1880
+ {
1881
+ "epoch": 0.536,
1882
+ "grad_norm": 24.625,
1883
+ "learning_rate": 1.0488497697956134e-05,
1884
+ "loss": 4.2927,
1885
+ "step": 2680
1886
+ },
1887
+ {
1888
+ "epoch": 0.538,
1889
+ "grad_norm": 13.9375,
1890
+ "learning_rate": 1.0418756537291996e-05,
1891
+ "loss": 4.3524,
1892
+ "step": 2690
1893
+ },
1894
+ {
1895
+ "epoch": 0.54,
1896
+ "grad_norm": 13.375,
1897
+ "learning_rate": 1.0348994967025012e-05,
1898
+ "loss": 4.3768,
1899
+ "step": 2700
1900
+ },
1901
+ {
1902
+ "epoch": 0.542,
1903
+ "grad_norm": 20.0,
1904
+ "learning_rate": 1.0279216387235691e-05,
1905
+ "loss": 4.3714,
1906
+ "step": 2710
1907
+ },
1908
+ {
1909
+ "epoch": 0.544,
1910
+ "grad_norm": 15.625,
1911
+ "learning_rate": 1.0209424198833571e-05,
1912
+ "loss": 4.3279,
1913
+ "step": 2720
1914
+ },
1915
+ {
1916
+ "epoch": 0.546,
1917
+ "grad_norm": 24.375,
1918
+ "learning_rate": 1.0139621803391454e-05,
1919
+ "loss": 4.3253,
1920
+ "step": 2730
1921
+ },
1922
+ {
1923
+ "epoch": 0.548,
1924
+ "grad_norm": 14.8125,
1925
+ "learning_rate": 1.0069812602979617e-05,
1926
+ "loss": 4.2729,
1927
+ "step": 2740
1928
+ },
1929
+ {
1930
+ "epoch": 0.55,
1931
+ "grad_norm": 17.875,
1932
+ "learning_rate": 1e-05,
1933
+ "loss": 4.2843,
1934
+ "step": 2750
1935
+ },
1936
+ {
1937
+ "epoch": 0.552,
1938
+ "grad_norm": 12.5,
1939
+ "learning_rate": 9.930187397020385e-06,
1940
+ "loss": 4.319,
1941
+ "step": 2760
1942
+ },
1943
+ {
1944
+ "epoch": 0.554,
1945
+ "grad_norm": 26.75,
1946
+ "learning_rate": 9.860378196608549e-06,
1947
+ "loss": 4.2186,
1948
+ "step": 2770
1949
+ },
1950
+ {
1951
+ "epoch": 0.556,
1952
+ "grad_norm": 18.375,
1953
+ "learning_rate": 9.790575801166432e-06,
1954
+ "loss": 4.4126,
1955
+ "step": 2780
1956
+ },
1957
+ {
1958
+ "epoch": 0.558,
1959
+ "grad_norm": 13.75,
1960
+ "learning_rate": 9.720783612764314e-06,
1961
+ "loss": 4.2974,
1962
+ "step": 2790
1963
+ },
1964
+ {
1965
+ "epoch": 0.56,
1966
+ "grad_norm": 12.0625,
1967
+ "learning_rate": 9.651005032974994e-06,
1968
+ "loss": 4.3253,
1969
+ "step": 2800
1970
+ },
1971
+ {
1972
+ "epoch": 0.562,
1973
+ "grad_norm": 19.375,
1974
+ "learning_rate": 9.581243462708007e-06,
1975
+ "loss": 4.2868,
1976
+ "step": 2810
1977
+ },
1978
+ {
1979
+ "epoch": 0.564,
1980
+ "grad_norm": 11.9375,
1981
+ "learning_rate": 9.511502302043867e-06,
1982
+ "loss": 4.3173,
1983
+ "step": 2820
1984
+ },
1985
+ {
1986
+ "epoch": 0.566,
1987
+ "grad_norm": 18.25,
1988
+ "learning_rate": 9.441784950068362e-06,
1989
+ "loss": 4.3163,
1990
+ "step": 2830
1991
+ },
1992
+ {
1993
+ "epoch": 0.568,
1994
+ "grad_norm": 17.625,
1995
+ "learning_rate": 9.372094804706867e-06,
1996
+ "loss": 4.1307,
1997
+ "step": 2840
1998
+ },
1999
+ {
2000
+ "epoch": 0.57,
2001
+ "grad_norm": 15.9375,
2002
+ "learning_rate": 9.302435262558748e-06,
2003
+ "loss": 4.2296,
2004
+ "step": 2850
2005
+ },
2006
+ {
2007
+ "epoch": 0.572,
2008
+ "grad_norm": 14.375,
2009
+ "learning_rate": 9.232809718731815e-06,
2010
+ "loss": 4.351,
2011
+ "step": 2860
2012
+ },
2013
+ {
2014
+ "epoch": 0.574,
2015
+ "grad_norm": 17.5,
2016
+ "learning_rate": 9.163221566676847e-06,
2017
+ "loss": 4.236,
2018
+ "step": 2870
2019
+ },
2020
+ {
2021
+ "epoch": 0.576,
2022
+ "grad_norm": 12.375,
2023
+ "learning_rate": 9.093674198022201e-06,
2024
+ "loss": 4.2663,
2025
+ "step": 2880
2026
+ },
2027
+ {
2028
+ "epoch": 0.578,
2029
+ "grad_norm": 11.75,
2030
+ "learning_rate": 9.024171002408507e-06,
2031
+ "loss": 4.2749,
2032
+ "step": 2890
2033
+ },
2034
+ {
2035
+ "epoch": 0.58,
2036
+ "grad_norm": 17.75,
2037
+ "learning_rate": 8.954715367323468e-06,
2038
+ "loss": 4.2242,
2039
+ "step": 2900
2040
+ },
2041
+ {
2042
+ "epoch": 0.582,
2043
+ "grad_norm": 17.5,
2044
+ "learning_rate": 8.885310677936746e-06,
2045
+ "loss": 4.2308,
2046
+ "step": 2910
2047
+ },
2048
+ {
2049
+ "epoch": 0.584,
2050
+ "grad_norm": 12.5,
2051
+ "learning_rate": 8.815960316934991e-06,
2052
+ "loss": 4.2103,
2053
+ "step": 2920
2054
+ },
2055
+ {
2056
+ "epoch": 0.586,
2057
+ "grad_norm": 15.875,
2058
+ "learning_rate": 8.746667664356957e-06,
2059
+ "loss": 4.2607,
2060
+ "step": 2930
2061
+ },
2062
+ {
2063
+ "epoch": 0.588,
2064
+ "grad_norm": 12.6875,
2065
+ "learning_rate": 8.677436097428775e-06,
2066
+ "loss": 4.3065,
2067
+ "step": 2940
2068
+ },
2069
+ {
2070
+ "epoch": 0.59,
2071
+ "grad_norm": 23.75,
2072
+ "learning_rate": 8.60826899039935e-06,
2073
+ "loss": 4.3511,
2074
+ "step": 2950
2075
+ },
2076
+ {
2077
+ "epoch": 0.592,
2078
+ "grad_norm": 11.8125,
2079
+ "learning_rate": 8.539169714375885e-06,
2080
+ "loss": 4.1963,
2081
+ "step": 2960
2082
+ },
2083
+ {
2084
+ "epoch": 0.594,
2085
+ "grad_norm": 14.375,
2086
+ "learning_rate": 8.47014163715962e-06,
2087
+ "loss": 4.2989,
2088
+ "step": 2970
2089
+ },
2090
+ {
2091
+ "epoch": 0.596,
2092
+ "grad_norm": 12.375,
2093
+ "learning_rate": 8.401188123081653e-06,
2094
+ "loss": 4.2325,
2095
+ "step": 2980
2096
+ },
2097
+ {
2098
+ "epoch": 0.598,
2099
+ "grad_norm": 12.9375,
2100
+ "learning_rate": 8.332312532838978e-06,
2101
+ "loss": 4.2739,
2102
+ "step": 2990
2103
+ },
2104
+ {
2105
+ "epoch": 0.6,
2106
+ "grad_norm": 15.5,
2107
+ "learning_rate": 8.263518223330698e-06,
2108
+ "loss": 4.2533,
2109
+ "step": 3000
2110
+ },
2111
+ {
2112
+ "epoch": 0.602,
2113
+ "grad_norm": 38.75,
2114
+ "learning_rate": 8.194808547494401e-06,
2115
+ "loss": 4.2211,
2116
+ "step": 3010
2117
+ },
2118
+ {
2119
+ "epoch": 0.604,
2120
+ "grad_norm": 10.375,
2121
+ "learning_rate": 8.126186854142752e-06,
2122
+ "loss": 4.2882,
2123
+ "step": 3020
2124
+ },
2125
+ {
2126
+ "epoch": 0.606,
2127
+ "grad_norm": 37.0,
2128
+ "learning_rate": 8.057656487800283e-06,
2129
+ "loss": 4.3458,
2130
+ "step": 3030
2131
+ },
2132
+ {
2133
+ "epoch": 0.608,
2134
+ "grad_norm": 12.0625,
2135
+ "learning_rate": 7.989220788540356e-06,
2136
+ "loss": 4.3793,
2137
+ "step": 3040
2138
+ },
2139
+ {
2140
+ "epoch": 0.61,
2141
+ "grad_norm": 14.3125,
2142
+ "learning_rate": 7.92088309182241e-06,
2143
+ "loss": 4.3001,
2144
+ "step": 3050
2145
+ },
2146
+ {
2147
+ "epoch": 0.612,
2148
+ "grad_norm": 11.375,
2149
+ "learning_rate": 7.852646728329368e-06,
2150
+ "loss": 4.2146,
2151
+ "step": 3060
2152
+ },
2153
+ {
2154
+ "epoch": 0.614,
2155
+ "grad_norm": 21.375,
2156
+ "learning_rate": 7.784515023805328e-06,
2157
+ "loss": 4.2712,
2158
+ "step": 3070
2159
+ },
2160
+ {
2161
+ "epoch": 0.616,
2162
+ "grad_norm": 15.1875,
2163
+ "learning_rate": 7.716491298893443e-06,
2164
+ "loss": 4.3,
2165
+ "step": 3080
2166
+ },
2167
+ {
2168
+ "epoch": 0.618,
2169
+ "grad_norm": 16.625,
2170
+ "learning_rate": 7.6485788689741e-06,
2171
+ "loss": 4.2537,
2172
+ "step": 3090
2173
+ },
2174
+ {
2175
+ "epoch": 0.62,
2176
+ "grad_norm": 11.875,
2177
+ "learning_rate": 7.580781044003324e-06,
2178
+ "loss": 4.2406,
2179
+ "step": 3100
2180
+ },
2181
+ {
2182
+ "epoch": 0.622,
2183
+ "grad_norm": 14.5,
2184
+ "learning_rate": 7.513101128351454e-06,
2185
+ "loss": 4.2587,
2186
+ "step": 3110
2187
+ },
2188
+ {
2189
+ "epoch": 0.624,
2190
+ "grad_norm": 14.9375,
2191
+ "learning_rate": 7.445542420642097e-06,
2192
+ "loss": 4.19,
2193
+ "step": 3120
2194
+ },
2195
+ {
2196
+ "epoch": 0.626,
2197
+ "grad_norm": 26.125,
2198
+ "learning_rate": 7.378108213591355e-06,
2199
+ "loss": 4.1422,
2200
+ "step": 3130
2201
+ },
2202
+ {
2203
+ "epoch": 0.628,
2204
+ "grad_norm": 11.3125,
2205
+ "learning_rate": 7.310801793847344e-06,
2206
+ "loss": 4.2211,
2207
+ "step": 3140
2208
+ },
2209
+ {
2210
+ "epoch": 0.63,
2211
+ "grad_norm": 13.75,
2212
+ "learning_rate": 7.243626441830009e-06,
2213
+ "loss": 4.2761,
2214
+ "step": 3150
2215
+ },
2216
+ {
2217
+ "epoch": 0.632,
2218
+ "grad_norm": 23.875,
2219
+ "learning_rate": 7.176585431571235e-06,
2220
+ "loss": 4.2211,
2221
+ "step": 3160
2222
+ },
2223
+ {
2224
+ "epoch": 0.634,
2225
+ "grad_norm": 17.25,
2226
+ "learning_rate": 7.109682030555283e-06,
2227
+ "loss": 4.2149,
2228
+ "step": 3170
2229
+ },
2230
+ {
2231
+ "epoch": 0.636,
2232
+ "grad_norm": 16.375,
2233
+ "learning_rate": 7.042919499559538e-06,
2234
+ "loss": 4.2345,
2235
+ "step": 3180
2236
+ },
2237
+ {
2238
+ "epoch": 0.638,
2239
+ "grad_norm": 19.125,
2240
+ "learning_rate": 6.976301092495556e-06,
2241
+ "loss": 4.2704,
2242
+ "step": 3190
2243
+ },
2244
+ {
2245
+ "epoch": 0.64,
2246
+ "grad_norm": 23.375,
2247
+ "learning_rate": 6.909830056250527e-06,
2248
+ "loss": 4.1474,
2249
+ "step": 3200
2250
+ },
2251
+ {
2252
+ "epoch": 0.642,
2253
+ "grad_norm": 12.125,
2254
+ "learning_rate": 6.843509630528977e-06,
2255
+ "loss": 4.2123,
2256
+ "step": 3210
2257
+ },
2258
+ {
2259
+ "epoch": 0.644,
2260
+ "grad_norm": 12.5,
2261
+ "learning_rate": 6.777343047694891e-06,
2262
+ "loss": 4.1462,
2263
+ "step": 3220
2264
+ },
2265
+ {
2266
+ "epoch": 0.646,
2267
+ "grad_norm": 11.4375,
2268
+ "learning_rate": 6.711333532614168e-06,
2269
+ "loss": 4.2102,
2270
+ "step": 3230
2271
+ },
2272
+ {
2273
+ "epoch": 0.648,
2274
+ "grad_norm": 20.375,
2275
+ "learning_rate": 6.645484302497452e-06,
2276
+ "loss": 4.2575,
2277
+ "step": 3240
2278
+ },
2279
+ {
2280
+ "epoch": 0.65,
2281
+ "grad_norm": 10.9375,
2282
+ "learning_rate": 6.579798566743314e-06,
2283
+ "loss": 4.222,
2284
+ "step": 3250
2285
+ },
2286
+ {
2287
+ "epoch": 0.652,
2288
+ "grad_norm": 17.125,
2289
+ "learning_rate": 6.5142795267818505e-06,
2290
+ "loss": 4.2019,
2291
+ "step": 3260
2292
+ },
2293
+ {
2294
+ "epoch": 0.654,
2295
+ "grad_norm": 14.25,
2296
+ "learning_rate": 6.448930375918632e-06,
2297
+ "loss": 4.109,
2298
+ "step": 3270
2299
+ },
2300
+ {
2301
+ "epoch": 0.656,
2302
+ "grad_norm": 12.875,
2303
+ "learning_rate": 6.383754299179079e-06,
2304
+ "loss": 4.1644,
2305
+ "step": 3280
2306
+ },
2307
+ {
2308
+ "epoch": 0.658,
2309
+ "grad_norm": 14.0,
2310
+ "learning_rate": 6.318754473153221e-06,
2311
+ "loss": 4.3606,
2312
+ "step": 3290
2313
+ },
2314
+ {
2315
+ "epoch": 0.66,
2316
+ "grad_norm": 12.4375,
2317
+ "learning_rate": 6.25393406584088e-06,
2318
+ "loss": 4.3048,
2319
+ "step": 3300
2320
+ },
2321
+ {
2322
+ "epoch": 0.662,
2323
+ "grad_norm": 19.875,
2324
+ "learning_rate": 6.18929623649726e-06,
2325
+ "loss": 4.3821,
2326
+ "step": 3310
2327
+ },
2328
+ {
2329
+ "epoch": 0.664,
2330
+ "grad_norm": 12.5,
2331
+ "learning_rate": 6.124844135478971e-06,
2332
+ "loss": 4.2947,
2333
+ "step": 3320
2334
+ },
2335
+ {
2336
+ "epoch": 0.666,
2337
+ "grad_norm": 13.8125,
2338
+ "learning_rate": 6.06058090409049e-06,
2339
+ "loss": 4.255,
2340
+ "step": 3330
2341
+ },
2342
+ {
2343
+ "epoch": 0.668,
2344
+ "grad_norm": 13.3125,
2345
+ "learning_rate": 5.996509674431053e-06,
2346
+ "loss": 4.1793,
2347
+ "step": 3340
2348
+ },
2349
+ {
2350
+ "epoch": 0.67,
2351
+ "grad_norm": 22.875,
2352
+ "learning_rate": 5.932633569242e-06,
2353
+ "loss": 4.1166,
2354
+ "step": 3350
2355
+ },
2356
+ {
2357
+ "epoch": 0.672,
2358
+ "grad_norm": 15.375,
2359
+ "learning_rate": 5.868955701754584e-06,
2360
+ "loss": 4.177,
2361
+ "step": 3360
2362
+ },
2363
+ {
2364
+ "epoch": 0.674,
2365
+ "grad_norm": 13.0625,
2366
+ "learning_rate": 5.8054791755382286e-06,
2367
+ "loss": 4.1678,
2368
+ "step": 3370
2369
+ },
2370
+ {
2371
+ "epoch": 0.676,
2372
+ "grad_norm": 15.75,
2373
+ "learning_rate": 5.742207084349274e-06,
2374
+ "loss": 4.0849,
2375
+ "step": 3380
2376
+ },
2377
+ {
2378
+ "epoch": 0.678,
2379
+ "grad_norm": 12.75,
2380
+ "learning_rate": 5.679142511980176e-06,
2381
+ "loss": 4.2568,
2382
+ "step": 3390
2383
+ },
2384
+ {
2385
+ "epoch": 0.68,
2386
+ "grad_norm": 12.875,
2387
+ "learning_rate": 5.616288532109225e-06,
2388
+ "loss": 4.1335,
2389
+ "step": 3400
2390
+ },
2391
+ {
2392
+ "epoch": 0.682,
2393
+ "grad_norm": 11.75,
2394
+ "learning_rate": 5.553648208150728e-06,
2395
+ "loss": 4.0526,
2396
+ "step": 3410
2397
+ },
2398
+ {
2399
+ "epoch": 0.684,
2400
+ "grad_norm": 10.0625,
2401
+ "learning_rate": 5.491224593105695e-06,
2402
+ "loss": 4.0994,
2403
+ "step": 3420
2404
+ },
2405
+ {
2406
+ "epoch": 0.686,
2407
+ "grad_norm": 10.875,
2408
+ "learning_rate": 5.429020729413062e-06,
2409
+ "loss": 4.2511,
2410
+ "step": 3430
2411
+ },
2412
+ {
2413
+ "epoch": 0.688,
2414
+ "grad_norm": 12.6875,
2415
+ "learning_rate": 5.367039648801386e-06,
2416
+ "loss": 4.1531,
2417
+ "step": 3440
2418
+ },
2419
+ {
2420
+ "epoch": 0.69,
2421
+ "grad_norm": 17.125,
2422
+ "learning_rate": 5.305284372141095e-06,
2423
+ "loss": 4.2132,
2424
+ "step": 3450
2425
+ },
2426
+ {
2427
+ "epoch": 0.692,
2428
+ "grad_norm": 12.6875,
2429
+ "learning_rate": 5.243757909297247e-06,
2430
+ "loss": 4.1491,
2431
+ "step": 3460
2432
+ },
2433
+ {
2434
+ "epoch": 0.694,
2435
+ "grad_norm": 16.875,
2436
+ "learning_rate": 5.1824632589828465e-06,
2437
+ "loss": 4.0723,
2438
+ "step": 3470
2439
+ },
2440
+ {
2441
+ "epoch": 0.696,
2442
+ "grad_norm": 11.0,
2443
+ "learning_rate": 5.121403408612672e-06,
2444
+ "loss": 4.1871,
2445
+ "step": 3480
2446
+ },
2447
+ {
2448
+ "epoch": 0.698,
2449
+ "grad_norm": 15.9375,
2450
+ "learning_rate": 5.060581334157693e-06,
2451
+ "loss": 4.1635,
2452
+ "step": 3490
2453
+ },
2454
+ {
2455
+ "epoch": 0.7,
2456
+ "grad_norm": 10.25,
2457
+ "learning_rate": 5.000000000000003e-06,
2458
+ "loss": 4.1115,
2459
+ "step": 3500
2460
+ },
2461
+ {
2462
+ "epoch": 0.702,
2463
+ "grad_norm": 10.1875,
2464
+ "learning_rate": 4.939662358788364e-06,
2465
+ "loss": 4.0888,
2466
+ "step": 3510
2467
+ },
2468
+ {
2469
+ "epoch": 0.704,
2470
+ "grad_norm": 12.1875,
2471
+ "learning_rate": 4.879571351294287e-06,
2472
+ "loss": 4.1087,
2473
+ "step": 3520
2474
+ },
2475
+ {
2476
+ "epoch": 0.706,
2477
+ "grad_norm": 18.625,
2478
+ "learning_rate": 4.8197299062687e-06,
2479
+ "loss": 4.1721,
2480
+ "step": 3530
2481
+ },
2482
+ {
2483
+ "epoch": 0.708,
2484
+ "grad_norm": 10.75,
2485
+ "learning_rate": 4.76014094029921e-06,
2486
+ "loss": 3.9734,
2487
+ "step": 3540
2488
+ },
2489
+ {
2490
+ "epoch": 0.71,
2491
+ "grad_norm": 12.3125,
2492
+ "learning_rate": 4.700807357667953e-06,
2493
+ "loss": 4.226,
2494
+ "step": 3550
2495
+ },
2496
+ {
2497
+ "epoch": 0.712,
2498
+ "grad_norm": 14.125,
2499
+ "learning_rate": 4.641732050210032e-06,
2500
+ "loss": 4.1795,
2501
+ "step": 3560
2502
+ },
2503
+ {
2504
+ "epoch": 0.714,
2505
+ "grad_norm": 12.625,
2506
+ "learning_rate": 4.582917897172603e-06,
2507
+ "loss": 4.1441,
2508
+ "step": 3570
2509
+ },
2510
+ {
2511
+ "epoch": 0.716,
2512
+ "grad_norm": 12.9375,
2513
+ "learning_rate": 4.524367765074499e-06,
2514
+ "loss": 4.2784,
2515
+ "step": 3580
2516
+ },
2517
+ {
2518
+ "epoch": 0.718,
2519
+ "grad_norm": 10.875,
2520
+ "learning_rate": 4.46608450756656e-06,
2521
+ "loss": 4.1296,
2522
+ "step": 3590
2523
+ },
2524
+ {
2525
+ "epoch": 0.72,
2526
+ "grad_norm": 12.0625,
2527
+ "learning_rate": 4.408070965292534e-06,
2528
+ "loss": 4.1368,
2529
+ "step": 3600
2530
+ },
2531
+ {
2532
+ "epoch": 0.722,
2533
+ "grad_norm": 10.875,
2534
+ "learning_rate": 4.350329965750622e-06,
2535
+ "loss": 4.0836,
2536
+ "step": 3610
2537
+ },
2538
+ {
2539
+ "epoch": 0.724,
2540
+ "grad_norm": 10.6875,
2541
+ "learning_rate": 4.292864323155684e-06,
2542
+ "loss": 4.1473,
2543
+ "step": 3620
2544
+ },
2545
+ {
2546
+ "epoch": 0.726,
2547
+ "grad_norm": 18.625,
2548
+ "learning_rate": 4.235676838302069e-06,
2549
+ "loss": 4.1051,
2550
+ "step": 3630
2551
+ },
2552
+ {
2553
+ "epoch": 0.728,
2554
+ "grad_norm": 10.5,
2555
+ "learning_rate": 4.178770298427107e-06,
2556
+ "loss": 3.9978,
2557
+ "step": 3640
2558
+ },
2559
+ {
2560
+ "epoch": 0.73,
2561
+ "grad_norm": 11.4375,
2562
+ "learning_rate": 4.12214747707527e-06,
2563
+ "loss": 4.0953,
2564
+ "step": 3650
2565
+ },
2566
+ {
2567
+ "epoch": 0.732,
2568
+ "grad_norm": 15.4375,
2569
+ "learning_rate": 4.065811133962987e-06,
2570
+ "loss": 4.1243,
2571
+ "step": 3660
2572
+ },
2573
+ {
2574
+ "epoch": 0.734,
2575
+ "grad_norm": 9.125,
2576
+ "learning_rate": 4.009764014844143e-06,
2577
+ "loss": 4.1257,
2578
+ "step": 3670
2579
+ },
2580
+ {
2581
+ "epoch": 0.736,
2582
+ "grad_norm": 27.25,
2583
+ "learning_rate": 3.954008851376252e-06,
2584
+ "loss": 4.1052,
2585
+ "step": 3680
2586
+ },
2587
+ {
2588
+ "epoch": 0.738,
2589
+ "grad_norm": 11.0625,
2590
+ "learning_rate": 3.898548360987325e-06,
2591
+ "loss": 4.1328,
2592
+ "step": 3690
2593
+ },
2594
+ {
2595
+ "epoch": 0.74,
2596
+ "grad_norm": 13.4375,
2597
+ "learning_rate": 3.8433852467434175e-06,
2598
+ "loss": 4.1803,
2599
+ "step": 3700
2600
+ },
2601
+ {
2602
+ "epoch": 0.742,
2603
+ "grad_norm": 10.875,
2604
+ "learning_rate": 3.7885221972168974e-06,
2605
+ "loss": 4.1661,
2606
+ "step": 3710
2607
+ },
2608
+ {
2609
+ "epoch": 0.744,
2610
+ "grad_norm": 12.5,
2611
+ "learning_rate": 3.7339618863553983e-06,
2612
+ "loss": 4.1936,
2613
+ "step": 3720
2614
+ },
2615
+ {
2616
+ "epoch": 0.746,
2617
+ "grad_norm": 10.0,
2618
+ "learning_rate": 3.679706973351491e-06,
2619
+ "loss": 4.0843,
2620
+ "step": 3730
2621
+ },
2622
+ {
2623
+ "epoch": 0.748,
2624
+ "grad_norm": 11.375,
2625
+ "learning_rate": 3.625760102513103e-06,
2626
+ "loss": 4.1312,
2627
+ "step": 3740
2628
+ },
2629
+ {
2630
+ "epoch": 0.75,
2631
+ "grad_norm": 17.0,
2632
+ "learning_rate": 3.5721239031346067e-06,
2633
+ "loss": 4.3324,
2634
+ "step": 3750
2635
+ },
2636
+ {
2637
+ "epoch": 0.752,
2638
+ "grad_norm": 13.125,
2639
+ "learning_rate": 3.5188009893686916e-06,
2640
+ "loss": 4.2326,
2641
+ "step": 3760
2642
+ },
2643
+ {
2644
+ "epoch": 0.754,
2645
+ "grad_norm": 10.3125,
2646
+ "learning_rate": 3.4657939600989453e-06,
2647
+ "loss": 4.1036,
2648
+ "step": 3770
2649
+ },
2650
+ {
2651
+ "epoch": 0.756,
2652
+ "grad_norm": 11.625,
2653
+ "learning_rate": 3.4131053988131947e-06,
2654
+ "loss": 4.1307,
2655
+ "step": 3780
2656
+ },
2657
+ {
2658
+ "epoch": 0.758,
2659
+ "grad_norm": 9.8125,
2660
+ "learning_rate": 3.360737873477584e-06,
2661
+ "loss": 4.1089,
2662
+ "step": 3790
2663
+ },
2664
+ {
2665
+ "epoch": 0.76,
2666
+ "grad_norm": 14.75,
2667
+ "learning_rate": 3.308693936411421e-06,
2668
+ "loss": 4.1519,
2669
+ "step": 3800
2670
+ },
2671
+ {
2672
+ "epoch": 0.762,
2673
+ "grad_norm": 13.375,
2674
+ "learning_rate": 3.2569761241627694e-06,
2675
+ "loss": 4.233,
2676
+ "step": 3810
2677
+ },
2678
+ {
2679
+ "epoch": 0.764,
2680
+ "grad_norm": 13.875,
2681
+ "learning_rate": 3.2055869573848374e-06,
2682
+ "loss": 4.1315,
2683
+ "step": 3820
2684
+ },
2685
+ {
2686
+ "epoch": 0.766,
2687
+ "grad_norm": 10.875,
2688
+ "learning_rate": 3.1545289407131128e-06,
2689
+ "loss": 4.1942,
2690
+ "step": 3830
2691
+ },
2692
+ {
2693
+ "epoch": 0.768,
2694
+ "grad_norm": 10.3125,
2695
+ "learning_rate": 3.103804562643302e-06,
2696
+ "loss": 4.1728,
2697
+ "step": 3840
2698
+ },
2699
+ {
2700
+ "epoch": 0.77,
2701
+ "grad_norm": 13.3125,
2702
+ "learning_rate": 3.0534162954100264e-06,
2703
+ "loss": 4.1592,
2704
+ "step": 3850
2705
+ },
2706
+ {
2707
+ "epoch": 0.772,
2708
+ "grad_norm": 20.625,
2709
+ "learning_rate": 3.003366594866345e-06,
2710
+ "loss": 4.0761,
2711
+ "step": 3860
2712
+ },
2713
+ {
2714
+ "epoch": 0.774,
2715
+ "grad_norm": 13.1875,
2716
+ "learning_rate": 2.953657900364053e-06,
2717
+ "loss": 4.1848,
2718
+ "step": 3870
2719
+ },
2720
+ {
2721
+ "epoch": 0.776,
2722
+ "grad_norm": 12.125,
2723
+ "learning_rate": 2.9042926346347932e-06,
2724
+ "loss": 4.1952,
2725
+ "step": 3880
2726
+ },
2727
+ {
2728
+ "epoch": 0.778,
2729
+ "grad_norm": 10.8125,
2730
+ "learning_rate": 2.855273203671969e-06,
2731
+ "loss": 4.1672,
2732
+ "step": 3890
2733
+ },
2734
+ {
2735
+ "epoch": 0.78,
2736
+ "grad_norm": 12.125,
2737
+ "learning_rate": 2.8066019966134907e-06,
2738
+ "loss": 4.1061,
2739
+ "step": 3900
2740
+ },
2741
+ {
2742
+ "epoch": 0.782,
2743
+ "grad_norm": 10.125,
2744
+ "learning_rate": 2.7582813856253276e-06,
2745
+ "loss": 4.0374,
2746
+ "step": 3910
2747
+ },
2748
+ {
2749
+ "epoch": 0.784,
2750
+ "grad_norm": 11.6875,
2751
+ "learning_rate": 2.7103137257858867e-06,
2752
+ "loss": 4.0819,
2753
+ "step": 3920
2754
+ },
2755
+ {
2756
+ "epoch": 0.786,
2757
+ "grad_norm": 9.3125,
2758
+ "learning_rate": 2.6627013549712355e-06,
2759
+ "loss": 4.1107,
2760
+ "step": 3930
2761
+ },
2762
+ {
2763
+ "epoch": 0.788,
2764
+ "grad_norm": 12.6875,
2765
+ "learning_rate": 2.615446593741161e-06,
2766
+ "loss": 3.9885,
2767
+ "step": 3940
2768
+ },
2769
+ {
2770
+ "epoch": 0.79,
2771
+ "grad_norm": 10.9375,
2772
+ "learning_rate": 2.5685517452260566e-06,
2773
+ "loss": 4.2262,
2774
+ "step": 3950
2775
+ },
2776
+ {
2777
+ "epoch": 0.792,
2778
+ "grad_norm": 60.25,
2779
+ "learning_rate": 2.522019095014683e-06,
2780
+ "loss": 4.1427,
2781
+ "step": 3960
2782
+ },
2783
+ {
2784
+ "epoch": 0.794,
2785
+ "grad_norm": 9.5625,
2786
+ "learning_rate": 2.4758509110427576e-06,
2787
+ "loss": 4.0854,
2788
+ "step": 3970
2789
+ },
2790
+ {
2791
+ "epoch": 0.796,
2792
+ "grad_norm": 9.1875,
2793
+ "learning_rate": 2.4300494434824373e-06,
2794
+ "loss": 4.0718,
2795
+ "step": 3980
2796
+ },
2797
+ {
2798
+ "epoch": 0.798,
2799
+ "grad_norm": 11.6875,
2800
+ "learning_rate": 2.3846169246326345e-06,
2801
+ "loss": 4.1575,
2802
+ "step": 3990
2803
+ },
2804
+ {
2805
+ "epoch": 0.8,
2806
+ "grad_norm": 9.1875,
2807
+ "learning_rate": 2.339555568810221e-06,
2808
+ "loss": 3.9899,
2809
+ "step": 4000
2810
+ },
2811
+ {
2812
+ "epoch": 0.802,
2813
+ "grad_norm": 12.4375,
2814
+ "learning_rate": 2.2948675722421086e-06,
2815
+ "loss": 4.1027,
2816
+ "step": 4010
2817
+ },
2818
+ {
2819
+ "epoch": 0.804,
2820
+ "grad_norm": 12.4375,
2821
+ "learning_rate": 2.2505551129582047e-06,
2822
+ "loss": 4.0224,
2823
+ "step": 4020
2824
+ },
2825
+ {
2826
+ "epoch": 0.806,
2827
+ "grad_norm": 14.125,
2828
+ "learning_rate": 2.206620350685257e-06,
2829
+ "loss": 4.1533,
2830
+ "step": 4030
2831
+ },
2832
+ {
2833
+ "epoch": 0.808,
2834
+ "grad_norm": 14.5625,
2835
+ "learning_rate": 2.163065426741603e-06,
2836
+ "loss": 4.0205,
2837
+ "step": 4040
2838
+ },
2839
+ {
2840
+ "epoch": 0.81,
2841
+ "grad_norm": 11.625,
2842
+ "learning_rate": 2.119892463932781e-06,
2843
+ "loss": 4.1979,
2844
+ "step": 4050
2845
+ },
2846
+ {
2847
+ "epoch": 0.812,
2848
+ "grad_norm": 10.1875,
2849
+ "learning_rate": 2.0771035664480944e-06,
2850
+ "loss": 4.1409,
2851
+ "step": 4060
2852
+ },
2853
+ {
2854
+ "epoch": 0.814,
2855
+ "grad_norm": 11.875,
2856
+ "learning_rate": 2.0347008197580376e-06,
2857
+ "loss": 4.0463,
2858
+ "step": 4070
2859
+ },
2860
+ {
2861
+ "epoch": 0.816,
2862
+ "grad_norm": 12.8125,
2863
+ "learning_rate": 1.9926862905126663e-06,
2864
+ "loss": 4.1377,
2865
+ "step": 4080
2866
+ },
2867
+ {
2868
+ "epoch": 0.818,
2869
+ "grad_norm": 12.6875,
2870
+ "learning_rate": 1.95106202644086e-06,
2871
+ "loss": 4.1349,
2872
+ "step": 4090
2873
+ },
2874
+ {
2875
+ "epoch": 0.82,
2876
+ "grad_norm": 10.1875,
2877
+ "learning_rate": 1.9098300562505266e-06,
2878
+ "loss": 4.1084,
2879
+ "step": 4100
2880
+ },
2881
+ {
2882
+ "epoch": 0.822,
2883
+ "grad_norm": 11.8125,
2884
+ "learning_rate": 1.8689923895297247e-06,
2885
+ "loss": 4.1096,
2886
+ "step": 4110
2887
+ },
2888
+ {
2889
+ "epoch": 0.824,
2890
+ "grad_norm": 9.1875,
2891
+ "learning_rate": 1.8285510166487154e-06,
2892
+ "loss": 4.0338,
2893
+ "step": 4120
2894
+ },
2895
+ {
2896
+ "epoch": 0.826,
2897
+ "grad_norm": 16.75,
2898
+ "learning_rate": 1.7885079086629598e-06,
2899
+ "loss": 4.1259,
2900
+ "step": 4130
2901
+ },
2902
+ {
2903
+ "epoch": 0.828,
2904
+ "grad_norm": 11.0,
2905
+ "learning_rate": 1.7488650172170496e-06,
2906
+ "loss": 4.0407,
2907
+ "step": 4140
2908
+ },
2909
+ {
2910
+ "epoch": 0.83,
2911
+ "grad_norm": 10.4375,
2912
+ "learning_rate": 1.709624274449584e-06,
2913
+ "loss": 4.0064,
2914
+ "step": 4150
2915
+ },
2916
+ {
2917
+ "epoch": 0.832,
2918
+ "grad_norm": 16.125,
2919
+ "learning_rate": 1.6707875928990059e-06,
2920
+ "loss": 4.0912,
2921
+ "step": 4160
2922
+ },
2923
+ {
2924
+ "epoch": 0.834,
2925
+ "grad_norm": 15.25,
2926
+ "learning_rate": 1.6323568654103838e-06,
2927
+ "loss": 4.0912,
2928
+ "step": 4170
2929
+ },
2930
+ {
2931
+ "epoch": 0.836,
2932
+ "grad_norm": 10.375,
2933
+ "learning_rate": 1.5943339650431578e-06,
2934
+ "loss": 4.0621,
2935
+ "step": 4180
2936
+ },
2937
+ {
2938
+ "epoch": 0.838,
2939
+ "grad_norm": 13.0625,
2940
+ "learning_rate": 1.5567207449798517e-06,
2941
+ "loss": 4.1367,
2942
+ "step": 4190
2943
+ },
2944
+ {
2945
+ "epoch": 0.84,
2946
+ "grad_norm": 22.75,
2947
+ "learning_rate": 1.5195190384357405e-06,
2948
+ "loss": 4.1296,
2949
+ "step": 4200
2950
+ },
2951
+ {
2952
+ "epoch": 0.842,
2953
+ "grad_norm": 10.0625,
2954
+ "learning_rate": 1.4827306585695234e-06,
2955
+ "loss": 4.071,
2956
+ "step": 4210
2957
+ },
2958
+ {
2959
+ "epoch": 0.844,
2960
+ "grad_norm": 12.125,
2961
+ "learning_rate": 1.446357398394934e-06,
2962
+ "loss": 4.1607,
2963
+ "step": 4220
2964
+ },
2965
+ {
2966
+ "epoch": 0.846,
2967
+ "grad_norm": 11.6875,
2968
+ "learning_rate": 1.4104010306933558e-06,
2969
+ "loss": 4.2111,
2970
+ "step": 4230
2971
+ },
2972
+ {
2973
+ "epoch": 0.848,
2974
+ "grad_norm": 11.875,
2975
+ "learning_rate": 1.3748633079274254e-06,
2976
+ "loss": 4.1617,
2977
+ "step": 4240
2978
+ },
2979
+ {
2980
+ "epoch": 0.85,
2981
+ "grad_norm": 10.1875,
2982
+ "learning_rate": 1.339745962155613e-06,
2983
+ "loss": 4.1874,
2984
+ "step": 4250
2985
+ },
2986
+ {
2987
+ "epoch": 0.852,
2988
+ "grad_norm": 12.125,
2989
+ "learning_rate": 1.30505070494781e-06,
2990
+ "loss": 4.1662,
2991
+ "step": 4260
2992
+ },
2993
+ {
2994
+ "epoch": 0.854,
2995
+ "grad_norm": 10.75,
2996
+ "learning_rate": 1.2707792273019049e-06,
2997
+ "loss": 4.1472,
2998
+ "step": 4270
2999
+ },
3000
+ {
3001
+ "epoch": 0.856,
3002
+ "grad_norm": 10.0,
3003
+ "learning_rate": 1.2369331995613664e-06,
3004
+ "loss": 4.1187,
3005
+ "step": 4280
3006
+ },
3007
+ {
3008
+ "epoch": 0.858,
3009
+ "grad_norm": 10.625,
3010
+ "learning_rate": 1.2035142713338366e-06,
3011
+ "loss": 4.0552,
3012
+ "step": 4290
3013
+ },
3014
+ {
3015
+ "epoch": 0.86,
3016
+ "grad_norm": 9.4375,
3017
+ "learning_rate": 1.1705240714107301e-06,
3018
+ "loss": 4.023,
3019
+ "step": 4300
3020
+ },
3021
+ {
3022
+ "epoch": 0.862,
3023
+ "grad_norm": 11.5625,
3024
+ "learning_rate": 1.1379642076878528e-06,
3025
+ "loss": 4.0227,
3026
+ "step": 4310
3027
+ },
3028
+ {
3029
+ "epoch": 0.864,
3030
+ "grad_norm": 12.1875,
3031
+ "learning_rate": 1.1058362670870248e-06,
3032
+ "loss": 4.1456,
3033
+ "step": 4320
3034
+ },
3035
+ {
3036
+ "epoch": 0.866,
3037
+ "grad_norm": 11.5,
3038
+ "learning_rate": 1.0741418154787443e-06,
3039
+ "loss": 4.0723,
3040
+ "step": 4330
3041
+ },
3042
+ {
3043
+ "epoch": 0.868,
3044
+ "grad_norm": 10.5,
3045
+ "learning_rate": 1.042882397605871e-06,
3046
+ "loss": 4.1546,
3047
+ "step": 4340
3048
+ },
3049
+ {
3050
+ "epoch": 0.87,
3051
+ "grad_norm": 12.8125,
3052
+ "learning_rate": 1.012059537008332e-06,
3053
+ "loss": 4.1591,
3054
+ "step": 4350
3055
+ },
3056
+ {
3057
+ "epoch": 0.872,
3058
+ "grad_norm": 12.9375,
3059
+ "learning_rate": 9.816747359488632e-07,
3060
+ "loss": 4.1806,
3061
+ "step": 4360
3062
+ },
3063
+ {
3064
+ "epoch": 0.874,
3065
+ "grad_norm": 18.625,
3066
+ "learning_rate": 9.517294753398066e-07,
3067
+ "loss": 3.9781,
3068
+ "step": 4370
3069
+ },
3070
+ {
3071
+ "epoch": 0.876,
3072
+ "grad_norm": 12.9375,
3073
+ "learning_rate": 9.222252146709143e-07,
3074
+ "loss": 4.1027,
3075
+ "step": 4380
3076
+ },
3077
+ {
3078
+ "epoch": 0.878,
3079
+ "grad_norm": 11.0625,
3080
+ "learning_rate": 8.931633919382299e-07,
3081
+ "loss": 4.1443,
3082
+ "step": 4390
3083
+ },
3084
+ {
3085
+ "epoch": 0.88,
3086
+ "grad_norm": 10.1875,
3087
+ "learning_rate": 8.645454235739903e-07,
3088
+ "loss": 4.0687,
3089
+ "step": 4400
3090
+ },
3091
+ {
3092
+ "epoch": 0.882,
3093
+ "grad_norm": 10.8125,
3094
+ "learning_rate": 8.363727043776037e-07,
3095
+ "loss": 4.1106,
3096
+ "step": 4410
3097
+ },
3098
+ {
3099
+ "epoch": 0.884,
3100
+ "grad_norm": 10.8125,
3101
+ "learning_rate": 8.086466074476562e-07,
3102
+ "loss": 4.2019,
3103
+ "step": 4420
3104
+ },
3105
+ {
3106
+ "epoch": 0.886,
3107
+ "grad_norm": 10.75,
3108
+ "learning_rate": 7.81368484114996e-07,
3109
+ "loss": 4.1106,
3110
+ "step": 4430
3111
+ },
3112
+ {
3113
+ "epoch": 0.888,
3114
+ "grad_norm": 14.5625,
3115
+ "learning_rate": 7.545396638768698e-07,
3116
+ "loss": 4.1001,
3117
+ "step": 4440
3118
+ },
3119
+ {
3120
+ "epoch": 0.89,
3121
+ "grad_norm": 11.1875,
3122
+ "learning_rate": 7.281614543321269e-07,
3123
+ "loss": 4.1392,
3124
+ "step": 4450
3125
+ },
3126
+ {
3127
+ "epoch": 0.892,
3128
+ "grad_norm": 13.4375,
3129
+ "learning_rate": 7.022351411174866e-07,
3130
+ "loss": 4.1419,
3131
+ "step": 4460
3132
+ },
3133
+ {
3134
+ "epoch": 0.894,
3135
+ "grad_norm": 11.5,
3136
+ "learning_rate": 6.767619878448783e-07,
3137
+ "loss": 3.9657,
3138
+ "step": 4470
3139
+ },
3140
+ {
3141
+ "epoch": 0.896,
3142
+ "grad_norm": 12.1875,
3143
+ "learning_rate": 6.517432360398556e-07,
3144
+ "loss": 4.0958,
3145
+ "step": 4480
3146
+ },
3147
+ {
3148
+ "epoch": 0.898,
3149
+ "grad_norm": 9.8125,
3150
+ "learning_rate": 6.271801050810856e-07,
3151
+ "loss": 4.0957,
3152
+ "step": 4490
3153
+ },
3154
+ {
3155
+ "epoch": 0.9,
3156
+ "grad_norm": 9.625,
3157
+ "learning_rate": 6.030737921409169e-07,
3158
+ "loss": 4.0438,
3159
+ "step": 4500
3160
+ },
3161
+ {
3162
+ "epoch": 0.902,
3163
+ "grad_norm": 14.875,
3164
+ "learning_rate": 5.794254721270331e-07,
3165
+ "loss": 4.148,
3166
+ "step": 4510
3167
+ },
3168
+ {
3169
+ "epoch": 0.904,
3170
+ "grad_norm": 10.0625,
3171
+ "learning_rate": 5.562362976251901e-07,
3172
+ "loss": 4.067,
3173
+ "step": 4520
3174
+ },
3175
+ {
3176
+ "epoch": 0.906,
3177
+ "grad_norm": 9.9375,
3178
+ "learning_rate": 5.335073988430373e-07,
3179
+ "loss": 4.0452,
3180
+ "step": 4530
3181
+ },
3182
+ {
3183
+ "epoch": 0.908,
3184
+ "grad_norm": 9.875,
3185
+ "learning_rate": 5.112398835550348e-07,
3186
+ "loss": 4.0823,
3187
+ "step": 4540
3188
+ },
3189
+ {
3190
+ "epoch": 0.91,
3191
+ "grad_norm": 11.875,
3192
+ "learning_rate": 4.894348370484648e-07,
3193
+ "loss": 4.095,
3194
+ "step": 4550
3195
+ },
3196
+ {
3197
+ "epoch": 0.912,
3198
+ "grad_norm": 11.5,
3199
+ "learning_rate": 4.6809332207053083e-07,
3200
+ "loss": 4.1219,
3201
+ "step": 4560
3202
+ },
3203
+ {
3204
+ "epoch": 0.914,
3205
+ "grad_norm": 10.4375,
3206
+ "learning_rate": 4.4721637877656377e-07,
3207
+ "loss": 3.9963,
3208
+ "step": 4570
3209
+ },
3210
+ {
3211
+ "epoch": 0.916,
3212
+ "grad_norm": 13.75,
3213
+ "learning_rate": 4.268050246793276e-07,
3214
+ "loss": 4.1048,
3215
+ "step": 4580
3216
+ },
3217
+ {
3218
+ "epoch": 0.918,
3219
+ "grad_norm": 9.9375,
3220
+ "learning_rate": 4.068602545994249e-07,
3221
+ "loss": 4.0423,
3222
+ "step": 4590
3223
+ },
3224
+ {
3225
+ "epoch": 0.92,
3226
+ "grad_norm": 35.5,
3227
+ "learning_rate": 3.8738304061681107e-07,
3228
+ "loss": 4.1475,
3229
+ "step": 4600
3230
+ },
3231
+ {
3232
+ "epoch": 0.922,
3233
+ "grad_norm": 12.375,
3234
+ "learning_rate": 3.68374332023419e-07,
3235
+ "loss": 4.1381,
3236
+ "step": 4610
3237
+ },
3238
+ {
3239
+ "epoch": 0.924,
3240
+ "grad_norm": 15.25,
3241
+ "learning_rate": 3.498350552768859e-07,
3242
+ "loss": 4.0389,
3243
+ "step": 4620
3244
+ },
3245
+ {
3246
+ "epoch": 0.926,
3247
+ "grad_norm": 12.4375,
3248
+ "learning_rate": 3.3176611395540625e-07,
3249
+ "loss": 4.158,
3250
+ "step": 4630
3251
+ },
3252
+ {
3253
+ "epoch": 0.928,
3254
+ "grad_norm": 9.625,
3255
+ "learning_rate": 3.1416838871368925e-07,
3256
+ "loss": 4.1262,
3257
+ "step": 4640
3258
+ },
3259
+ {
3260
+ "epoch": 0.93,
3261
+ "grad_norm": 19.625,
3262
+ "learning_rate": 2.970427372400353e-07,
3263
+ "loss": 4.1166,
3264
+ "step": 4650
3265
+ },
3266
+ {
3267
+ "epoch": 0.932,
3268
+ "grad_norm": 11.375,
3269
+ "learning_rate": 2.8038999421453827e-07,
3270
+ "loss": 4.16,
3271
+ "step": 4660
3272
+ },
3273
+ {
3274
+ "epoch": 0.934,
3275
+ "grad_norm": 9.8125,
3276
+ "learning_rate": 2.6421097126839714e-07,
3277
+ "loss": 4.1498,
3278
+ "step": 4670
3279
+ },
3280
+ {
3281
+ "epoch": 0.936,
3282
+ "grad_norm": 10.625,
3283
+ "learning_rate": 2.4850645694436736e-07,
3284
+ "loss": 4.1886,
3285
+ "step": 4680
3286
+ },
3287
+ {
3288
+ "epoch": 0.938,
3289
+ "grad_norm": 17.875,
3290
+ "learning_rate": 2.332772166583208e-07,
3291
+ "loss": 4.2035,
3292
+ "step": 4690
3293
+ },
3294
+ {
3295
+ "epoch": 0.94,
3296
+ "grad_norm": 10.8125,
3297
+ "learning_rate": 2.1852399266194312e-07,
3298
+ "loss": 4.0977,
3299
+ "step": 4700
3300
+ },
3301
+ {
3302
+ "epoch": 0.942,
3303
+ "grad_norm": 11.125,
3304
+ "learning_rate": 2.0424750400655947e-07,
3305
+ "loss": 4.1676,
3306
+ "step": 4710
3307
+ },
3308
+ {
3309
+ "epoch": 0.944,
3310
+ "grad_norm": 9.3125,
3311
+ "learning_rate": 1.9044844650808468e-07,
3312
+ "loss": 4.1597,
3313
+ "step": 4720
3314
+ },
3315
+ {
3316
+ "epoch": 0.946,
3317
+ "grad_norm": 9.8125,
3318
+ "learning_rate": 1.7712749271311392e-07,
3319
+ "loss": 4.1758,
3320
+ "step": 4730
3321
+ },
3322
+ {
3323
+ "epoch": 0.948,
3324
+ "grad_norm": 11.1875,
3325
+ "learning_rate": 1.6428529186614195e-07,
3326
+ "loss": 4.0688,
3327
+ "step": 4740
3328
+ },
3329
+ {
3330
+ "epoch": 0.95,
3331
+ "grad_norm": 10.5625,
3332
+ "learning_rate": 1.519224698779198e-07,
3333
+ "loss": 4.1514,
3334
+ "step": 4750
3335
+ },
3336
+ {
3337
+ "epoch": 0.952,
3338
+ "grad_norm": 13.5,
3339
+ "learning_rate": 1.400396292949513e-07,
3340
+ "loss": 4.1525,
3341
+ "step": 4760
3342
+ },
3343
+ {
3344
+ "epoch": 0.954,
3345
+ "grad_norm": 11.4375,
3346
+ "learning_rate": 1.2863734927012094e-07,
3347
+ "loss": 4.0028,
3348
+ "step": 4770
3349
+ },
3350
+ {
3351
+ "epoch": 0.956,
3352
+ "grad_norm": 10.4375,
3353
+ "learning_rate": 1.1771618553447217e-07,
3354
+ "loss": 4.1243,
3355
+ "step": 4780
3356
+ },
3357
+ {
3358
+ "epoch": 0.958,
3359
+ "grad_norm": 11.125,
3360
+ "learning_rate": 1.0727667037011668e-07,
3361
+ "loss": 4.1464,
3362
+ "step": 4790
3363
+ },
3364
+ {
3365
+ "epoch": 0.96,
3366
+ "grad_norm": 11.0625,
3367
+ "learning_rate": 9.731931258429638e-08,
3368
+ "loss": 4.1058,
3369
+ "step": 4800
3370
+ },
3371
+ {
3372
+ "epoch": 0.962,
3373
+ "grad_norm": 12.1875,
3374
+ "learning_rate": 8.784459748458318e-08,
3375
+ "loss": 4.2001,
3376
+ "step": 4810
3377
+ },
3378
+ {
3379
+ "epoch": 0.964,
3380
+ "grad_norm": 11.5,
3381
+ "learning_rate": 7.885298685522235e-08,
3382
+ "loss": 4.1632,
3383
+ "step": 4820
3384
+ },
3385
+ {
3386
+ "epoch": 0.966,
3387
+ "grad_norm": 16.75,
3388
+ "learning_rate": 7.034491893463059e-08,
3389
+ "loss": 4.2223,
3390
+ "step": 4830
3391
+ },
3392
+ {
3393
+ "epoch": 0.968,
3394
+ "grad_norm": 8.75,
3395
+ "learning_rate": 6.232080839403631e-08,
3396
+ "loss": 4.01,
3397
+ "step": 4840
3398
+ },
3399
+ {
3400
+ "epoch": 0.97,
3401
+ "grad_norm": 12.9375,
3402
+ "learning_rate": 5.4781046317267103e-08,
3403
+ "loss": 4.2039,
3404
+ "step": 4850
3405
+ },
3406
+ {
3407
+ "epoch": 0.972,
3408
+ "grad_norm": 10.8125,
3409
+ "learning_rate": 4.772600018168816e-08,
3410
+ "loss": 4.0684,
3411
+ "step": 4860
3412
+ },
3413
+ {
3414
+ "epoch": 0.974,
3415
+ "grad_norm": 11.4375,
3416
+ "learning_rate": 4.115601384029666e-08,
3417
+ "loss": 3.9565,
3418
+ "step": 4870
3419
+ },
3420
+ {
3421
+ "epoch": 0.976,
3422
+ "grad_norm": 9.75,
3423
+ "learning_rate": 3.50714075049563e-08,
3424
+ "loss": 4.1201,
3425
+ "step": 4880
3426
+ },
3427
+ {
3428
+ "epoch": 0.978,
3429
+ "grad_norm": 10.8125,
3430
+ "learning_rate": 2.947247773079753e-08,
3431
+ "loss": 4.2197,
3432
+ "step": 4890
3433
+ },
3434
+ {
3435
+ "epoch": 0.98,
3436
+ "grad_norm": 11.6875,
3437
+ "learning_rate": 2.4359497401758026e-08,
3438
+ "loss": 4.1977,
3439
+ "step": 4900
3440
+ },
3441
+ {
3442
+ "epoch": 0.982,
3443
+ "grad_norm": 10.5,
3444
+ "learning_rate": 1.973271571728441e-08,
3445
+ "loss": 4.088,
3446
+ "step": 4910
3447
+ },
3448
+ {
3449
+ "epoch": 0.984,
3450
+ "grad_norm": 17.375,
3451
+ "learning_rate": 1.5592358180189782e-08,
3452
+ "loss": 4.1927,
3453
+ "step": 4920
3454
+ },
3455
+ {
3456
+ "epoch": 0.986,
3457
+ "grad_norm": 9.5,
3458
+ "learning_rate": 1.1938626585660252e-08,
3459
+ "loss": 4.1761,
3460
+ "step": 4930
3461
+ },
3462
+ {
3463
+ "epoch": 0.988,
3464
+ "grad_norm": 10.875,
3465
+ "learning_rate": 8.771699011416169e-09,
3466
+ "loss": 4.1907,
3467
+ "step": 4940
3468
+ },
3469
+ {
3470
+ "epoch": 0.99,
3471
+ "grad_norm": 10.125,
3472
+ "learning_rate": 6.091729809042379e-09,
3473
+ "loss": 4.0264,
3474
+ "step": 4950
3475
+ },
3476
+ {
3477
+ "epoch": 0.992,
3478
+ "grad_norm": 11.875,
3479
+ "learning_rate": 3.898849596456477e-09,
3480
+ "loss": 4.0806,
3481
+ "step": 4960
3482
+ },
3483
+ {
3484
+ "epoch": 0.994,
3485
+ "grad_norm": 9.4375,
3486
+ "learning_rate": 2.193165251545004e-09,
3487
+ "loss": 4.0634,
3488
+ "step": 4970
3489
+ },
3490
+ {
3491
+ "epoch": 0.996,
3492
+ "grad_norm": 11.1875,
3493
+ "learning_rate": 9.74759906957612e-10,
3494
+ "loss": 4.0266,
3495
+ "step": 4980
3496
+ },
3497
+ {
3498
+ "epoch": 0.998,
3499
+ "grad_norm": 12.8125,
3500
+ "learning_rate": 2.436929460525317e-10,
3501
+ "loss": 4.0775,
3502
+ "step": 4990
3503
+ },
3504
+ {
3505
+ "epoch": 1.0,
3506
+ "grad_norm": 10.25,
3507
+ "learning_rate": 0.0,
3508
+ "loss": 4.0756,
3509
+ "step": 5000
3510
+ }
3511
+ ],
3512
+ "logging_steps": 10,
3513
+ "max_steps": 5000,
3514
+ "num_input_tokens_seen": 0,
3515
+ "num_train_epochs": 9223372036854775807,
3516
+ "save_steps": 1000,
3517
+ "stateful_callbacks": {
3518
+ "TrainerControl": {
3519
+ "args": {
3520
+ "should_epoch_stop": false,
3521
+ "should_evaluate": false,
3522
+ "should_log": false,
3523
+ "should_save": true,
3524
+ "should_training_stop": true
3525
+ },
3526
+ "attributes": {}
3527
+ }
3528
+ },
3529
+ "total_flos": 9.5664155394048e+17,
3530
+ "train_batch_size": 8,
3531
+ "trial_name": null,
3532
+ "trial_params": null
3533
+ }
checkpoint-5000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c51e94da6d2aa3c731e6c47ec4d57b7e602213ac8fcc65705808387f23a6f3a
3
+ size 5368