Igor-22 commited on
Commit
fb44e39
·
verified ·
1 Parent(s): 0725535

Upload 34 files

Browse files
Files changed (34) hide show
  1. ptt5-cronosflow_ai_public/checkpoint-18500/config.json +31 -0
  2. ptt5-cronosflow_ai_public/checkpoint-18500/generation_config.json +6 -0
  3. ptt5-cronosflow_ai_public/checkpoint-18500/model.safetensors +3 -0
  4. ptt5-cronosflow_ai_public/checkpoint-18500/optimizer.pt +3 -0
  5. ptt5-cronosflow_ai_public/checkpoint-18500/rng_state.pth +3 -0
  6. ptt5-cronosflow_ai_public/checkpoint-18500/scaler.pt +3 -0
  7. ptt5-cronosflow_ai_public/checkpoint-18500/scheduler.pt +3 -0
  8. ptt5-cronosflow_ai_public/checkpoint-18500/special_tokens_map.json +125 -0
  9. ptt5-cronosflow_ai_public/checkpoint-18500/spiece.model +3 -0
  10. ptt5-cronosflow_ai_public/checkpoint-18500/tokenizer.json +0 -0
  11. ptt5-cronosflow_ai_public/checkpoint-18500/tokenizer_config.json +941 -0
  12. ptt5-cronosflow_ai_public/checkpoint-18500/trainer_state.json +2648 -0
  13. ptt5-cronosflow_ai_public/checkpoint-18500/training_args.bin +3 -0
  14. ptt5-cronosflow_ai_public/checkpoint-18564/config.json +31 -0
  15. ptt5-cronosflow_ai_public/checkpoint-18564/generation_config.json +6 -0
  16. ptt5-cronosflow_ai_public/checkpoint-18564/model.safetensors +3 -0
  17. ptt5-cronosflow_ai_public/checkpoint-18564/optimizer.pt +3 -0
  18. ptt5-cronosflow_ai_public/checkpoint-18564/rng_state.pth +3 -0
  19. ptt5-cronosflow_ai_public/checkpoint-18564/scaler.pt +3 -0
  20. ptt5-cronosflow_ai_public/checkpoint-18564/scheduler.pt +3 -0
  21. ptt5-cronosflow_ai_public/checkpoint-18564/special_tokens_map.json +125 -0
  22. ptt5-cronosflow_ai_public/checkpoint-18564/spiece.model +3 -0
  23. ptt5-cronosflow_ai_public/checkpoint-18564/tokenizer.json +0 -0
  24. ptt5-cronosflow_ai_public/checkpoint-18564/tokenizer_config.json +941 -0
  25. ptt5-cronosflow_ai_public/checkpoint-18564/trainer_state.json +2655 -0
  26. ptt5-cronosflow_ai_public/checkpoint-18564/training_args.bin +3 -0
  27. ptt5-cronosflow_ai_public/config.json +31 -0
  28. ptt5-cronosflow_ai_public/generation_config.json +6 -0
  29. ptt5-cronosflow_ai_public/model.safetensors +3 -0
  30. ptt5-cronosflow_ai_public/special_tokens_map.json +125 -0
  31. ptt5-cronosflow_ai_public/spiece.model +3 -0
  32. ptt5-cronosflow_ai_public/tokenizer.json +0 -0
  33. ptt5-cronosflow_ai_public/tokenizer_config.json +941 -0
  34. ptt5-cronosflow_ai_public/training_args.bin +3 -0
ptt5-cronosflow_ai_public/checkpoint-18500/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.54.1",
29
+ "use_cache": true,
30
+ "vocab_size": 32128
31
+ }
ptt5-cronosflow_ai_public/checkpoint-18500/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.54.1"
6
+ }
ptt5-cronosflow_ai_public/checkpoint-18500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6919afb4fd124503d4c74b4d6fab16976bd30578c9243a7c0401bba9ad5c6827
3
+ size 891644712
ptt5-cronosflow_ai_public/checkpoint-18500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a4dd2803058b23c77399188824af50aae95745ea4b5b913dc07f8b9bc5919a1
3
+ size 1783445259
ptt5-cronosflow_ai_public/checkpoint-18500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ab508feb06254c4aedd37fdc66b624980f1a604e016f4254ed7b26968403c1
3
+ size 14645
ptt5-cronosflow_ai_public/checkpoint-18500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c4a2ae37fdd1668960b188a1c8ddfeb70e2f25d8f80d12aabf449831985e170
3
+ size 1383
ptt5-cronosflow_ai_public/checkpoint-18500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8698d235df2ddaf64f8c9e3124c9374e906a5fd60cfa722aff27fa6104e2c0
3
+ size 1465
ptt5-cronosflow_ai_public/checkpoint-18500/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
ptt5-cronosflow_ai_public/checkpoint-18500/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb25b1d67f04fce0e710d58430b606b4ee9887144fa2da22d123c44061cc62e
3
+ size 755569
ptt5-cronosflow_ai_public/checkpoint-18500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ptt5-cronosflow_ai_public/checkpoint-18500/tokenizer_config.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": false,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "legacy": true,
936
+ "model_max_length": 1000000000000000019884624838656,
937
+ "pad_token": "<pad>",
938
+ "sp_model_kwargs": {},
939
+ "tokenizer_class": "T5Tokenizer",
940
+ "unk_token": "<unk>"
941
+ }
ptt5-cronosflow_ai_public/checkpoint-18500/trainer_state.json ADDED
@@ -0,0 +1,2648 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.9896574014221073,
6
+ "eval_steps": 500,
7
+ "global_step": 18500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00808015513897867,
14
+ "grad_norm": 40.89574432373047,
15
+ "learning_rate": 1.995151906916613e-05,
16
+ "loss": 25.8011,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.01616031027795734,
21
+ "grad_norm": 1.4409021139144897,
22
+ "learning_rate": 1.9897651368239605e-05,
23
+ "loss": 2.011,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.024240465416936006,
28
+ "grad_norm": 0.27292221784591675,
29
+ "learning_rate": 1.9843783667313083e-05,
30
+ "loss": 0.1682,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.03232062055591468,
35
+ "grad_norm": 0.21620342135429382,
36
+ "learning_rate": 1.9789915966386557e-05,
37
+ "loss": 0.1127,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.040400775694893344,
42
+ "grad_norm": 0.19684338569641113,
43
+ "learning_rate": 1.9736048265460034e-05,
44
+ "loss": 0.0924,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.04848093083387201,
49
+ "grad_norm": 0.21188506484031677,
50
+ "learning_rate": 1.9682180564533505e-05,
51
+ "loss": 0.0768,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.05656108597285068,
56
+ "grad_norm": 0.16330359876155853,
57
+ "learning_rate": 1.9628312863606982e-05,
58
+ "loss": 0.0596,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.06464124111182935,
63
+ "grad_norm": 0.12760096788406372,
64
+ "learning_rate": 1.9574445162680457e-05,
65
+ "loss": 0.0491,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.07272139625080802,
70
+ "grad_norm": 0.16558507084846497,
71
+ "learning_rate": 1.9520577461753934e-05,
72
+ "loss": 0.0424,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.08080155138978669,
77
+ "grad_norm": 0.1511087417602539,
78
+ "learning_rate": 1.9466709760827408e-05,
79
+ "loss": 0.0376,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.08888170652876536,
84
+ "grad_norm": 0.09860303997993469,
85
+ "learning_rate": 1.9412842059900886e-05,
86
+ "loss": 0.0333,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.09696186166774402,
91
+ "grad_norm": 0.1415504515171051,
92
+ "learning_rate": 1.935897435897436e-05,
93
+ "loss": 0.0299,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.10504201680672269,
98
+ "grad_norm": 0.12042852491140366,
99
+ "learning_rate": 1.9305106658047837e-05,
100
+ "loss": 0.0298,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.11312217194570136,
105
+ "grad_norm": 0.14820343255996704,
106
+ "learning_rate": 1.925123895712131e-05,
107
+ "loss": 0.0297,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.12120232708468003,
112
+ "grad_norm": 0.11845523118972778,
113
+ "learning_rate": 1.919737125619479e-05,
114
+ "loss": 0.024,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.1292824822236587,
119
+ "grad_norm": 0.13682147860527039,
120
+ "learning_rate": 1.9143503555268263e-05,
121
+ "loss": 0.024,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.13736263736263737,
126
+ "grad_norm": 0.07670263946056366,
127
+ "learning_rate": 1.908963585434174e-05,
128
+ "loss": 0.0216,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.14544279250161604,
133
+ "grad_norm": 0.10427036881446838,
134
+ "learning_rate": 1.903576815341521e-05,
135
+ "loss": 0.0229,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.1535229476405947,
140
+ "grad_norm": 0.14853981137275696,
141
+ "learning_rate": 1.898190045248869e-05,
142
+ "loss": 0.0204,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.16160310277957338,
147
+ "grad_norm": 0.08788396418094635,
148
+ "learning_rate": 1.8928032751562163e-05,
149
+ "loss": 0.0201,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.16968325791855204,
154
+ "grad_norm": 0.1365722268819809,
155
+ "learning_rate": 1.887416505063564e-05,
156
+ "loss": 0.019,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.1777634130575307,
161
+ "grad_norm": 0.133611798286438,
162
+ "learning_rate": 1.8820297349709114e-05,
163
+ "loss": 0.0212,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.18584356819650938,
168
+ "grad_norm": 0.09723819047212601,
169
+ "learning_rate": 1.8766429648782592e-05,
170
+ "loss": 0.0169,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.19392372333548805,
175
+ "grad_norm": 0.11186394095420837,
176
+ "learning_rate": 1.8712561947856066e-05,
177
+ "loss": 0.0178,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.2020038784744667,
182
+ "grad_norm": 0.10648094117641449,
183
+ "learning_rate": 1.8658694246929544e-05,
184
+ "loss": 0.0172,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.21008403361344538,
189
+ "grad_norm": 0.10959897935390472,
190
+ "learning_rate": 1.8604826546003018e-05,
191
+ "loss": 0.0178,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.21816418875242405,
196
+ "grad_norm": 0.09298472851514816,
197
+ "learning_rate": 1.8550958845076495e-05,
198
+ "loss": 0.0154,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.22624434389140272,
203
+ "grad_norm": 0.08410840481519699,
204
+ "learning_rate": 1.849709114414997e-05,
205
+ "loss": 0.0162,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.23432449903038138,
210
+ "grad_norm": 0.15365834534168243,
211
+ "learning_rate": 1.8443223443223447e-05,
212
+ "loss": 0.0148,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.24240465416936005,
217
+ "grad_norm": 0.09604126960039139,
218
+ "learning_rate": 1.838935574229692e-05,
219
+ "loss": 0.0146,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.2504848093083387,
224
+ "grad_norm": 0.06805470585823059,
225
+ "learning_rate": 1.8335488041370395e-05,
226
+ "loss": 0.0162,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.2585649644473174,
231
+ "grad_norm": 0.11596197634935379,
232
+ "learning_rate": 1.8281620340443872e-05,
233
+ "loss": 0.0112,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.26664511958629605,
238
+ "grad_norm": 0.08166597783565521,
239
+ "learning_rate": 1.8227752639517347e-05,
240
+ "loss": 0.0136,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.27472527472527475,
245
+ "grad_norm": 0.08969355374574661,
246
+ "learning_rate": 1.817388493859082e-05,
247
+ "loss": 0.0132,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.2828054298642534,
252
+ "grad_norm": 0.0873119905591011,
253
+ "learning_rate": 1.8120017237664298e-05,
254
+ "loss": 0.0129,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.2908855850032321,
259
+ "grad_norm": 0.10579364001750946,
260
+ "learning_rate": 1.8066149536737772e-05,
261
+ "loss": 0.0123,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.2989657401422107,
266
+ "grad_norm": 0.12571881711483002,
267
+ "learning_rate": 1.801228183581125e-05,
268
+ "loss": 0.0128,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.3070458952811894,
273
+ "grad_norm": 0.08085139840841293,
274
+ "learning_rate": 1.7958414134884724e-05,
275
+ "loss": 0.0121,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.31512605042016806,
280
+ "grad_norm": 0.06765197962522507,
281
+ "learning_rate": 1.79045464339582e-05,
282
+ "loss": 0.0103,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.32320620555914675,
287
+ "grad_norm": 0.07517407834529877,
288
+ "learning_rate": 1.7850678733031676e-05,
289
+ "loss": 0.0107,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.3312863606981254,
294
+ "grad_norm": 0.060215964913368225,
295
+ "learning_rate": 1.779681103210515e-05,
296
+ "loss": 0.0123,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.3393665158371041,
301
+ "grad_norm": 0.08518676459789276,
302
+ "learning_rate": 1.7742943331178627e-05,
303
+ "loss": 0.0107,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.3474466709760827,
308
+ "grad_norm": 0.05002804845571518,
309
+ "learning_rate": 1.76890756302521e-05,
310
+ "loss": 0.0108,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.3555268261150614,
315
+ "grad_norm": 0.042444173246622086,
316
+ "learning_rate": 1.763520792932558e-05,
317
+ "loss": 0.01,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.36360698125404006,
322
+ "grad_norm": 0.07093804329633713,
323
+ "learning_rate": 1.7581340228399053e-05,
324
+ "loss": 0.0113,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.37168713639301876,
329
+ "grad_norm": 0.059032320976257324,
330
+ "learning_rate": 1.752747252747253e-05,
331
+ "loss": 0.011,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.3797672915319974,
336
+ "grad_norm": 0.05217365920543671,
337
+ "learning_rate": 1.7473604826546004e-05,
338
+ "loss": 0.0097,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.3878474466709761,
343
+ "grad_norm": 0.12220600247383118,
344
+ "learning_rate": 1.7419737125619482e-05,
345
+ "loss": 0.01,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.39592760180995473,
350
+ "grad_norm": 0.09106040000915527,
351
+ "learning_rate": 1.7365869424692956e-05,
352
+ "loss": 0.0117,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.4040077569489334,
357
+ "grad_norm": 0.09308184683322906,
358
+ "learning_rate": 1.731200172376643e-05,
359
+ "loss": 0.01,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.41208791208791207,
364
+ "grad_norm": 0.08041771501302719,
365
+ "learning_rate": 1.7258134022839908e-05,
366
+ "loss": 0.0112,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.42016806722689076,
371
+ "grad_norm": 0.05206672102212906,
372
+ "learning_rate": 1.7204266321913382e-05,
373
+ "loss": 0.0103,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.4282482223658694,
378
+ "grad_norm": 0.0851343497633934,
379
+ "learning_rate": 1.7150398620986856e-05,
380
+ "loss": 0.0093,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.4363283775048481,
385
+ "grad_norm": 0.08132291585206985,
386
+ "learning_rate": 1.7096530920060333e-05,
387
+ "loss": 0.0118,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.44440853264382674,
392
+ "grad_norm": 0.06463415920734406,
393
+ "learning_rate": 1.7042663219133807e-05,
394
+ "loss": 0.0106,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.45248868778280543,
399
+ "grad_norm": 0.08292311429977417,
400
+ "learning_rate": 1.6988795518207285e-05,
401
+ "loss": 0.0097,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.46056884292178407,
406
+ "grad_norm": 0.10132889449596405,
407
+ "learning_rate": 1.693492781728076e-05,
408
+ "loss": 0.009,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.46864899806076277,
413
+ "grad_norm": 0.06622787564992905,
414
+ "learning_rate": 1.6881060116354237e-05,
415
+ "loss": 0.0092,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.47672915319974146,
420
+ "grad_norm": 0.055822569876909256,
421
+ "learning_rate": 1.682719241542771e-05,
422
+ "loss": 0.0088,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.4848093083387201,
427
+ "grad_norm": 0.04172702878713608,
428
+ "learning_rate": 1.6773324714501188e-05,
429
+ "loss": 0.0081,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.4928894634776988,
434
+ "grad_norm": 0.08130078762769699,
435
+ "learning_rate": 1.6719457013574662e-05,
436
+ "loss": 0.0085,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.5009696186166774,
441
+ "grad_norm": 0.048671796917915344,
442
+ "learning_rate": 1.666558931264814e-05,
443
+ "loss": 0.0079,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.5090497737556561,
448
+ "grad_norm": 0.12270870059728622,
449
+ "learning_rate": 1.6611721611721614e-05,
450
+ "loss": 0.0084,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.5171299288946348,
455
+ "grad_norm": 0.053976595401763916,
456
+ "learning_rate": 1.6557853910795088e-05,
457
+ "loss": 0.0095,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.5252100840336135,
462
+ "grad_norm": 0.09643538296222687,
463
+ "learning_rate": 1.6503986209868562e-05,
464
+ "loss": 0.0086,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.5332902391725921,
469
+ "grad_norm": 0.04082519933581352,
470
+ "learning_rate": 1.645011850894204e-05,
471
+ "loss": 0.0085,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.5413703943115707,
476
+ "grad_norm": 0.07320540398359299,
477
+ "learning_rate": 1.6396250808015514e-05,
478
+ "loss": 0.0095,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.5494505494505495,
483
+ "grad_norm": 0.08433382958173752,
484
+ "learning_rate": 1.634238310708899e-05,
485
+ "loss": 0.0086,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.5575307045895281,
490
+ "grad_norm": 0.08490192890167236,
491
+ "learning_rate": 1.6288515406162465e-05,
492
+ "loss": 0.0087,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.5656108597285068,
497
+ "grad_norm": 0.07407897710800171,
498
+ "learning_rate": 1.6234647705235943e-05,
499
+ "loss": 0.0095,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.5736910148674854,
504
+ "grad_norm": 0.04006027430295944,
505
+ "learning_rate": 1.6180780004309417e-05,
506
+ "loss": 0.0085,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.5817711700064642,
511
+ "grad_norm": 0.10100733488798141,
512
+ "learning_rate": 1.6126912303382894e-05,
513
+ "loss": 0.0082,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.5898513251454428,
518
+ "grad_norm": 0.046667344868183136,
519
+ "learning_rate": 1.607304460245637e-05,
520
+ "loss": 0.0088,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.5979314802844214,
525
+ "grad_norm": 0.07386622577905655,
526
+ "learning_rate": 1.6019176901529846e-05,
527
+ "loss": 0.0097,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.6060116354234001,
532
+ "grad_norm": 0.07727360725402832,
533
+ "learning_rate": 1.596530920060332e-05,
534
+ "loss": 0.0078,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.6140917905623788,
539
+ "grad_norm": 0.01824168674647808,
540
+ "learning_rate": 1.5911441499676794e-05,
541
+ "loss": 0.0082,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.6221719457013575,
546
+ "grad_norm": 0.02981133572757244,
547
+ "learning_rate": 1.585757379875027e-05,
548
+ "loss": 0.0077,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.6302521008403361,
553
+ "grad_norm": 0.07947336137294769,
554
+ "learning_rate": 1.5803706097823746e-05,
555
+ "loss": 0.0073,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.6383322559793148,
560
+ "grad_norm": 0.04702315106987953,
561
+ "learning_rate": 1.574983839689722e-05,
562
+ "loss": 0.0074,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.6464124111182935,
567
+ "grad_norm": 0.0397706963121891,
568
+ "learning_rate": 1.5695970695970697e-05,
569
+ "loss": 0.0085,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 0.6544925662572721,
574
+ "grad_norm": 0.0445311963558197,
575
+ "learning_rate": 1.564210299504417e-05,
576
+ "loss": 0.0071,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 0.6625727213962508,
581
+ "grad_norm": 0.03868868947029114,
582
+ "learning_rate": 1.558823529411765e-05,
583
+ "loss": 0.0071,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 0.6706528765352294,
588
+ "grad_norm": 0.09177325665950775,
589
+ "learning_rate": 1.5534367593191123e-05,
590
+ "loss": 0.0078,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 0.6787330316742082,
595
+ "grad_norm": 0.05718887969851494,
596
+ "learning_rate": 1.54804998922646e-05,
597
+ "loss": 0.008,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 0.6868131868131868,
602
+ "grad_norm": 0.04949459806084633,
603
+ "learning_rate": 1.5426632191338075e-05,
604
+ "loss": 0.0073,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 0.6948933419521655,
609
+ "grad_norm": 0.04109389707446098,
610
+ "learning_rate": 1.5372764490411552e-05,
611
+ "loss": 0.0073,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 0.7029734970911441,
616
+ "grad_norm": 0.07063832134008408,
617
+ "learning_rate": 1.5318896789485026e-05,
618
+ "loss": 0.0083,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 0.7110536522301228,
623
+ "grad_norm": 0.07452435046434402,
624
+ "learning_rate": 1.52650290885585e-05,
625
+ "loss": 0.0073,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 0.7191338073691015,
630
+ "grad_norm": 0.04412061721086502,
631
+ "learning_rate": 1.5211161387631976e-05,
632
+ "loss": 0.0067,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 0.7272139625080801,
637
+ "grad_norm": 0.07454030215740204,
638
+ "learning_rate": 1.5157293686705452e-05,
639
+ "loss": 0.0075,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 0.7352941176470589,
644
+ "grad_norm": 0.04662289470434189,
645
+ "learning_rate": 1.5103425985778928e-05,
646
+ "loss": 0.0074,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 0.7433742727860375,
651
+ "grad_norm": 0.05991057679057121,
652
+ "learning_rate": 1.5049558284852404e-05,
653
+ "loss": 0.0071,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 0.7514544279250162,
658
+ "grad_norm": 0.04592648521065712,
659
+ "learning_rate": 1.499569058392588e-05,
660
+ "loss": 0.0076,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 0.7595345830639948,
665
+ "grad_norm": 0.06309536099433899,
666
+ "learning_rate": 1.4941822882999355e-05,
667
+ "loss": 0.0076,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 0.7676147382029735,
672
+ "grad_norm": 0.05248362198472023,
673
+ "learning_rate": 1.4887955182072831e-05,
674
+ "loss": 0.0075,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 0.7756948933419522,
679
+ "grad_norm": 0.04493599757552147,
680
+ "learning_rate": 1.4834087481146307e-05,
681
+ "loss": 0.007,
682
+ "step": 4800
683
+ },
684
+ {
685
+ "epoch": 0.7837750484809308,
686
+ "grad_norm": 0.020138224586844444,
687
+ "learning_rate": 1.4780219780219783e-05,
688
+ "loss": 0.0063,
689
+ "step": 4850
690
+ },
691
+ {
692
+ "epoch": 0.7918552036199095,
693
+ "grad_norm": 0.073582723736763,
694
+ "learning_rate": 1.4726352079293259e-05,
695
+ "loss": 0.0063,
696
+ "step": 4900
697
+ },
698
+ {
699
+ "epoch": 0.7999353587588882,
700
+ "grad_norm": 0.050810813903808594,
701
+ "learning_rate": 1.4672484378366731e-05,
702
+ "loss": 0.0079,
703
+ "step": 4950
704
+ },
705
+ {
706
+ "epoch": 0.8080155138978669,
707
+ "grad_norm": 0.09147041290998459,
708
+ "learning_rate": 1.4618616677440207e-05,
709
+ "loss": 0.007,
710
+ "step": 5000
711
+ },
712
+ {
713
+ "epoch": 0.8160956690368455,
714
+ "grad_norm": 0.02943544089794159,
715
+ "learning_rate": 1.4564748976513683e-05,
716
+ "loss": 0.0064,
717
+ "step": 5050
718
+ },
719
+ {
720
+ "epoch": 0.8241758241758241,
721
+ "grad_norm": 0.058280181139707565,
722
+ "learning_rate": 1.4510881275587158e-05,
723
+ "loss": 0.0063,
724
+ "step": 5100
725
+ },
726
+ {
727
+ "epoch": 0.8322559793148029,
728
+ "grad_norm": 0.05846063792705536,
729
+ "learning_rate": 1.4457013574660634e-05,
730
+ "loss": 0.0071,
731
+ "step": 5150
732
+ },
733
+ {
734
+ "epoch": 0.8403361344537815,
735
+ "grad_norm": 0.08794039487838745,
736
+ "learning_rate": 1.440314587373411e-05,
737
+ "loss": 0.0066,
738
+ "step": 5200
739
+ },
740
+ {
741
+ "epoch": 0.8484162895927602,
742
+ "grad_norm": 0.05881703272461891,
743
+ "learning_rate": 1.4349278172807586e-05,
744
+ "loss": 0.0075,
745
+ "step": 5250
746
+ },
747
+ {
748
+ "epoch": 0.8564964447317388,
749
+ "grad_norm": 0.060504719614982605,
750
+ "learning_rate": 1.4295410471881062e-05,
751
+ "loss": 0.0061,
752
+ "step": 5300
753
+ },
754
+ {
755
+ "epoch": 0.8645765998707176,
756
+ "grad_norm": 0.04584150016307831,
757
+ "learning_rate": 1.4241542770954537e-05,
758
+ "loss": 0.0059,
759
+ "step": 5350
760
+ },
761
+ {
762
+ "epoch": 0.8726567550096962,
763
+ "grad_norm": 0.0818849429488182,
764
+ "learning_rate": 1.4187675070028013e-05,
765
+ "loss": 0.0067,
766
+ "step": 5400
767
+ },
768
+ {
769
+ "epoch": 0.8807369101486748,
770
+ "grad_norm": 0.04742725193500519,
771
+ "learning_rate": 1.4133807369101489e-05,
772
+ "loss": 0.0066,
773
+ "step": 5450
774
+ },
775
+ {
776
+ "epoch": 0.8888170652876535,
777
+ "grad_norm": 0.06628070026636124,
778
+ "learning_rate": 1.4079939668174965e-05,
779
+ "loss": 0.0069,
780
+ "step": 5500
781
+ },
782
+ {
783
+ "epoch": 0.8968972204266322,
784
+ "grad_norm": 0.0498398132622242,
785
+ "learning_rate": 1.4026071967248437e-05,
786
+ "loss": 0.006,
787
+ "step": 5550
788
+ },
789
+ {
790
+ "epoch": 0.9049773755656109,
791
+ "grad_norm": 0.07333686202764511,
792
+ "learning_rate": 1.3972204266321913e-05,
793
+ "loss": 0.0073,
794
+ "step": 5600
795
+ },
796
+ {
797
+ "epoch": 0.9130575307045895,
798
+ "grad_norm": 0.040425509214401245,
799
+ "learning_rate": 1.3918336565395389e-05,
800
+ "loss": 0.0061,
801
+ "step": 5650
802
+ },
803
+ {
804
+ "epoch": 0.9211376858435681,
805
+ "grad_norm": 0.04927436634898186,
806
+ "learning_rate": 1.3864468864468865e-05,
807
+ "loss": 0.0064,
808
+ "step": 5700
809
+ },
810
+ {
811
+ "epoch": 0.9292178409825469,
812
+ "grad_norm": 0.07403150945901871,
813
+ "learning_rate": 1.381060116354234e-05,
814
+ "loss": 0.0057,
815
+ "step": 5750
816
+ },
817
+ {
818
+ "epoch": 0.9372979961215255,
819
+ "grad_norm": 0.0294960867613554,
820
+ "learning_rate": 1.3756733462615816e-05,
821
+ "loss": 0.0057,
822
+ "step": 5800
823
+ },
824
+ {
825
+ "epoch": 0.9453781512605042,
826
+ "grad_norm": 0.06763947010040283,
827
+ "learning_rate": 1.3702865761689292e-05,
828
+ "loss": 0.0061,
829
+ "step": 5850
830
+ },
831
+ {
832
+ "epoch": 0.9534583063994829,
833
+ "grad_norm": 0.034876059740781784,
834
+ "learning_rate": 1.3648998060762768e-05,
835
+ "loss": 0.0073,
836
+ "step": 5900
837
+ },
838
+ {
839
+ "epoch": 0.9615384615384616,
840
+ "grad_norm": 0.0363958366215229,
841
+ "learning_rate": 1.3595130359836244e-05,
842
+ "loss": 0.0065,
843
+ "step": 5950
844
+ },
845
+ {
846
+ "epoch": 0.9696186166774402,
847
+ "grad_norm": 0.03505223989486694,
848
+ "learning_rate": 1.354126265890972e-05,
849
+ "loss": 0.0065,
850
+ "step": 6000
851
+ },
852
+ {
853
+ "epoch": 0.9776987718164188,
854
+ "grad_norm": 0.010415361262857914,
855
+ "learning_rate": 1.3487394957983195e-05,
856
+ "loss": 0.0063,
857
+ "step": 6050
858
+ },
859
+ {
860
+ "epoch": 0.9857789269553976,
861
+ "grad_norm": 0.05905304104089737,
862
+ "learning_rate": 1.343352725705667e-05,
863
+ "loss": 0.0055,
864
+ "step": 6100
865
+ },
866
+ {
867
+ "epoch": 0.9938590820943762,
868
+ "grad_norm": 0.03133542463183403,
869
+ "learning_rate": 1.3379659556130145e-05,
870
+ "loss": 0.0062,
871
+ "step": 6150
872
+ },
873
+ {
874
+ "epoch": 1.0,
875
+ "eval_loss": 0.00468644080683589,
876
+ "eval_rouge1": 86.16729085635436,
877
+ "eval_rouge2": 82.00613853575325,
878
+ "eval_rougeL": 85.17049406119979,
879
+ "eval_rougeLsum": 85.1321983661705,
880
+ "eval_runtime": 50.3158,
881
+ "eval_samples_per_second": 9.937,
882
+ "eval_steps_per_second": 1.252,
883
+ "step": 6188
884
+ },
885
+ {
886
+ "epoch": 1.0019392372333549,
887
+ "grad_norm": 0.0473632887005806,
888
+ "learning_rate": 1.3325791855203621e-05,
889
+ "loss": 0.006,
890
+ "step": 6200
891
+ },
892
+ {
893
+ "epoch": 1.0100193923723335,
894
+ "grad_norm": 0.009613406844437122,
895
+ "learning_rate": 1.3271924154277097e-05,
896
+ "loss": 0.0058,
897
+ "step": 6250
898
+ },
899
+ {
900
+ "epoch": 1.0180995475113122,
901
+ "grad_norm": 0.07586677372455597,
902
+ "learning_rate": 1.3218056453350573e-05,
903
+ "loss": 0.0053,
904
+ "step": 6300
905
+ },
906
+ {
907
+ "epoch": 1.0261797026502908,
908
+ "grad_norm": 0.03996267169713974,
909
+ "learning_rate": 1.3165266106442578e-05,
910
+ "loss": 0.0053,
911
+ "step": 6350
912
+ },
913
+ {
914
+ "epoch": 1.0342598577892697,
915
+ "grad_norm": 0.04150750860571861,
916
+ "learning_rate": 1.3111398405516054e-05,
917
+ "loss": 0.006,
918
+ "step": 6400
919
+ },
920
+ {
921
+ "epoch": 1.0423400129282483,
922
+ "grad_norm": 0.047103989869356155,
923
+ "learning_rate": 1.305753070458953e-05,
924
+ "loss": 0.0063,
925
+ "step": 6450
926
+ },
927
+ {
928
+ "epoch": 1.050420168067227,
929
+ "grad_norm": 0.04707568511366844,
930
+ "learning_rate": 1.3003663003663005e-05,
931
+ "loss": 0.0054,
932
+ "step": 6500
933
+ },
934
+ {
935
+ "epoch": 1.0585003232062056,
936
+ "grad_norm": 0.04693872109055519,
937
+ "learning_rate": 1.2949795302736481e-05,
938
+ "loss": 0.0058,
939
+ "step": 6550
940
+ },
941
+ {
942
+ "epoch": 1.0665804783451842,
943
+ "grad_norm": 0.03767074644565582,
944
+ "learning_rate": 1.2895927601809957e-05,
945
+ "loss": 0.0049,
946
+ "step": 6600
947
+ },
948
+ {
949
+ "epoch": 1.0746606334841629,
950
+ "grad_norm": 0.049506109207868576,
951
+ "learning_rate": 1.2842059900883433e-05,
952
+ "loss": 0.0061,
953
+ "step": 6650
954
+ },
955
+ {
956
+ "epoch": 1.0827407886231415,
957
+ "grad_norm": 0.040579311549663544,
958
+ "learning_rate": 1.2788192199956907e-05,
959
+ "loss": 0.0053,
960
+ "step": 6700
961
+ },
962
+ {
963
+ "epoch": 1.0908209437621201,
964
+ "grad_norm": 0.06605598330497742,
965
+ "learning_rate": 1.273432449903038e-05,
966
+ "loss": 0.0049,
967
+ "step": 6750
968
+ },
969
+ {
970
+ "epoch": 1.098901098901099,
971
+ "grad_norm": 0.0573626309633255,
972
+ "learning_rate": 1.2680456798103857e-05,
973
+ "loss": 0.0058,
974
+ "step": 6800
975
+ },
976
+ {
977
+ "epoch": 1.1069812540400776,
978
+ "grad_norm": 0.04869833588600159,
979
+ "learning_rate": 1.2626589097177332e-05,
980
+ "loss": 0.0054,
981
+ "step": 6850
982
+ },
983
+ {
984
+ "epoch": 1.1150614091790563,
985
+ "grad_norm": 0.030207501724362373,
986
+ "learning_rate": 1.2572721396250808e-05,
987
+ "loss": 0.0049,
988
+ "step": 6900
989
+ },
990
+ {
991
+ "epoch": 1.123141564318035,
992
+ "grad_norm": 0.04019474983215332,
993
+ "learning_rate": 1.2518853695324284e-05,
994
+ "loss": 0.0054,
995
+ "step": 6950
996
+ },
997
+ {
998
+ "epoch": 1.1312217194570136,
999
+ "grad_norm": 0.03316131606698036,
1000
+ "learning_rate": 1.246498599439776e-05,
1001
+ "loss": 0.0063,
1002
+ "step": 7000
1003
+ },
1004
+ {
1005
+ "epoch": 1.1393018745959922,
1006
+ "grad_norm": 0.04495147988200188,
1007
+ "learning_rate": 1.2411118293471236e-05,
1008
+ "loss": 0.006,
1009
+ "step": 7050
1010
+ },
1011
+ {
1012
+ "epoch": 1.1473820297349708,
1013
+ "grad_norm": 0.029968004673719406,
1014
+ "learning_rate": 1.2357250592544711e-05,
1015
+ "loss": 0.0055,
1016
+ "step": 7100
1017
+ },
1018
+ {
1019
+ "epoch": 1.1554621848739495,
1020
+ "grad_norm": 0.05552554875612259,
1021
+ "learning_rate": 1.2303382891618187e-05,
1022
+ "loss": 0.0056,
1023
+ "step": 7150
1024
+ },
1025
+ {
1026
+ "epoch": 1.1635423400129283,
1027
+ "grad_norm": 0.040211454033851624,
1028
+ "learning_rate": 1.2249515190691663e-05,
1029
+ "loss": 0.0059,
1030
+ "step": 7200
1031
+ },
1032
+ {
1033
+ "epoch": 1.171622495151907,
1034
+ "grad_norm": 0.030323076993227005,
1035
+ "learning_rate": 1.2195647489765139e-05,
1036
+ "loss": 0.0057,
1037
+ "step": 7250
1038
+ },
1039
+ {
1040
+ "epoch": 1.1797026502908856,
1041
+ "grad_norm": 0.040990181267261505,
1042
+ "learning_rate": 1.2141779788838613e-05,
1043
+ "loss": 0.0053,
1044
+ "step": 7300
1045
+ },
1046
+ {
1047
+ "epoch": 1.1877828054298643,
1048
+ "grad_norm": 0.03895975649356842,
1049
+ "learning_rate": 1.2087912087912089e-05,
1050
+ "loss": 0.0054,
1051
+ "step": 7350
1052
+ },
1053
+ {
1054
+ "epoch": 1.195862960568843,
1055
+ "grad_norm": 0.04454527050256729,
1056
+ "learning_rate": 1.2034044386985565e-05,
1057
+ "loss": 0.0053,
1058
+ "step": 7400
1059
+ },
1060
+ {
1061
+ "epoch": 1.2039431157078215,
1062
+ "grad_norm": 0.04071690887212753,
1063
+ "learning_rate": 1.198017668605904e-05,
1064
+ "loss": 0.0053,
1065
+ "step": 7450
1066
+ },
1067
+ {
1068
+ "epoch": 1.2120232708468002,
1069
+ "grad_norm": 0.03768669813871384,
1070
+ "learning_rate": 1.1926308985132516e-05,
1071
+ "loss": 0.0059,
1072
+ "step": 7500
1073
+ },
1074
+ {
1075
+ "epoch": 1.220103425985779,
1076
+ "grad_norm": 0.048281479626894,
1077
+ "learning_rate": 1.187244128420599e-05,
1078
+ "loss": 0.0057,
1079
+ "step": 7550
1080
+ },
1081
+ {
1082
+ "epoch": 1.2281835811247577,
1083
+ "grad_norm": 0.037021659314632416,
1084
+ "learning_rate": 1.1818573583279466e-05,
1085
+ "loss": 0.0059,
1086
+ "step": 7600
1087
+ },
1088
+ {
1089
+ "epoch": 1.2362637362637363,
1090
+ "grad_norm": 0.060549281537532806,
1091
+ "learning_rate": 1.1764705882352942e-05,
1092
+ "loss": 0.0054,
1093
+ "step": 7650
1094
+ },
1095
+ {
1096
+ "epoch": 1.244343891402715,
1097
+ "grad_norm": 0.06345050781965256,
1098
+ "learning_rate": 1.1710838181426418e-05,
1099
+ "loss": 0.0057,
1100
+ "step": 7700
1101
+ },
1102
+ {
1103
+ "epoch": 1.2524240465416936,
1104
+ "grad_norm": 0.03186087682843208,
1105
+ "learning_rate": 1.1656970480499893e-05,
1106
+ "loss": 0.0055,
1107
+ "step": 7750
1108
+ },
1109
+ {
1110
+ "epoch": 1.2605042016806722,
1111
+ "grad_norm": 0.057463087141513824,
1112
+ "learning_rate": 1.160310277957337e-05,
1113
+ "loss": 0.0057,
1114
+ "step": 7800
1115
+ },
1116
+ {
1117
+ "epoch": 1.2685843568196509,
1118
+ "grad_norm": 0.04167677462100983,
1119
+ "learning_rate": 1.1549235078646843e-05,
1120
+ "loss": 0.0056,
1121
+ "step": 7850
1122
+ },
1123
+ {
1124
+ "epoch": 1.2766645119586295,
1125
+ "grad_norm": 0.04780175909399986,
1126
+ "learning_rate": 1.149536737772032e-05,
1127
+ "loss": 0.0056,
1128
+ "step": 7900
1129
+ },
1130
+ {
1131
+ "epoch": 1.2847446670976082,
1132
+ "grad_norm": 0.06335488706827164,
1133
+ "learning_rate": 1.1441499676793795e-05,
1134
+ "loss": 0.0055,
1135
+ "step": 7950
1136
+ },
1137
+ {
1138
+ "epoch": 1.292824822236587,
1139
+ "grad_norm": 0.04902550205588341,
1140
+ "learning_rate": 1.138763197586727e-05,
1141
+ "loss": 0.0062,
1142
+ "step": 8000
1143
+ },
1144
+ {
1145
+ "epoch": 1.3009049773755657,
1146
+ "grad_norm": 0.0339086689054966,
1147
+ "learning_rate": 1.1333764274940747e-05,
1148
+ "loss": 0.0049,
1149
+ "step": 8050
1150
+ },
1151
+ {
1152
+ "epoch": 1.3089851325145443,
1153
+ "grad_norm": 0.044165465980768204,
1154
+ "learning_rate": 1.1279896574014222e-05,
1155
+ "loss": 0.0058,
1156
+ "step": 8100
1157
+ },
1158
+ {
1159
+ "epoch": 1.317065287653523,
1160
+ "grad_norm": 0.037159230560064316,
1161
+ "learning_rate": 1.1226028873087698e-05,
1162
+ "loss": 0.0053,
1163
+ "step": 8150
1164
+ },
1165
+ {
1166
+ "epoch": 1.3251454427925016,
1167
+ "grad_norm": 0.03820132464170456,
1168
+ "learning_rate": 1.1172161172161174e-05,
1169
+ "loss": 0.0053,
1170
+ "step": 8200
1171
+ },
1172
+ {
1173
+ "epoch": 1.3332255979314802,
1174
+ "grad_norm": 0.024112703278660774,
1175
+ "learning_rate": 1.111829347123465e-05,
1176
+ "loss": 0.0054,
1177
+ "step": 8250
1178
+ },
1179
+ {
1180
+ "epoch": 1.341305753070459,
1181
+ "grad_norm": 0.029049362987279892,
1182
+ "learning_rate": 1.1064425770308126e-05,
1183
+ "loss": 0.005,
1184
+ "step": 8300
1185
+ },
1186
+ {
1187
+ "epoch": 1.3493859082094377,
1188
+ "grad_norm": 0.0295393168926239,
1189
+ "learning_rate": 1.1010558069381601e-05,
1190
+ "loss": 0.0053,
1191
+ "step": 8350
1192
+ },
1193
+ {
1194
+ "epoch": 1.3574660633484164,
1195
+ "grad_norm": 0.04328558221459389,
1196
+ "learning_rate": 1.0956690368455075e-05,
1197
+ "loss": 0.005,
1198
+ "step": 8400
1199
+ },
1200
+ {
1201
+ "epoch": 1.365546218487395,
1202
+ "grad_norm": 0.058262139558792114,
1203
+ "learning_rate": 1.090282266752855e-05,
1204
+ "loss": 0.0053,
1205
+ "step": 8450
1206
+ },
1207
+ {
1208
+ "epoch": 1.3736263736263736,
1209
+ "grad_norm": 0.033369556069374084,
1210
+ "learning_rate": 1.0848954966602025e-05,
1211
+ "loss": 0.0058,
1212
+ "step": 8500
1213
+ },
1214
+ {
1215
+ "epoch": 1.3817065287653523,
1216
+ "grad_norm": 0.07817134261131287,
1217
+ "learning_rate": 1.0795087265675501e-05,
1218
+ "loss": 0.0053,
1219
+ "step": 8550
1220
+ },
1221
+ {
1222
+ "epoch": 1.389786683904331,
1223
+ "grad_norm": 0.0364365428686142,
1224
+ "learning_rate": 1.0741219564748977e-05,
1225
+ "loss": 0.0049,
1226
+ "step": 8600
1227
+ },
1228
+ {
1229
+ "epoch": 1.3978668390433096,
1230
+ "grad_norm": 0.047975849360227585,
1231
+ "learning_rate": 1.0687351863822453e-05,
1232
+ "loss": 0.0054,
1233
+ "step": 8650
1234
+ },
1235
+ {
1236
+ "epoch": 1.4059469941822882,
1237
+ "grad_norm": 0.05053960904479027,
1238
+ "learning_rate": 1.0633484162895929e-05,
1239
+ "loss": 0.0049,
1240
+ "step": 8700
1241
+ },
1242
+ {
1243
+ "epoch": 1.4140271493212668,
1244
+ "grad_norm": 0.05517440661787987,
1245
+ "learning_rate": 1.0579616461969404e-05,
1246
+ "loss": 0.0053,
1247
+ "step": 8750
1248
+ },
1249
+ {
1250
+ "epoch": 1.4221073044602457,
1251
+ "grad_norm": 0.045634444802999496,
1252
+ "learning_rate": 1.052574876104288e-05,
1253
+ "loss": 0.0051,
1254
+ "step": 8800
1255
+ },
1256
+ {
1257
+ "epoch": 1.4301874595992243,
1258
+ "grad_norm": 0.06119120493531227,
1259
+ "learning_rate": 1.0471881060116356e-05,
1260
+ "loss": 0.005,
1261
+ "step": 8850
1262
+ },
1263
+ {
1264
+ "epoch": 1.438267614738203,
1265
+ "grad_norm": 0.037451136857271194,
1266
+ "learning_rate": 1.0418013359189832e-05,
1267
+ "loss": 0.005,
1268
+ "step": 8900
1269
+ },
1270
+ {
1271
+ "epoch": 1.4463477698771816,
1272
+ "grad_norm": 0.045001059770584106,
1273
+ "learning_rate": 1.0364145658263308e-05,
1274
+ "loss": 0.0055,
1275
+ "step": 8950
1276
+ },
1277
+ {
1278
+ "epoch": 1.4544279250161603,
1279
+ "grad_norm": 0.027605222538113594,
1280
+ "learning_rate": 1.031027795733678e-05,
1281
+ "loss": 0.0047,
1282
+ "step": 9000
1283
+ },
1284
+ {
1285
+ "epoch": 1.4625080801551391,
1286
+ "grad_norm": 0.04454193264245987,
1287
+ "learning_rate": 1.0256410256410256e-05,
1288
+ "loss": 0.0054,
1289
+ "step": 9050
1290
+ },
1291
+ {
1292
+ "epoch": 1.4705882352941178,
1293
+ "grad_norm": 0.023829152807593346,
1294
+ "learning_rate": 1.0202542555483732e-05,
1295
+ "loss": 0.0051,
1296
+ "step": 9100
1297
+ },
1298
+ {
1299
+ "epoch": 1.4786683904330964,
1300
+ "grad_norm": 0.04157187044620514,
1301
+ "learning_rate": 1.0148674854557207e-05,
1302
+ "loss": 0.0047,
1303
+ "step": 9150
1304
+ },
1305
+ {
1306
+ "epoch": 1.486748545572075,
1307
+ "grad_norm": 0.03874518349766731,
1308
+ "learning_rate": 1.0094807153630683e-05,
1309
+ "loss": 0.0053,
1310
+ "step": 9200
1311
+ },
1312
+ {
1313
+ "epoch": 1.4948287007110537,
1314
+ "grad_norm": 0.026905696839094162,
1315
+ "learning_rate": 1.0040939452704159e-05,
1316
+ "loss": 0.005,
1317
+ "step": 9250
1318
+ },
1319
+ {
1320
+ "epoch": 1.5029088558500323,
1321
+ "grad_norm": 0.06382673233747482,
1322
+ "learning_rate": 9.987071751777635e-06,
1323
+ "loss": 0.005,
1324
+ "step": 9300
1325
+ },
1326
+ {
1327
+ "epoch": 1.510989010989011,
1328
+ "grad_norm": 0.02449849620461464,
1329
+ "learning_rate": 9.93320405085111e-06,
1330
+ "loss": 0.0053,
1331
+ "step": 9350
1332
+ },
1333
+ {
1334
+ "epoch": 1.5190691661279896,
1335
+ "grad_norm": 0.04602253809571266,
1336
+ "learning_rate": 9.879336349924586e-06,
1337
+ "loss": 0.0058,
1338
+ "step": 9400
1339
+ },
1340
+ {
1341
+ "epoch": 1.5271493212669682,
1342
+ "grad_norm": 0.026318348944187164,
1343
+ "learning_rate": 9.82546864899806e-06,
1344
+ "loss": 0.005,
1345
+ "step": 9450
1346
+ },
1347
+ {
1348
+ "epoch": 1.5352294764059469,
1349
+ "grad_norm": 0.028364863246679306,
1350
+ "learning_rate": 9.771600948071536e-06,
1351
+ "loss": 0.0047,
1352
+ "step": 9500
1353
+ },
1354
+ {
1355
+ "epoch": 1.5433096315449255,
1356
+ "grad_norm": 0.03204864263534546,
1357
+ "learning_rate": 9.717733247145012e-06,
1358
+ "loss": 0.0046,
1359
+ "step": 9550
1360
+ },
1361
+ {
1362
+ "epoch": 1.5513897866839044,
1363
+ "grad_norm": 0.023740077391266823,
1364
+ "learning_rate": 9.663865546218488e-06,
1365
+ "loss": 0.0057,
1366
+ "step": 9600
1367
+ },
1368
+ {
1369
+ "epoch": 1.559469941822883,
1370
+ "grad_norm": 0.028953751549124718,
1371
+ "learning_rate": 9.609997845291964e-06,
1372
+ "loss": 0.0049,
1373
+ "step": 9650
1374
+ },
1375
+ {
1376
+ "epoch": 1.5675500969618616,
1377
+ "grad_norm": 0.039458662271499634,
1378
+ "learning_rate": 9.55613014436544e-06,
1379
+ "loss": 0.0052,
1380
+ "step": 9700
1381
+ },
1382
+ {
1383
+ "epoch": 1.5756302521008403,
1384
+ "grad_norm": 0.02466548979282379,
1385
+ "learning_rate": 9.502262443438914e-06,
1386
+ "loss": 0.0053,
1387
+ "step": 9750
1388
+ },
1389
+ {
1390
+ "epoch": 1.5837104072398192,
1391
+ "grad_norm": 0.09884428232908249,
1392
+ "learning_rate": 9.44839474251239e-06,
1393
+ "loss": 0.0045,
1394
+ "step": 9800
1395
+ },
1396
+ {
1397
+ "epoch": 1.5917905623787978,
1398
+ "grad_norm": 0.052319470793008804,
1399
+ "learning_rate": 9.394527041585865e-06,
1400
+ "loss": 0.0047,
1401
+ "step": 9850
1402
+ },
1403
+ {
1404
+ "epoch": 1.5998707175177764,
1405
+ "grad_norm": 0.04534400627017021,
1406
+ "learning_rate": 9.340659340659341e-06,
1407
+ "loss": 0.0042,
1408
+ "step": 9900
1409
+ },
1410
+ {
1411
+ "epoch": 1.607950872656755,
1412
+ "grad_norm": 0.031061217188835144,
1413
+ "learning_rate": 9.286791639732817e-06,
1414
+ "loss": 0.0053,
1415
+ "step": 9950
1416
+ },
1417
+ {
1418
+ "epoch": 1.6160310277957337,
1419
+ "grad_norm": 0.04152417555451393,
1420
+ "learning_rate": 9.232923938806293e-06,
1421
+ "loss": 0.0044,
1422
+ "step": 10000
1423
+ },
1424
+ {
1425
+ "epoch": 1.6241111829347123,
1426
+ "grad_norm": 0.06364952027797699,
1427
+ "learning_rate": 9.179056237879767e-06,
1428
+ "loss": 0.0051,
1429
+ "step": 10050
1430
+ },
1431
+ {
1432
+ "epoch": 1.632191338073691,
1433
+ "grad_norm": 0.05075689032673836,
1434
+ "learning_rate": 9.125188536953243e-06,
1435
+ "loss": 0.005,
1436
+ "step": 10100
1437
+ },
1438
+ {
1439
+ "epoch": 1.6402714932126696,
1440
+ "grad_norm": 0.05718667805194855,
1441
+ "learning_rate": 9.071320836026718e-06,
1442
+ "loss": 0.005,
1443
+ "step": 10150
1444
+ },
1445
+ {
1446
+ "epoch": 1.6483516483516483,
1447
+ "grad_norm": 0.05176397040486336,
1448
+ "learning_rate": 9.017453135100194e-06,
1449
+ "loss": 0.005,
1450
+ "step": 10200
1451
+ },
1452
+ {
1453
+ "epoch": 1.656431803490627,
1454
+ "grad_norm": 0.05737081915140152,
1455
+ "learning_rate": 8.96358543417367e-06,
1456
+ "loss": 0.0054,
1457
+ "step": 10250
1458
+ },
1459
+ {
1460
+ "epoch": 1.6645119586296055,
1461
+ "grad_norm": 0.02792266197502613,
1462
+ "learning_rate": 8.909717733247146e-06,
1463
+ "loss": 0.0044,
1464
+ "step": 10300
1465
+ },
1466
+ {
1467
+ "epoch": 1.6725921137685844,
1468
+ "grad_norm": 0.029061343520879745,
1469
+ "learning_rate": 8.855850032320622e-06,
1470
+ "loss": 0.0052,
1471
+ "step": 10350
1472
+ },
1473
+ {
1474
+ "epoch": 1.680672268907563,
1475
+ "grad_norm": 0.03089820221066475,
1476
+ "learning_rate": 8.801982331394097e-06,
1477
+ "loss": 0.005,
1478
+ "step": 10400
1479
+ },
1480
+ {
1481
+ "epoch": 1.6887524240465417,
1482
+ "grad_norm": 0.046603500843048096,
1483
+ "learning_rate": 8.748114630467572e-06,
1484
+ "loss": 0.006,
1485
+ "step": 10450
1486
+ },
1487
+ {
1488
+ "epoch": 1.6968325791855203,
1489
+ "grad_norm": 0.033478520810604095,
1490
+ "learning_rate": 8.694246929541047e-06,
1491
+ "loss": 0.0045,
1492
+ "step": 10500
1493
+ },
1494
+ {
1495
+ "epoch": 1.7049127343244992,
1496
+ "grad_norm": 0.045349959284067154,
1497
+ "learning_rate": 8.640379228614523e-06,
1498
+ "loss": 0.0043,
1499
+ "step": 10550
1500
+ },
1501
+ {
1502
+ "epoch": 1.7129928894634778,
1503
+ "grad_norm": 0.04198373854160309,
1504
+ "learning_rate": 8.586511527687999e-06,
1505
+ "loss": 0.0046,
1506
+ "step": 10600
1507
+ },
1508
+ {
1509
+ "epoch": 1.7210730446024565,
1510
+ "grad_norm": 0.030365299433469772,
1511
+ "learning_rate": 8.532643826761475e-06,
1512
+ "loss": 0.0047,
1513
+ "step": 10650
1514
+ },
1515
+ {
1516
+ "epoch": 1.729153199741435,
1517
+ "grad_norm": 0.053815387189388275,
1518
+ "learning_rate": 8.47877612583495e-06,
1519
+ "loss": 0.0053,
1520
+ "step": 10700
1521
+ },
1522
+ {
1523
+ "epoch": 1.7372333548804137,
1524
+ "grad_norm": 0.040949735790491104,
1525
+ "learning_rate": 8.424908424908426e-06,
1526
+ "loss": 0.0049,
1527
+ "step": 10750
1528
+ },
1529
+ {
1530
+ "epoch": 1.7453135100193924,
1531
+ "grad_norm": 0.02742874063551426,
1532
+ "learning_rate": 8.371040723981902e-06,
1533
+ "loss": 0.0049,
1534
+ "step": 10800
1535
+ },
1536
+ {
1537
+ "epoch": 1.753393665158371,
1538
+ "grad_norm": 0.06784753501415253,
1539
+ "learning_rate": 8.317173023055376e-06,
1540
+ "loss": 0.0058,
1541
+ "step": 10850
1542
+ },
1543
+ {
1544
+ "epoch": 1.7614738202973497,
1545
+ "grad_norm": 0.03332887962460518,
1546
+ "learning_rate": 8.263305322128852e-06,
1547
+ "loss": 0.0046,
1548
+ "step": 10900
1549
+ },
1550
+ {
1551
+ "epoch": 1.7695539754363283,
1552
+ "grad_norm": 0.031116908416152,
1553
+ "learning_rate": 8.209437621202328e-06,
1554
+ "loss": 0.0046,
1555
+ "step": 10950
1556
+ },
1557
+ {
1558
+ "epoch": 1.777634130575307,
1559
+ "grad_norm": 0.03276669979095459,
1560
+ "learning_rate": 8.155569920275804e-06,
1561
+ "loss": 0.0045,
1562
+ "step": 11000
1563
+ },
1564
+ {
1565
+ "epoch": 1.7857142857142856,
1566
+ "grad_norm": 0.04121123626828194,
1567
+ "learning_rate": 8.10170221934928e-06,
1568
+ "loss": 0.0057,
1569
+ "step": 11050
1570
+ },
1571
+ {
1572
+ "epoch": 1.7937944408532642,
1573
+ "grad_norm": 0.05228004604578018,
1574
+ "learning_rate": 8.047834518422755e-06,
1575
+ "loss": 0.005,
1576
+ "step": 11100
1577
+ },
1578
+ {
1579
+ "epoch": 1.801874595992243,
1580
+ "grad_norm": 0.03658825531601906,
1581
+ "learning_rate": 7.993966817496231e-06,
1582
+ "loss": 0.0048,
1583
+ "step": 11150
1584
+ },
1585
+ {
1586
+ "epoch": 1.8099547511312217,
1587
+ "grad_norm": 0.029890988022089005,
1588
+ "learning_rate": 7.940099116569705e-06,
1589
+ "loss": 0.0045,
1590
+ "step": 11200
1591
+ },
1592
+ {
1593
+ "epoch": 1.8180349062702004,
1594
+ "grad_norm": 0.057183150202035904,
1595
+ "learning_rate": 7.886231415643181e-06,
1596
+ "loss": 0.0046,
1597
+ "step": 11250
1598
+ },
1599
+ {
1600
+ "epoch": 1.826115061409179,
1601
+ "grad_norm": 0.032826654613018036,
1602
+ "learning_rate": 7.832363714716657e-06,
1603
+ "loss": 0.0044,
1604
+ "step": 11300
1605
+ },
1606
+ {
1607
+ "epoch": 1.8341952165481579,
1608
+ "grad_norm": 0.08467372506856918,
1609
+ "learning_rate": 7.778496013790133e-06,
1610
+ "loss": 0.0048,
1611
+ "step": 11350
1612
+ },
1613
+ {
1614
+ "epoch": 1.8422753716871365,
1615
+ "grad_norm": 0.03478661924600601,
1616
+ "learning_rate": 7.724628312863608e-06,
1617
+ "loss": 0.005,
1618
+ "step": 11400
1619
+ },
1620
+ {
1621
+ "epoch": 1.8503555268261151,
1622
+ "grad_norm": 0.05386711657047272,
1623
+ "learning_rate": 7.670760611937084e-06,
1624
+ "loss": 0.0048,
1625
+ "step": 11450
1626
+ },
1627
+ {
1628
+ "epoch": 1.8584356819650938,
1629
+ "grad_norm": 0.03354140743613243,
1630
+ "learning_rate": 7.616892911010558e-06,
1631
+ "loss": 0.0044,
1632
+ "step": 11500
1633
+ },
1634
+ {
1635
+ "epoch": 1.8665158371040724,
1636
+ "grad_norm": 0.043414924293756485,
1637
+ "learning_rate": 7.563025210084034e-06,
1638
+ "loss": 0.0055,
1639
+ "step": 11550
1640
+ },
1641
+ {
1642
+ "epoch": 1.874595992243051,
1643
+ "grad_norm": 0.040471382439136505,
1644
+ "learning_rate": 7.50915750915751e-06,
1645
+ "loss": 0.0052,
1646
+ "step": 11600
1647
+ },
1648
+ {
1649
+ "epoch": 1.8826761473820297,
1650
+ "grad_norm": 0.06200335547327995,
1651
+ "learning_rate": 7.455289808230986e-06,
1652
+ "loss": 0.0053,
1653
+ "step": 11650
1654
+ },
1655
+ {
1656
+ "epoch": 1.8907563025210083,
1657
+ "grad_norm": 0.04366638883948326,
1658
+ "learning_rate": 7.4014221073044616e-06,
1659
+ "loss": 0.0046,
1660
+ "step": 11700
1661
+ },
1662
+ {
1663
+ "epoch": 1.898836457659987,
1664
+ "grad_norm": 0.022821014747023582,
1665
+ "learning_rate": 7.3475544063779365e-06,
1666
+ "loss": 0.0045,
1667
+ "step": 11750
1668
+ },
1669
+ {
1670
+ "epoch": 1.9069166127989656,
1671
+ "grad_norm": 0.038873497396707535,
1672
+ "learning_rate": 7.2936867054514115e-06,
1673
+ "loss": 0.0046,
1674
+ "step": 11800
1675
+ },
1676
+ {
1677
+ "epoch": 1.9149967679379443,
1678
+ "grad_norm": 0.04890233278274536,
1679
+ "learning_rate": 7.239819004524887e-06,
1680
+ "loss": 0.0057,
1681
+ "step": 11850
1682
+ },
1683
+ {
1684
+ "epoch": 1.9230769230769231,
1685
+ "grad_norm": 0.04092305526137352,
1686
+ "learning_rate": 7.185951303598363e-06,
1687
+ "loss": 0.005,
1688
+ "step": 11900
1689
+ },
1690
+ {
1691
+ "epoch": 1.9311570782159018,
1692
+ "grad_norm": 0.05939971283078194,
1693
+ "learning_rate": 7.132083602671839e-06,
1694
+ "loss": 0.0046,
1695
+ "step": 11950
1696
+ },
1697
+ {
1698
+ "epoch": 1.9392372333548804,
1699
+ "grad_norm": 0.037901926785707474,
1700
+ "learning_rate": 7.078215901745315e-06,
1701
+ "loss": 0.0045,
1702
+ "step": 12000
1703
+ },
1704
+ {
1705
+ "epoch": 1.947317388493859,
1706
+ "grad_norm": 0.0488058477640152,
1707
+ "learning_rate": 7.024348200818789e-06,
1708
+ "loss": 0.005,
1709
+ "step": 12050
1710
+ },
1711
+ {
1712
+ "epoch": 1.955397543632838,
1713
+ "grad_norm": 0.06671205163002014,
1714
+ "learning_rate": 6.970480499892265e-06,
1715
+ "loss": 0.0053,
1716
+ "step": 12100
1717
+ },
1718
+ {
1719
+ "epoch": 1.9634776987718165,
1720
+ "grad_norm": 0.03580876812338829,
1721
+ "learning_rate": 6.91661279896574e-06,
1722
+ "loss": 0.0048,
1723
+ "step": 12150
1724
+ },
1725
+ {
1726
+ "epoch": 1.9715578539107952,
1727
+ "grad_norm": 0.05258365720510483,
1728
+ "learning_rate": 6.862745098039216e-06,
1729
+ "loss": 0.0047,
1730
+ "step": 12200
1731
+ },
1732
+ {
1733
+ "epoch": 1.9796380090497738,
1734
+ "grad_norm": 0.035823095589876175,
1735
+ "learning_rate": 6.808877397112692e-06,
1736
+ "loss": 0.0053,
1737
+ "step": 12250
1738
+ },
1739
+ {
1740
+ "epoch": 1.9877181641887525,
1741
+ "grad_norm": 0.03747252747416496,
1742
+ "learning_rate": 6.755009696186168e-06,
1743
+ "loss": 0.0052,
1744
+ "step": 12300
1745
+ },
1746
+ {
1747
+ "epoch": 1.995798319327731,
1748
+ "grad_norm": 0.029116889461874962,
1749
+ "learning_rate": 6.701141995259643e-06,
1750
+ "loss": 0.0045,
1751
+ "step": 12350
1752
+ },
1753
+ {
1754
+ "epoch": 2.0,
1755
+ "eval_loss": 0.003754823002964258,
1756
+ "eval_rouge1": 87.21845608272304,
1757
+ "eval_rouge2": 83.41556886218162,
1758
+ "eval_rougeL": 85.9862609239223,
1759
+ "eval_rougeLsum": 85.95382052592191,
1760
+ "eval_runtime": 48.1802,
1761
+ "eval_samples_per_second": 10.378,
1762
+ "eval_steps_per_second": 1.308,
1763
+ "step": 12376
1764
+ },
1765
+ {
1766
+ "epoch": 2.0038784744667097,
1767
+ "grad_norm": 0.040494147688150406,
1768
+ "learning_rate": 6.647274294333118e-06,
1769
+ "loss": 0.0051,
1770
+ "step": 12400
1771
+ },
1772
+ {
1773
+ "epoch": 2.0119586296056884,
1774
+ "grad_norm": 0.021118978038430214,
1775
+ "learning_rate": 6.5934065934065935e-06,
1776
+ "loss": 0.0044,
1777
+ "step": 12450
1778
+ },
1779
+ {
1780
+ "epoch": 2.020038784744667,
1781
+ "grad_norm": 0.03655942156910896,
1782
+ "learning_rate": 6.539538892480069e-06,
1783
+ "loss": 0.0046,
1784
+ "step": 12500
1785
+ },
1786
+ {
1787
+ "epoch": 2.0281189398836457,
1788
+ "grad_norm": 0.033596962690353394,
1789
+ "learning_rate": 6.485671191553545e-06,
1790
+ "loss": 0.0049,
1791
+ "step": 12550
1792
+ },
1793
+ {
1794
+ "epoch": 2.0361990950226243,
1795
+ "grad_norm": 0.04082285612821579,
1796
+ "learning_rate": 6.431803490627021e-06,
1797
+ "loss": 0.0046,
1798
+ "step": 12600
1799
+ },
1800
+ {
1801
+ "epoch": 2.044279250161603,
1802
+ "grad_norm": 0.035328153520822525,
1803
+ "learning_rate": 6.377935789700496e-06,
1804
+ "loss": 0.0047,
1805
+ "step": 12650
1806
+ },
1807
+ {
1808
+ "epoch": 2.0523594053005816,
1809
+ "grad_norm": 0.06532145291566849,
1810
+ "learning_rate": 6.324068088773972e-06,
1811
+ "loss": 0.0046,
1812
+ "step": 12700
1813
+ },
1814
+ {
1815
+ "epoch": 2.0604395604395602,
1816
+ "grad_norm": 0.021467560902237892,
1817
+ "learning_rate": 6.2702003878474475e-06,
1818
+ "loss": 0.0044,
1819
+ "step": 12750
1820
+ },
1821
+ {
1822
+ "epoch": 2.0685197155785393,
1823
+ "grad_norm": 0.028903750702738762,
1824
+ "learning_rate": 6.2163326869209225e-06,
1825
+ "loss": 0.0047,
1826
+ "step": 12800
1827
+ },
1828
+ {
1829
+ "epoch": 2.076599870717518,
1830
+ "grad_norm": 0.04827199503779411,
1831
+ "learning_rate": 6.162464985994398e-06,
1832
+ "loss": 0.0046,
1833
+ "step": 12850
1834
+ },
1835
+ {
1836
+ "epoch": 2.0846800258564966,
1837
+ "grad_norm": 0.05190654471516609,
1838
+ "learning_rate": 6.108597285067874e-06,
1839
+ "loss": 0.0044,
1840
+ "step": 12900
1841
+ },
1842
+ {
1843
+ "epoch": 2.0927601809954752,
1844
+ "grad_norm": 0.043597374111413956,
1845
+ "learning_rate": 6.054729584141349e-06,
1846
+ "loss": 0.0039,
1847
+ "step": 12950
1848
+ },
1849
+ {
1850
+ "epoch": 2.100840336134454,
1851
+ "grad_norm": 0.025249801576137543,
1852
+ "learning_rate": 6.000861883214825e-06,
1853
+ "loss": 0.0049,
1854
+ "step": 13000
1855
+ },
1856
+ {
1857
+ "epoch": 2.1089204912734325,
1858
+ "grad_norm": 0.04429004713892937,
1859
+ "learning_rate": 5.946994182288301e-06,
1860
+ "loss": 0.0045,
1861
+ "step": 13050
1862
+ },
1863
+ {
1864
+ "epoch": 2.117000646412411,
1865
+ "grad_norm": 0.05018601194024086,
1866
+ "learning_rate": 5.8931264813617764e-06,
1867
+ "loss": 0.0047,
1868
+ "step": 13100
1869
+ },
1870
+ {
1871
+ "epoch": 2.12508080155139,
1872
+ "grad_norm": 0.0563606433570385,
1873
+ "learning_rate": 5.839258780435252e-06,
1874
+ "loss": 0.0049,
1875
+ "step": 13150
1876
+ },
1877
+ {
1878
+ "epoch": 2.1331609566903684,
1879
+ "grad_norm": 0.036379583179950714,
1880
+ "learning_rate": 5.785391079508727e-06,
1881
+ "loss": 0.0045,
1882
+ "step": 13200
1883
+ },
1884
+ {
1885
+ "epoch": 2.141241111829347,
1886
+ "grad_norm": 0.03966435417532921,
1887
+ "learning_rate": 5.731523378582202e-06,
1888
+ "loss": 0.0046,
1889
+ "step": 13250
1890
+ },
1891
+ {
1892
+ "epoch": 2.1493212669683257,
1893
+ "grad_norm": 0.03525066375732422,
1894
+ "learning_rate": 5.677655677655678e-06,
1895
+ "loss": 0.004,
1896
+ "step": 13300
1897
+ },
1898
+ {
1899
+ "epoch": 2.1574014221073043,
1900
+ "grad_norm": 0.04028931260108948,
1901
+ "learning_rate": 5.623787976729154e-06,
1902
+ "loss": 0.0045,
1903
+ "step": 13350
1904
+ },
1905
+ {
1906
+ "epoch": 2.165481577246283,
1907
+ "grad_norm": 0.027697792276740074,
1908
+ "learning_rate": 5.5699202758026296e-06,
1909
+ "loss": 0.0049,
1910
+ "step": 13400
1911
+ },
1912
+ {
1913
+ "epoch": 2.1735617323852616,
1914
+ "grad_norm": 0.02208828553557396,
1915
+ "learning_rate": 5.516052574876105e-06,
1916
+ "loss": 0.0044,
1917
+ "step": 13450
1918
+ },
1919
+ {
1920
+ "epoch": 2.1816418875242403,
1921
+ "grad_norm": 0.03327793627977371,
1922
+ "learning_rate": 5.4621848739495795e-06,
1923
+ "loss": 0.0052,
1924
+ "step": 13500
1925
+ },
1926
+ {
1927
+ "epoch": 2.1897220426632193,
1928
+ "grad_norm": 0.040238089859485626,
1929
+ "learning_rate": 5.408317173023055e-06,
1930
+ "loss": 0.0044,
1931
+ "step": 13550
1932
+ },
1933
+ {
1934
+ "epoch": 2.197802197802198,
1935
+ "grad_norm": 0.02015913464128971,
1936
+ "learning_rate": 5.354449472096531e-06,
1937
+ "loss": 0.0049,
1938
+ "step": 13600
1939
+ },
1940
+ {
1941
+ "epoch": 2.2058823529411766,
1942
+ "grad_norm": 0.018138017505407333,
1943
+ "learning_rate": 5.300581771170007e-06,
1944
+ "loss": 0.0048,
1945
+ "step": 13650
1946
+ },
1947
+ {
1948
+ "epoch": 2.2139625080801553,
1949
+ "grad_norm": 0.050266802310943604,
1950
+ "learning_rate": 5.246714070243483e-06,
1951
+ "loss": 0.0043,
1952
+ "step": 13700
1953
+ },
1954
+ {
1955
+ "epoch": 2.222042663219134,
1956
+ "grad_norm": 0.04515570029616356,
1957
+ "learning_rate": 5.1928463693169585e-06,
1958
+ "loss": 0.0036,
1959
+ "step": 13750
1960
+ },
1961
+ {
1962
+ "epoch": 2.2301228183581125,
1963
+ "grad_norm": 0.039447471499443054,
1964
+ "learning_rate": 5.138978668390433e-06,
1965
+ "loss": 0.0044,
1966
+ "step": 13800
1967
+ },
1968
+ {
1969
+ "epoch": 2.238202973497091,
1970
+ "grad_norm": 0.03310653567314148,
1971
+ "learning_rate": 5.085110967463908e-06,
1972
+ "loss": 0.0044,
1973
+ "step": 13850
1974
+ },
1975
+ {
1976
+ "epoch": 2.24628312863607,
1977
+ "grad_norm": 0.014222861267626286,
1978
+ "learning_rate": 5.031243266537384e-06,
1979
+ "loss": 0.0047,
1980
+ "step": 13900
1981
+ },
1982
+ {
1983
+ "epoch": 2.2543632837750485,
1984
+ "grad_norm": 0.016546355560421944,
1985
+ "learning_rate": 4.97737556561086e-06,
1986
+ "loss": 0.0047,
1987
+ "step": 13950
1988
+ },
1989
+ {
1990
+ "epoch": 2.262443438914027,
1991
+ "grad_norm": 0.05192546918988228,
1992
+ "learning_rate": 4.923507864684336e-06,
1993
+ "loss": 0.0043,
1994
+ "step": 14000
1995
+ },
1996
+ {
1997
+ "epoch": 2.2705235940530057,
1998
+ "grad_norm": 0.04964493215084076,
1999
+ "learning_rate": 4.869640163757811e-06,
2000
+ "loss": 0.0047,
2001
+ "step": 14050
2002
+ },
2003
+ {
2004
+ "epoch": 2.2786037491919844,
2005
+ "grad_norm": 0.01690448634326458,
2006
+ "learning_rate": 4.8157724628312866e-06,
2007
+ "loss": 0.0043,
2008
+ "step": 14100
2009
+ },
2010
+ {
2011
+ "epoch": 2.286683904330963,
2012
+ "grad_norm": 0.03871385008096695,
2013
+ "learning_rate": 4.761904761904762e-06,
2014
+ "loss": 0.0054,
2015
+ "step": 14150
2016
+ },
2017
+ {
2018
+ "epoch": 2.2947640594699417,
2019
+ "grad_norm": 0.029631048440933228,
2020
+ "learning_rate": 4.708037060978238e-06,
2021
+ "loss": 0.0042,
2022
+ "step": 14200
2023
+ },
2024
+ {
2025
+ "epoch": 2.3028442146089203,
2026
+ "grad_norm": 0.031350765377283096,
2027
+ "learning_rate": 4.654169360051713e-06,
2028
+ "loss": 0.0045,
2029
+ "step": 14250
2030
+ },
2031
+ {
2032
+ "epoch": 2.310924369747899,
2033
+ "grad_norm": 0.05931168794631958,
2034
+ "learning_rate": 4.600301659125189e-06,
2035
+ "loss": 0.0051,
2036
+ "step": 14300
2037
+ },
2038
+ {
2039
+ "epoch": 2.3190045248868776,
2040
+ "grad_norm": 0.04504646733403206,
2041
+ "learning_rate": 4.546433958198665e-06,
2042
+ "loss": 0.0043,
2043
+ "step": 14350
2044
+ },
2045
+ {
2046
+ "epoch": 2.3270846800258567,
2047
+ "grad_norm": 0.04591371491551399,
2048
+ "learning_rate": 4.4925662572721405e-06,
2049
+ "loss": 0.0046,
2050
+ "step": 14400
2051
+ },
2052
+ {
2053
+ "epoch": 2.3351648351648353,
2054
+ "grad_norm": 0.030743196606636047,
2055
+ "learning_rate": 4.4386985563456155e-06,
2056
+ "loss": 0.004,
2057
+ "step": 14450
2058
+ },
2059
+ {
2060
+ "epoch": 2.343244990303814,
2061
+ "grad_norm": 0.04723818972706795,
2062
+ "learning_rate": 4.384830855419091e-06,
2063
+ "loss": 0.0036,
2064
+ "step": 14500
2065
+ },
2066
+ {
2067
+ "epoch": 2.3513251454427926,
2068
+ "grad_norm": 0.02913173846900463,
2069
+ "learning_rate": 4.330963154492567e-06,
2070
+ "loss": 0.0049,
2071
+ "step": 14550
2072
+ },
2073
+ {
2074
+ "epoch": 2.3594053005817712,
2075
+ "grad_norm": 0.025342822074890137,
2076
+ "learning_rate": 4.277095453566042e-06,
2077
+ "loss": 0.0052,
2078
+ "step": 14600
2079
+ },
2080
+ {
2081
+ "epoch": 2.36748545572075,
2082
+ "grad_norm": 0.04897177964448929,
2083
+ "learning_rate": 4.223227752639518e-06,
2084
+ "loss": 0.0046,
2085
+ "step": 14650
2086
+ },
2087
+ {
2088
+ "epoch": 2.3755656108597285,
2089
+ "grad_norm": 0.05571192875504494,
2090
+ "learning_rate": 4.169360051712994e-06,
2091
+ "loss": 0.0045,
2092
+ "step": 14700
2093
+ },
2094
+ {
2095
+ "epoch": 2.383645765998707,
2096
+ "grad_norm": 0.04304831102490425,
2097
+ "learning_rate": 4.115492350786469e-06,
2098
+ "loss": 0.0045,
2099
+ "step": 14750
2100
+ },
2101
+ {
2102
+ "epoch": 2.391725921137686,
2103
+ "grad_norm": 0.04351252317428589,
2104
+ "learning_rate": 4.0616246498599444e-06,
2105
+ "loss": 0.0046,
2106
+ "step": 14800
2107
+ },
2108
+ {
2109
+ "epoch": 2.3998060762766644,
2110
+ "grad_norm": 0.07481127232313156,
2111
+ "learning_rate": 4.00775694893342e-06,
2112
+ "loss": 0.0044,
2113
+ "step": 14850
2114
+ },
2115
+ {
2116
+ "epoch": 2.407886231415643,
2117
+ "grad_norm": 0.06555662304162979,
2118
+ "learning_rate": 3.953889248006895e-06,
2119
+ "loss": 0.0046,
2120
+ "step": 14900
2121
+ },
2122
+ {
2123
+ "epoch": 2.4159663865546217,
2124
+ "grad_norm": 0.03455435112118721,
2125
+ "learning_rate": 3.900021547080371e-06,
2126
+ "loss": 0.0047,
2127
+ "step": 14950
2128
+ },
2129
+ {
2130
+ "epoch": 2.4240465416936003,
2131
+ "grad_norm": 0.0476142056286335,
2132
+ "learning_rate": 3.846153846153847e-06,
2133
+ "loss": 0.0046,
2134
+ "step": 15000
2135
+ },
2136
+ {
2137
+ "epoch": 2.4321266968325794,
2138
+ "grad_norm": 0.07432708144187927,
2139
+ "learning_rate": 3.7922861452273218e-06,
2140
+ "loss": 0.0044,
2141
+ "step": 15050
2142
+ },
2143
+ {
2144
+ "epoch": 2.440206851971558,
2145
+ "grad_norm": 0.018862377852201462,
2146
+ "learning_rate": 3.7384184443007976e-06,
2147
+ "loss": 0.0042,
2148
+ "step": 15100
2149
+ },
2150
+ {
2151
+ "epoch": 2.4482870071105367,
2152
+ "grad_norm": 0.0463634617626667,
2153
+ "learning_rate": 3.6845507433742734e-06,
2154
+ "loss": 0.0051,
2155
+ "step": 15150
2156
+ },
2157
+ {
2158
+ "epoch": 2.4563671622495153,
2159
+ "grad_norm": 0.0470375195145607,
2160
+ "learning_rate": 3.6306830424477483e-06,
2161
+ "loss": 0.0046,
2162
+ "step": 15200
2163
+ },
2164
+ {
2165
+ "epoch": 2.464447317388494,
2166
+ "grad_norm": 0.028038673102855682,
2167
+ "learning_rate": 3.576815341521224e-06,
2168
+ "loss": 0.0045,
2169
+ "step": 15250
2170
+ },
2171
+ {
2172
+ "epoch": 2.4725274725274726,
2173
+ "grad_norm": 0.03303570672869682,
2174
+ "learning_rate": 3.5229476405947e-06,
2175
+ "loss": 0.0048,
2176
+ "step": 15300
2177
+ },
2178
+ {
2179
+ "epoch": 2.4806076276664513,
2180
+ "grad_norm": 0.040639448910951614,
2181
+ "learning_rate": 3.4690799396681753e-06,
2182
+ "loss": 0.0045,
2183
+ "step": 15350
2184
+ },
2185
+ {
2186
+ "epoch": 2.48868778280543,
2187
+ "grad_norm": 0.03696522116661072,
2188
+ "learning_rate": 3.4152122387416507e-06,
2189
+ "loss": 0.0047,
2190
+ "step": 15400
2191
+ },
2192
+ {
2193
+ "epoch": 2.4967679379444085,
2194
+ "grad_norm": 0.06647258996963501,
2195
+ "learning_rate": 3.3613445378151265e-06,
2196
+ "loss": 0.0046,
2197
+ "step": 15450
2198
+ },
2199
+ {
2200
+ "epoch": 2.504848093083387,
2201
+ "grad_norm": 0.039001937955617905,
2202
+ "learning_rate": 3.307476836888602e-06,
2203
+ "loss": 0.0052,
2204
+ "step": 15500
2205
+ },
2206
+ {
2207
+ "epoch": 2.512928248222366,
2208
+ "grad_norm": 0.02684204652905464,
2209
+ "learning_rate": 3.2536091359620777e-06,
2210
+ "loss": 0.0043,
2211
+ "step": 15550
2212
+ },
2213
+ {
2214
+ "epoch": 2.5210084033613445,
2215
+ "grad_norm": 0.04314061999320984,
2216
+ "learning_rate": 3.1997414350355526e-06,
2217
+ "loss": 0.0047,
2218
+ "step": 15600
2219
+ },
2220
+ {
2221
+ "epoch": 2.529088558500323,
2222
+ "grad_norm": 0.04125179722905159,
2223
+ "learning_rate": 3.1458737341090284e-06,
2224
+ "loss": 0.0046,
2225
+ "step": 15650
2226
+ },
2227
+ {
2228
+ "epoch": 2.5371687136393017,
2229
+ "grad_norm": 0.01851014606654644,
2230
+ "learning_rate": 3.0920060331825042e-06,
2231
+ "loss": 0.0045,
2232
+ "step": 15700
2233
+ },
2234
+ {
2235
+ "epoch": 2.5452488687782804,
2236
+ "grad_norm": 0.03928118199110031,
2237
+ "learning_rate": 3.038138332255979e-06,
2238
+ "loss": 0.0043,
2239
+ "step": 15750
2240
+ },
2241
+ {
2242
+ "epoch": 2.553329023917259,
2243
+ "grad_norm": 0.0691729187965393,
2244
+ "learning_rate": 2.984270631329455e-06,
2245
+ "loss": 0.005,
2246
+ "step": 15800
2247
+ },
2248
+ {
2249
+ "epoch": 2.5614091790562377,
2250
+ "grad_norm": 0.016138378530740738,
2251
+ "learning_rate": 2.930402930402931e-06,
2252
+ "loss": 0.0041,
2253
+ "step": 15850
2254
+ },
2255
+ {
2256
+ "epoch": 2.5694893341952163,
2257
+ "grad_norm": 0.020654356107115746,
2258
+ "learning_rate": 2.8765352294764057e-06,
2259
+ "loss": 0.004,
2260
+ "step": 15900
2261
+ },
2262
+ {
2263
+ "epoch": 2.577569489334195,
2264
+ "grad_norm": 0.04678305238485336,
2265
+ "learning_rate": 2.8226675285498815e-06,
2266
+ "loss": 0.0045,
2267
+ "step": 15950
2268
+ },
2269
+ {
2270
+ "epoch": 2.585649644473174,
2271
+ "grad_norm": 0.035098664462566376,
2272
+ "learning_rate": 2.7687998276233574e-06,
2273
+ "loss": 0.0049,
2274
+ "step": 16000
2275
+ },
2276
+ {
2277
+ "epoch": 2.5937297996121527,
2278
+ "grad_norm": 0.02151743695139885,
2279
+ "learning_rate": 2.7149321266968327e-06,
2280
+ "loss": 0.0049,
2281
+ "step": 16050
2282
+ },
2283
+ {
2284
+ "epoch": 2.6018099547511313,
2285
+ "grad_norm": 0.008306082338094711,
2286
+ "learning_rate": 2.6610644257703085e-06,
2287
+ "loss": 0.0043,
2288
+ "step": 16100
2289
+ },
2290
+ {
2291
+ "epoch": 2.60989010989011,
2292
+ "grad_norm": 0.03021089918911457,
2293
+ "learning_rate": 2.607196724843784e-06,
2294
+ "loss": 0.0042,
2295
+ "step": 16150
2296
+ },
2297
+ {
2298
+ "epoch": 2.6179702650290886,
2299
+ "grad_norm": 0.032146211713552475,
2300
+ "learning_rate": 2.5533290239172593e-06,
2301
+ "loss": 0.0041,
2302
+ "step": 16200
2303
+ },
2304
+ {
2305
+ "epoch": 2.6260504201680672,
2306
+ "grad_norm": 0.030957765877246857,
2307
+ "learning_rate": 2.499461322990735e-06,
2308
+ "loss": 0.0041,
2309
+ "step": 16250
2310
+ },
2311
+ {
2312
+ "epoch": 2.634130575307046,
2313
+ "grad_norm": 0.04607204720377922,
2314
+ "learning_rate": 2.4455936220642105e-06,
2315
+ "loss": 0.0051,
2316
+ "step": 16300
2317
+ },
2318
+ {
2319
+ "epoch": 2.6422107304460245,
2320
+ "grad_norm": 0.02674623765051365,
2321
+ "learning_rate": 2.3917259211376863e-06,
2322
+ "loss": 0.0044,
2323
+ "step": 16350
2324
+ },
2325
+ {
2326
+ "epoch": 2.650290885585003,
2327
+ "grad_norm": 0.016672629863023758,
2328
+ "learning_rate": 2.3378582202111617e-06,
2329
+ "loss": 0.0036,
2330
+ "step": 16400
2331
+ },
2332
+ {
2333
+ "epoch": 2.658371040723982,
2334
+ "grad_norm": 0.03345870599150658,
2335
+ "learning_rate": 2.283990519284637e-06,
2336
+ "loss": 0.0042,
2337
+ "step": 16450
2338
+ },
2339
+ {
2340
+ "epoch": 2.6664511958629604,
2341
+ "grad_norm": 0.03514959663152695,
2342
+ "learning_rate": 2.230122818358113e-06,
2343
+ "loss": 0.0049,
2344
+ "step": 16500
2345
+ },
2346
+ {
2347
+ "epoch": 2.6745313510019395,
2348
+ "grad_norm": 0.03409695625305176,
2349
+ "learning_rate": 2.1762551174315882e-06,
2350
+ "loss": 0.0044,
2351
+ "step": 16550
2352
+ },
2353
+ {
2354
+ "epoch": 2.682611506140918,
2355
+ "grad_norm": 0.021505704149603844,
2356
+ "learning_rate": 2.1223874165050636e-06,
2357
+ "loss": 0.0039,
2358
+ "step": 16600
2359
+ },
2360
+ {
2361
+ "epoch": 2.690691661279897,
2362
+ "grad_norm": 0.142180934548378,
2363
+ "learning_rate": 2.068519715578539e-06,
2364
+ "loss": 0.0049,
2365
+ "step": 16650
2366
+ },
2367
+ {
2368
+ "epoch": 2.6987718164188754,
2369
+ "grad_norm": 0.05118989571928978,
2370
+ "learning_rate": 2.0146520146520148e-06,
2371
+ "loss": 0.0044,
2372
+ "step": 16700
2373
+ },
2374
+ {
2375
+ "epoch": 2.706851971557854,
2376
+ "grad_norm": 0.03433993086218834,
2377
+ "learning_rate": 1.96078431372549e-06,
2378
+ "loss": 0.0042,
2379
+ "step": 16750
2380
+ },
2381
+ {
2382
+ "epoch": 2.7149321266968327,
2383
+ "grad_norm": 0.05495297163724899,
2384
+ "learning_rate": 1.9069166127989658e-06,
2385
+ "loss": 0.0044,
2386
+ "step": 16800
2387
+ },
2388
+ {
2389
+ "epoch": 2.7230122818358113,
2390
+ "grad_norm": 0.03106830269098282,
2391
+ "learning_rate": 1.8530489118724416e-06,
2392
+ "loss": 0.0042,
2393
+ "step": 16850
2394
+ },
2395
+ {
2396
+ "epoch": 2.73109243697479,
2397
+ "grad_norm": 0.05960262566804886,
2398
+ "learning_rate": 1.799181210945917e-06,
2399
+ "loss": 0.004,
2400
+ "step": 16900
2401
+ },
2402
+ {
2403
+ "epoch": 2.7391725921137686,
2404
+ "grad_norm": 0.0477134995162487,
2405
+ "learning_rate": 1.7453135100193923e-06,
2406
+ "loss": 0.0045,
2407
+ "step": 16950
2408
+ },
2409
+ {
2410
+ "epoch": 2.7472527472527473,
2411
+ "grad_norm": 0.04596434533596039,
2412
+ "learning_rate": 1.6925231631113985e-06,
2413
+ "loss": 0.0051,
2414
+ "step": 17000
2415
+ },
2416
+ {
2417
+ "epoch": 2.755332902391726,
2418
+ "grad_norm": 0.02121753990650177,
2419
+ "learning_rate": 1.6386554621848741e-06,
2420
+ "loss": 0.0046,
2421
+ "step": 17050
2422
+ },
2423
+ {
2424
+ "epoch": 2.7634130575307045,
2425
+ "grad_norm": 0.04902210831642151,
2426
+ "learning_rate": 1.5847877612583495e-06,
2427
+ "loss": 0.005,
2428
+ "step": 17100
2429
+ },
2430
+ {
2431
+ "epoch": 2.771493212669683,
2432
+ "grad_norm": 0.03566383942961693,
2433
+ "learning_rate": 1.5309200603318253e-06,
2434
+ "loss": 0.0039,
2435
+ "step": 17150
2436
+ },
2437
+ {
2438
+ "epoch": 2.779573367808662,
2439
+ "grad_norm": 0.03547670692205429,
2440
+ "learning_rate": 1.4770523594053007e-06,
2441
+ "loss": 0.0045,
2442
+ "step": 17200
2443
+ },
2444
+ {
2445
+ "epoch": 2.7876535229476405,
2446
+ "grad_norm": 0.03021397814154625,
2447
+ "learning_rate": 1.423184658478776e-06,
2448
+ "loss": 0.0043,
2449
+ "step": 17250
2450
+ },
2451
+ {
2452
+ "epoch": 2.795733678086619,
2453
+ "grad_norm": 0.03953844681382179,
2454
+ "learning_rate": 1.3693169575522519e-06,
2455
+ "loss": 0.0039,
2456
+ "step": 17300
2457
+ },
2458
+ {
2459
+ "epoch": 2.8038138332255977,
2460
+ "grad_norm": 0.03536642715334892,
2461
+ "learning_rate": 1.3154492566257273e-06,
2462
+ "loss": 0.0041,
2463
+ "step": 17350
2464
+ },
2465
+ {
2466
+ "epoch": 2.8118939883645764,
2467
+ "grad_norm": 0.03634963929653168,
2468
+ "learning_rate": 1.2615815556992029e-06,
2469
+ "loss": 0.005,
2470
+ "step": 17400
2471
+ },
2472
+ {
2473
+ "epoch": 2.819974143503555,
2474
+ "grad_norm": 0.032898109406232834,
2475
+ "learning_rate": 1.2077138547726784e-06,
2476
+ "loss": 0.004,
2477
+ "step": 17450
2478
+ },
2479
+ {
2480
+ "epoch": 2.8280542986425337,
2481
+ "grad_norm": 0.05191650986671448,
2482
+ "learning_rate": 1.153846153846154e-06,
2483
+ "loss": 0.0046,
2484
+ "step": 17500
2485
+ },
2486
+ {
2487
+ "epoch": 2.8361344537815127,
2488
+ "grad_norm": 0.02623840421438217,
2489
+ "learning_rate": 1.0999784529196294e-06,
2490
+ "loss": 0.0042,
2491
+ "step": 17550
2492
+ },
2493
+ {
2494
+ "epoch": 2.8442146089204914,
2495
+ "grad_norm": 0.05044868588447571,
2496
+ "learning_rate": 1.046110751993105e-06,
2497
+ "loss": 0.0044,
2498
+ "step": 17600
2499
+ },
2500
+ {
2501
+ "epoch": 2.85229476405947,
2502
+ "grad_norm": 0.12745575606822968,
2503
+ "learning_rate": 9.922430510665806e-07,
2504
+ "loss": 0.0046,
2505
+ "step": 17650
2506
+ },
2507
+ {
2508
+ "epoch": 2.8603749191984487,
2509
+ "grad_norm": 0.04590355604887009,
2510
+ "learning_rate": 9.383753501400561e-07,
2511
+ "loss": 0.0041,
2512
+ "step": 17700
2513
+ },
2514
+ {
2515
+ "epoch": 2.8684550743374273,
2516
+ "grad_norm": 0.027806632220745087,
2517
+ "learning_rate": 8.845076492135317e-07,
2518
+ "loss": 0.0049,
2519
+ "step": 17750
2520
+ },
2521
+ {
2522
+ "epoch": 2.876535229476406,
2523
+ "grad_norm": 0.047230854630470276,
2524
+ "learning_rate": 8.306399482870072e-07,
2525
+ "loss": 0.0044,
2526
+ "step": 17800
2527
+ },
2528
+ {
2529
+ "epoch": 2.8846153846153846,
2530
+ "grad_norm": 0.023929964751005173,
2531
+ "learning_rate": 7.767722473604828e-07,
2532
+ "loss": 0.0041,
2533
+ "step": 17850
2534
+ },
2535
+ {
2536
+ "epoch": 2.892695539754363,
2537
+ "grad_norm": 0.01972135528922081,
2538
+ "learning_rate": 7.229045464339583e-07,
2539
+ "loss": 0.0038,
2540
+ "step": 17900
2541
+ },
2542
+ {
2543
+ "epoch": 2.900775694893342,
2544
+ "grad_norm": 0.06653473526239395,
2545
+ "learning_rate": 6.690368455074338e-07,
2546
+ "loss": 0.0043,
2547
+ "step": 17950
2548
+ },
2549
+ {
2550
+ "epoch": 2.9088558500323205,
2551
+ "grad_norm": 0.03229772299528122,
2552
+ "learning_rate": 6.151691445809093e-07,
2553
+ "loss": 0.0045,
2554
+ "step": 18000
2555
+ },
2556
+ {
2557
+ "epoch": 2.916936005171299,
2558
+ "grad_norm": 0.027306850999593735,
2559
+ "learning_rate": 5.613014436543849e-07,
2560
+ "loss": 0.0044,
2561
+ "step": 18050
2562
+ },
2563
+ {
2564
+ "epoch": 2.9250161603102782,
2565
+ "grad_norm": 0.04258955270051956,
2566
+ "learning_rate": 5.074337427278604e-07,
2567
+ "loss": 0.0044,
2568
+ "step": 18100
2569
+ },
2570
+ {
2571
+ "epoch": 2.933096315449257,
2572
+ "grad_norm": 0.05304836109280586,
2573
+ "learning_rate": 4.5356604180133593e-07,
2574
+ "loss": 0.0042,
2575
+ "step": 18150
2576
+ },
2577
+ {
2578
+ "epoch": 2.9411764705882355,
2579
+ "grad_norm": 0.03534824028611183,
2580
+ "learning_rate": 3.9969834087481147e-07,
2581
+ "loss": 0.0044,
2582
+ "step": 18200
2583
+ },
2584
+ {
2585
+ "epoch": 2.949256625727214,
2586
+ "grad_norm": 0.04045730456709862,
2587
+ "learning_rate": 3.4583063994828706e-07,
2588
+ "loss": 0.0046,
2589
+ "step": 18250
2590
+ },
2591
+ {
2592
+ "epoch": 2.957336780866193,
2593
+ "grad_norm": 0.022856054827570915,
2594
+ "learning_rate": 2.919629390217626e-07,
2595
+ "loss": 0.0046,
2596
+ "step": 18300
2597
+ },
2598
+ {
2599
+ "epoch": 2.9654169360051714,
2600
+ "grad_norm": 0.04489414766430855,
2601
+ "learning_rate": 2.3809523809523811e-07,
2602
+ "loss": 0.0041,
2603
+ "step": 18350
2604
+ },
2605
+ {
2606
+ "epoch": 2.97349709114415,
2607
+ "grad_norm": 0.022563565522432327,
2608
+ "learning_rate": 1.8422753716871365e-07,
2609
+ "loss": 0.0045,
2610
+ "step": 18400
2611
+ },
2612
+ {
2613
+ "epoch": 2.9815772462831287,
2614
+ "grad_norm": 0.05544481799006462,
2615
+ "learning_rate": 1.303598362421892e-07,
2616
+ "loss": 0.0042,
2617
+ "step": 18450
2618
+ },
2619
+ {
2620
+ "epoch": 2.9896574014221073,
2621
+ "grad_norm": 0.03954526409506798,
2622
+ "learning_rate": 7.649213531566473e-08,
2623
+ "loss": 0.0045,
2624
+ "step": 18500
2625
+ }
2626
+ ],
2627
+ "logging_steps": 50,
2628
+ "max_steps": 18564,
2629
+ "num_input_tokens_seen": 0,
2630
+ "num_train_epochs": 3,
2631
+ "save_steps": 500,
2632
+ "stateful_callbacks": {
2633
+ "TrainerControl": {
2634
+ "args": {
2635
+ "should_epoch_stop": false,
2636
+ "should_evaluate": false,
2637
+ "should_log": false,
2638
+ "should_save": true,
2639
+ "should_training_stop": false
2640
+ },
2641
+ "attributes": {}
2642
+ }
2643
+ },
2644
+ "total_flos": 9.012089613975552e+16,
2645
+ "train_batch_size": 8,
2646
+ "trial_name": null,
2647
+ "trial_params": null
2648
+ }
ptt5-cronosflow_ai_public/checkpoint-18500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34e93f42a27804d870f9882bcb1911bb1a6b24e02a2c5af6c116bbf06d3b37a
3
+ size 5905
ptt5-cronosflow_ai_public/checkpoint-18564/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.54.1",
29
+ "use_cache": true,
30
+ "vocab_size": 32128
31
+ }
ptt5-cronosflow_ai_public/checkpoint-18564/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.54.1"
6
+ }
ptt5-cronosflow_ai_public/checkpoint-18564/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9994e1a896341001e10534c4188235730aa16a0244427d1212089a330bba22e
3
+ size 891644712
ptt5-cronosflow_ai_public/checkpoint-18564/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef977d018533537c330b50c33247298d450b2eb3126191ebf9021b2c6764ee7
3
+ size 1783445259
ptt5-cronosflow_ai_public/checkpoint-18564/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7da957b93d2e435d937b2b7a9b9ad5830432916ea65a44c94bcb6a522bcbf3d
3
+ size 14645
ptt5-cronosflow_ai_public/checkpoint-18564/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70622a70617934774a1b6ee4c2e0ea2bf91ef731866a00f2d1930be375e9a7ac
3
+ size 1383
ptt5-cronosflow_ai_public/checkpoint-18564/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58db999b9b0a63e3770918c932752b83d1d8a6e87ca2325c64a249a13fa791a6
3
+ size 1465
ptt5-cronosflow_ai_public/checkpoint-18564/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
ptt5-cronosflow_ai_public/checkpoint-18564/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb25b1d67f04fce0e710d58430b606b4ee9887144fa2da22d123c44061cc62e
3
+ size 755569
ptt5-cronosflow_ai_public/checkpoint-18564/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ptt5-cronosflow_ai_public/checkpoint-18564/tokenizer_config.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": false,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "legacy": true,
936
+ "model_max_length": 1000000000000000019884624838656,
937
+ "pad_token": "<pad>",
938
+ "sp_model_kwargs": {},
939
+ "tokenizer_class": "T5Tokenizer",
940
+ "unk_token": "<unk>"
941
+ }
ptt5-cronosflow_ai_public/checkpoint-18564/trainer_state.json ADDED
@@ -0,0 +1,2655 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 18564,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00808015513897867,
14
+ "grad_norm": 40.89574432373047,
15
+ "learning_rate": 1.995151906916613e-05,
16
+ "loss": 25.8011,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.01616031027795734,
21
+ "grad_norm": 1.4409021139144897,
22
+ "learning_rate": 1.9897651368239605e-05,
23
+ "loss": 2.011,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.024240465416936006,
28
+ "grad_norm": 0.27292221784591675,
29
+ "learning_rate": 1.9843783667313083e-05,
30
+ "loss": 0.1682,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.03232062055591468,
35
+ "grad_norm": 0.21620342135429382,
36
+ "learning_rate": 1.9789915966386557e-05,
37
+ "loss": 0.1127,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.040400775694893344,
42
+ "grad_norm": 0.19684338569641113,
43
+ "learning_rate": 1.9736048265460034e-05,
44
+ "loss": 0.0924,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.04848093083387201,
49
+ "grad_norm": 0.21188506484031677,
50
+ "learning_rate": 1.9682180564533505e-05,
51
+ "loss": 0.0768,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.05656108597285068,
56
+ "grad_norm": 0.16330359876155853,
57
+ "learning_rate": 1.9628312863606982e-05,
58
+ "loss": 0.0596,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.06464124111182935,
63
+ "grad_norm": 0.12760096788406372,
64
+ "learning_rate": 1.9574445162680457e-05,
65
+ "loss": 0.0491,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.07272139625080802,
70
+ "grad_norm": 0.16558507084846497,
71
+ "learning_rate": 1.9520577461753934e-05,
72
+ "loss": 0.0424,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.08080155138978669,
77
+ "grad_norm": 0.1511087417602539,
78
+ "learning_rate": 1.9466709760827408e-05,
79
+ "loss": 0.0376,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.08888170652876536,
84
+ "grad_norm": 0.09860303997993469,
85
+ "learning_rate": 1.9412842059900886e-05,
86
+ "loss": 0.0333,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.09696186166774402,
91
+ "grad_norm": 0.1415504515171051,
92
+ "learning_rate": 1.935897435897436e-05,
93
+ "loss": 0.0299,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.10504201680672269,
98
+ "grad_norm": 0.12042852491140366,
99
+ "learning_rate": 1.9305106658047837e-05,
100
+ "loss": 0.0298,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.11312217194570136,
105
+ "grad_norm": 0.14820343255996704,
106
+ "learning_rate": 1.925123895712131e-05,
107
+ "loss": 0.0297,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.12120232708468003,
112
+ "grad_norm": 0.11845523118972778,
113
+ "learning_rate": 1.919737125619479e-05,
114
+ "loss": 0.024,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.1292824822236587,
119
+ "grad_norm": 0.13682147860527039,
120
+ "learning_rate": 1.9143503555268263e-05,
121
+ "loss": 0.024,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.13736263736263737,
126
+ "grad_norm": 0.07670263946056366,
127
+ "learning_rate": 1.908963585434174e-05,
128
+ "loss": 0.0216,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.14544279250161604,
133
+ "grad_norm": 0.10427036881446838,
134
+ "learning_rate": 1.903576815341521e-05,
135
+ "loss": 0.0229,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.1535229476405947,
140
+ "grad_norm": 0.14853981137275696,
141
+ "learning_rate": 1.898190045248869e-05,
142
+ "loss": 0.0204,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.16160310277957338,
147
+ "grad_norm": 0.08788396418094635,
148
+ "learning_rate": 1.8928032751562163e-05,
149
+ "loss": 0.0201,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.16968325791855204,
154
+ "grad_norm": 0.1365722268819809,
155
+ "learning_rate": 1.887416505063564e-05,
156
+ "loss": 0.019,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.1777634130575307,
161
+ "grad_norm": 0.133611798286438,
162
+ "learning_rate": 1.8820297349709114e-05,
163
+ "loss": 0.0212,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.18584356819650938,
168
+ "grad_norm": 0.09723819047212601,
169
+ "learning_rate": 1.8766429648782592e-05,
170
+ "loss": 0.0169,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.19392372333548805,
175
+ "grad_norm": 0.11186394095420837,
176
+ "learning_rate": 1.8712561947856066e-05,
177
+ "loss": 0.0178,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.2020038784744667,
182
+ "grad_norm": 0.10648094117641449,
183
+ "learning_rate": 1.8658694246929544e-05,
184
+ "loss": 0.0172,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.21008403361344538,
189
+ "grad_norm": 0.10959897935390472,
190
+ "learning_rate": 1.8604826546003018e-05,
191
+ "loss": 0.0178,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.21816418875242405,
196
+ "grad_norm": 0.09298472851514816,
197
+ "learning_rate": 1.8550958845076495e-05,
198
+ "loss": 0.0154,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.22624434389140272,
203
+ "grad_norm": 0.08410840481519699,
204
+ "learning_rate": 1.849709114414997e-05,
205
+ "loss": 0.0162,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.23432449903038138,
210
+ "grad_norm": 0.15365834534168243,
211
+ "learning_rate": 1.8443223443223447e-05,
212
+ "loss": 0.0148,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.24240465416936005,
217
+ "grad_norm": 0.09604126960039139,
218
+ "learning_rate": 1.838935574229692e-05,
219
+ "loss": 0.0146,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.2504848093083387,
224
+ "grad_norm": 0.06805470585823059,
225
+ "learning_rate": 1.8335488041370395e-05,
226
+ "loss": 0.0162,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.2585649644473174,
231
+ "grad_norm": 0.11596197634935379,
232
+ "learning_rate": 1.8281620340443872e-05,
233
+ "loss": 0.0112,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.26664511958629605,
238
+ "grad_norm": 0.08166597783565521,
239
+ "learning_rate": 1.8227752639517347e-05,
240
+ "loss": 0.0136,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.27472527472527475,
245
+ "grad_norm": 0.08969355374574661,
246
+ "learning_rate": 1.817388493859082e-05,
247
+ "loss": 0.0132,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.2828054298642534,
252
+ "grad_norm": 0.0873119905591011,
253
+ "learning_rate": 1.8120017237664298e-05,
254
+ "loss": 0.0129,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.2908855850032321,
259
+ "grad_norm": 0.10579364001750946,
260
+ "learning_rate": 1.8066149536737772e-05,
261
+ "loss": 0.0123,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.2989657401422107,
266
+ "grad_norm": 0.12571881711483002,
267
+ "learning_rate": 1.801228183581125e-05,
268
+ "loss": 0.0128,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.3070458952811894,
273
+ "grad_norm": 0.08085139840841293,
274
+ "learning_rate": 1.7958414134884724e-05,
275
+ "loss": 0.0121,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.31512605042016806,
280
+ "grad_norm": 0.06765197962522507,
281
+ "learning_rate": 1.79045464339582e-05,
282
+ "loss": 0.0103,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.32320620555914675,
287
+ "grad_norm": 0.07517407834529877,
288
+ "learning_rate": 1.7850678733031676e-05,
289
+ "loss": 0.0107,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.3312863606981254,
294
+ "grad_norm": 0.060215964913368225,
295
+ "learning_rate": 1.779681103210515e-05,
296
+ "loss": 0.0123,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.3393665158371041,
301
+ "grad_norm": 0.08518676459789276,
302
+ "learning_rate": 1.7742943331178627e-05,
303
+ "loss": 0.0107,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.3474466709760827,
308
+ "grad_norm": 0.05002804845571518,
309
+ "learning_rate": 1.76890756302521e-05,
310
+ "loss": 0.0108,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.3555268261150614,
315
+ "grad_norm": 0.042444173246622086,
316
+ "learning_rate": 1.763520792932558e-05,
317
+ "loss": 0.01,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.36360698125404006,
322
+ "grad_norm": 0.07093804329633713,
323
+ "learning_rate": 1.7581340228399053e-05,
324
+ "loss": 0.0113,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.37168713639301876,
329
+ "grad_norm": 0.059032320976257324,
330
+ "learning_rate": 1.752747252747253e-05,
331
+ "loss": 0.011,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.3797672915319974,
336
+ "grad_norm": 0.05217365920543671,
337
+ "learning_rate": 1.7473604826546004e-05,
338
+ "loss": 0.0097,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.3878474466709761,
343
+ "grad_norm": 0.12220600247383118,
344
+ "learning_rate": 1.7419737125619482e-05,
345
+ "loss": 0.01,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.39592760180995473,
350
+ "grad_norm": 0.09106040000915527,
351
+ "learning_rate": 1.7365869424692956e-05,
352
+ "loss": 0.0117,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.4040077569489334,
357
+ "grad_norm": 0.09308184683322906,
358
+ "learning_rate": 1.731200172376643e-05,
359
+ "loss": 0.01,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.41208791208791207,
364
+ "grad_norm": 0.08041771501302719,
365
+ "learning_rate": 1.7258134022839908e-05,
366
+ "loss": 0.0112,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.42016806722689076,
371
+ "grad_norm": 0.05206672102212906,
372
+ "learning_rate": 1.7204266321913382e-05,
373
+ "loss": 0.0103,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.4282482223658694,
378
+ "grad_norm": 0.0851343497633934,
379
+ "learning_rate": 1.7150398620986856e-05,
380
+ "loss": 0.0093,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.4363283775048481,
385
+ "grad_norm": 0.08132291585206985,
386
+ "learning_rate": 1.7096530920060333e-05,
387
+ "loss": 0.0118,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.44440853264382674,
392
+ "grad_norm": 0.06463415920734406,
393
+ "learning_rate": 1.7042663219133807e-05,
394
+ "loss": 0.0106,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.45248868778280543,
399
+ "grad_norm": 0.08292311429977417,
400
+ "learning_rate": 1.6988795518207285e-05,
401
+ "loss": 0.0097,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.46056884292178407,
406
+ "grad_norm": 0.10132889449596405,
407
+ "learning_rate": 1.693492781728076e-05,
408
+ "loss": 0.009,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.46864899806076277,
413
+ "grad_norm": 0.06622787564992905,
414
+ "learning_rate": 1.6881060116354237e-05,
415
+ "loss": 0.0092,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.47672915319974146,
420
+ "grad_norm": 0.055822569876909256,
421
+ "learning_rate": 1.682719241542771e-05,
422
+ "loss": 0.0088,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.4848093083387201,
427
+ "grad_norm": 0.04172702878713608,
428
+ "learning_rate": 1.6773324714501188e-05,
429
+ "loss": 0.0081,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.4928894634776988,
434
+ "grad_norm": 0.08130078762769699,
435
+ "learning_rate": 1.6719457013574662e-05,
436
+ "loss": 0.0085,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.5009696186166774,
441
+ "grad_norm": 0.048671796917915344,
442
+ "learning_rate": 1.666558931264814e-05,
443
+ "loss": 0.0079,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.5090497737556561,
448
+ "grad_norm": 0.12270870059728622,
449
+ "learning_rate": 1.6611721611721614e-05,
450
+ "loss": 0.0084,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.5171299288946348,
455
+ "grad_norm": 0.053976595401763916,
456
+ "learning_rate": 1.6557853910795088e-05,
457
+ "loss": 0.0095,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.5252100840336135,
462
+ "grad_norm": 0.09643538296222687,
463
+ "learning_rate": 1.6503986209868562e-05,
464
+ "loss": 0.0086,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.5332902391725921,
469
+ "grad_norm": 0.04082519933581352,
470
+ "learning_rate": 1.645011850894204e-05,
471
+ "loss": 0.0085,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.5413703943115707,
476
+ "grad_norm": 0.07320540398359299,
477
+ "learning_rate": 1.6396250808015514e-05,
478
+ "loss": 0.0095,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.5494505494505495,
483
+ "grad_norm": 0.08433382958173752,
484
+ "learning_rate": 1.634238310708899e-05,
485
+ "loss": 0.0086,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.5575307045895281,
490
+ "grad_norm": 0.08490192890167236,
491
+ "learning_rate": 1.6288515406162465e-05,
492
+ "loss": 0.0087,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.5656108597285068,
497
+ "grad_norm": 0.07407897710800171,
498
+ "learning_rate": 1.6234647705235943e-05,
499
+ "loss": 0.0095,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.5736910148674854,
504
+ "grad_norm": 0.04006027430295944,
505
+ "learning_rate": 1.6180780004309417e-05,
506
+ "loss": 0.0085,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.5817711700064642,
511
+ "grad_norm": 0.10100733488798141,
512
+ "learning_rate": 1.6126912303382894e-05,
513
+ "loss": 0.0082,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.5898513251454428,
518
+ "grad_norm": 0.046667344868183136,
519
+ "learning_rate": 1.607304460245637e-05,
520
+ "loss": 0.0088,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.5979314802844214,
525
+ "grad_norm": 0.07386622577905655,
526
+ "learning_rate": 1.6019176901529846e-05,
527
+ "loss": 0.0097,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.6060116354234001,
532
+ "grad_norm": 0.07727360725402832,
533
+ "learning_rate": 1.596530920060332e-05,
534
+ "loss": 0.0078,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.6140917905623788,
539
+ "grad_norm": 0.01824168674647808,
540
+ "learning_rate": 1.5911441499676794e-05,
541
+ "loss": 0.0082,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.6221719457013575,
546
+ "grad_norm": 0.02981133572757244,
547
+ "learning_rate": 1.585757379875027e-05,
548
+ "loss": 0.0077,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.6302521008403361,
553
+ "grad_norm": 0.07947336137294769,
554
+ "learning_rate": 1.5803706097823746e-05,
555
+ "loss": 0.0073,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.6383322559793148,
560
+ "grad_norm": 0.04702315106987953,
561
+ "learning_rate": 1.574983839689722e-05,
562
+ "loss": 0.0074,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.6464124111182935,
567
+ "grad_norm": 0.0397706963121891,
568
+ "learning_rate": 1.5695970695970697e-05,
569
+ "loss": 0.0085,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 0.6544925662572721,
574
+ "grad_norm": 0.0445311963558197,
575
+ "learning_rate": 1.564210299504417e-05,
576
+ "loss": 0.0071,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 0.6625727213962508,
581
+ "grad_norm": 0.03868868947029114,
582
+ "learning_rate": 1.558823529411765e-05,
583
+ "loss": 0.0071,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 0.6706528765352294,
588
+ "grad_norm": 0.09177325665950775,
589
+ "learning_rate": 1.5534367593191123e-05,
590
+ "loss": 0.0078,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 0.6787330316742082,
595
+ "grad_norm": 0.05718887969851494,
596
+ "learning_rate": 1.54804998922646e-05,
597
+ "loss": 0.008,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 0.6868131868131868,
602
+ "grad_norm": 0.04949459806084633,
603
+ "learning_rate": 1.5426632191338075e-05,
604
+ "loss": 0.0073,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 0.6948933419521655,
609
+ "grad_norm": 0.04109389707446098,
610
+ "learning_rate": 1.5372764490411552e-05,
611
+ "loss": 0.0073,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 0.7029734970911441,
616
+ "grad_norm": 0.07063832134008408,
617
+ "learning_rate": 1.5318896789485026e-05,
618
+ "loss": 0.0083,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 0.7110536522301228,
623
+ "grad_norm": 0.07452435046434402,
624
+ "learning_rate": 1.52650290885585e-05,
625
+ "loss": 0.0073,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 0.7191338073691015,
630
+ "grad_norm": 0.04412061721086502,
631
+ "learning_rate": 1.5211161387631976e-05,
632
+ "loss": 0.0067,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 0.7272139625080801,
637
+ "grad_norm": 0.07454030215740204,
638
+ "learning_rate": 1.5157293686705452e-05,
639
+ "loss": 0.0075,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 0.7352941176470589,
644
+ "grad_norm": 0.04662289470434189,
645
+ "learning_rate": 1.5103425985778928e-05,
646
+ "loss": 0.0074,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 0.7433742727860375,
651
+ "grad_norm": 0.05991057679057121,
652
+ "learning_rate": 1.5049558284852404e-05,
653
+ "loss": 0.0071,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 0.7514544279250162,
658
+ "grad_norm": 0.04592648521065712,
659
+ "learning_rate": 1.499569058392588e-05,
660
+ "loss": 0.0076,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 0.7595345830639948,
665
+ "grad_norm": 0.06309536099433899,
666
+ "learning_rate": 1.4941822882999355e-05,
667
+ "loss": 0.0076,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 0.7676147382029735,
672
+ "grad_norm": 0.05248362198472023,
673
+ "learning_rate": 1.4887955182072831e-05,
674
+ "loss": 0.0075,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 0.7756948933419522,
679
+ "grad_norm": 0.04493599757552147,
680
+ "learning_rate": 1.4834087481146307e-05,
681
+ "loss": 0.007,
682
+ "step": 4800
683
+ },
684
+ {
685
+ "epoch": 0.7837750484809308,
686
+ "grad_norm": 0.020138224586844444,
687
+ "learning_rate": 1.4780219780219783e-05,
688
+ "loss": 0.0063,
689
+ "step": 4850
690
+ },
691
+ {
692
+ "epoch": 0.7918552036199095,
693
+ "grad_norm": 0.073582723736763,
694
+ "learning_rate": 1.4726352079293259e-05,
695
+ "loss": 0.0063,
696
+ "step": 4900
697
+ },
698
+ {
699
+ "epoch": 0.7999353587588882,
700
+ "grad_norm": 0.050810813903808594,
701
+ "learning_rate": 1.4672484378366731e-05,
702
+ "loss": 0.0079,
703
+ "step": 4950
704
+ },
705
+ {
706
+ "epoch": 0.8080155138978669,
707
+ "grad_norm": 0.09147041290998459,
708
+ "learning_rate": 1.4618616677440207e-05,
709
+ "loss": 0.007,
710
+ "step": 5000
711
+ },
712
+ {
713
+ "epoch": 0.8160956690368455,
714
+ "grad_norm": 0.02943544089794159,
715
+ "learning_rate": 1.4564748976513683e-05,
716
+ "loss": 0.0064,
717
+ "step": 5050
718
+ },
719
+ {
720
+ "epoch": 0.8241758241758241,
721
+ "grad_norm": 0.058280181139707565,
722
+ "learning_rate": 1.4510881275587158e-05,
723
+ "loss": 0.0063,
724
+ "step": 5100
725
+ },
726
+ {
727
+ "epoch": 0.8322559793148029,
728
+ "grad_norm": 0.05846063792705536,
729
+ "learning_rate": 1.4457013574660634e-05,
730
+ "loss": 0.0071,
731
+ "step": 5150
732
+ },
733
+ {
734
+ "epoch": 0.8403361344537815,
735
+ "grad_norm": 0.08794039487838745,
736
+ "learning_rate": 1.440314587373411e-05,
737
+ "loss": 0.0066,
738
+ "step": 5200
739
+ },
740
+ {
741
+ "epoch": 0.8484162895927602,
742
+ "grad_norm": 0.05881703272461891,
743
+ "learning_rate": 1.4349278172807586e-05,
744
+ "loss": 0.0075,
745
+ "step": 5250
746
+ },
747
+ {
748
+ "epoch": 0.8564964447317388,
749
+ "grad_norm": 0.060504719614982605,
750
+ "learning_rate": 1.4295410471881062e-05,
751
+ "loss": 0.0061,
752
+ "step": 5300
753
+ },
754
+ {
755
+ "epoch": 0.8645765998707176,
756
+ "grad_norm": 0.04584150016307831,
757
+ "learning_rate": 1.4241542770954537e-05,
758
+ "loss": 0.0059,
759
+ "step": 5350
760
+ },
761
+ {
762
+ "epoch": 0.8726567550096962,
763
+ "grad_norm": 0.0818849429488182,
764
+ "learning_rate": 1.4187675070028013e-05,
765
+ "loss": 0.0067,
766
+ "step": 5400
767
+ },
768
+ {
769
+ "epoch": 0.8807369101486748,
770
+ "grad_norm": 0.04742725193500519,
771
+ "learning_rate": 1.4133807369101489e-05,
772
+ "loss": 0.0066,
773
+ "step": 5450
774
+ },
775
+ {
776
+ "epoch": 0.8888170652876535,
777
+ "grad_norm": 0.06628070026636124,
778
+ "learning_rate": 1.4079939668174965e-05,
779
+ "loss": 0.0069,
780
+ "step": 5500
781
+ },
782
+ {
783
+ "epoch": 0.8968972204266322,
784
+ "grad_norm": 0.0498398132622242,
785
+ "learning_rate": 1.4026071967248437e-05,
786
+ "loss": 0.006,
787
+ "step": 5550
788
+ },
789
+ {
790
+ "epoch": 0.9049773755656109,
791
+ "grad_norm": 0.07333686202764511,
792
+ "learning_rate": 1.3972204266321913e-05,
793
+ "loss": 0.0073,
794
+ "step": 5600
795
+ },
796
+ {
797
+ "epoch": 0.9130575307045895,
798
+ "grad_norm": 0.040425509214401245,
799
+ "learning_rate": 1.3918336565395389e-05,
800
+ "loss": 0.0061,
801
+ "step": 5650
802
+ },
803
+ {
804
+ "epoch": 0.9211376858435681,
805
+ "grad_norm": 0.04927436634898186,
806
+ "learning_rate": 1.3864468864468865e-05,
807
+ "loss": 0.0064,
808
+ "step": 5700
809
+ },
810
+ {
811
+ "epoch": 0.9292178409825469,
812
+ "grad_norm": 0.07403150945901871,
813
+ "learning_rate": 1.381060116354234e-05,
814
+ "loss": 0.0057,
815
+ "step": 5750
816
+ },
817
+ {
818
+ "epoch": 0.9372979961215255,
819
+ "grad_norm": 0.0294960867613554,
820
+ "learning_rate": 1.3756733462615816e-05,
821
+ "loss": 0.0057,
822
+ "step": 5800
823
+ },
824
+ {
825
+ "epoch": 0.9453781512605042,
826
+ "grad_norm": 0.06763947010040283,
827
+ "learning_rate": 1.3702865761689292e-05,
828
+ "loss": 0.0061,
829
+ "step": 5850
830
+ },
831
+ {
832
+ "epoch": 0.9534583063994829,
833
+ "grad_norm": 0.034876059740781784,
834
+ "learning_rate": 1.3648998060762768e-05,
835
+ "loss": 0.0073,
836
+ "step": 5900
837
+ },
838
+ {
839
+ "epoch": 0.9615384615384616,
840
+ "grad_norm": 0.0363958366215229,
841
+ "learning_rate": 1.3595130359836244e-05,
842
+ "loss": 0.0065,
843
+ "step": 5950
844
+ },
845
+ {
846
+ "epoch": 0.9696186166774402,
847
+ "grad_norm": 0.03505223989486694,
848
+ "learning_rate": 1.354126265890972e-05,
849
+ "loss": 0.0065,
850
+ "step": 6000
851
+ },
852
+ {
853
+ "epoch": 0.9776987718164188,
854
+ "grad_norm": 0.010415361262857914,
855
+ "learning_rate": 1.3487394957983195e-05,
856
+ "loss": 0.0063,
857
+ "step": 6050
858
+ },
859
+ {
860
+ "epoch": 0.9857789269553976,
861
+ "grad_norm": 0.05905304104089737,
862
+ "learning_rate": 1.343352725705667e-05,
863
+ "loss": 0.0055,
864
+ "step": 6100
865
+ },
866
+ {
867
+ "epoch": 0.9938590820943762,
868
+ "grad_norm": 0.03133542463183403,
869
+ "learning_rate": 1.3379659556130145e-05,
870
+ "loss": 0.0062,
871
+ "step": 6150
872
+ },
873
+ {
874
+ "epoch": 1.0,
875
+ "eval_loss": 0.00468644080683589,
876
+ "eval_rouge1": 86.16729085635436,
877
+ "eval_rouge2": 82.00613853575325,
878
+ "eval_rougeL": 85.17049406119979,
879
+ "eval_rougeLsum": 85.1321983661705,
880
+ "eval_runtime": 50.3158,
881
+ "eval_samples_per_second": 9.937,
882
+ "eval_steps_per_second": 1.252,
883
+ "step": 6188
884
+ },
885
+ {
886
+ "epoch": 1.0019392372333549,
887
+ "grad_norm": 0.0473632887005806,
888
+ "learning_rate": 1.3325791855203621e-05,
889
+ "loss": 0.006,
890
+ "step": 6200
891
+ },
892
+ {
893
+ "epoch": 1.0100193923723335,
894
+ "grad_norm": 0.009613406844437122,
895
+ "learning_rate": 1.3271924154277097e-05,
896
+ "loss": 0.0058,
897
+ "step": 6250
898
+ },
899
+ {
900
+ "epoch": 1.0180995475113122,
901
+ "grad_norm": 0.07586677372455597,
902
+ "learning_rate": 1.3218056453350573e-05,
903
+ "loss": 0.0053,
904
+ "step": 6300
905
+ },
906
+ {
907
+ "epoch": 1.0261797026502908,
908
+ "grad_norm": 0.03996267169713974,
909
+ "learning_rate": 1.3165266106442578e-05,
910
+ "loss": 0.0053,
911
+ "step": 6350
912
+ },
913
+ {
914
+ "epoch": 1.0342598577892697,
915
+ "grad_norm": 0.04150750860571861,
916
+ "learning_rate": 1.3111398405516054e-05,
917
+ "loss": 0.006,
918
+ "step": 6400
919
+ },
920
+ {
921
+ "epoch": 1.0423400129282483,
922
+ "grad_norm": 0.047103989869356155,
923
+ "learning_rate": 1.305753070458953e-05,
924
+ "loss": 0.0063,
925
+ "step": 6450
926
+ },
927
+ {
928
+ "epoch": 1.050420168067227,
929
+ "grad_norm": 0.04707568511366844,
930
+ "learning_rate": 1.3003663003663005e-05,
931
+ "loss": 0.0054,
932
+ "step": 6500
933
+ },
934
+ {
935
+ "epoch": 1.0585003232062056,
936
+ "grad_norm": 0.04693872109055519,
937
+ "learning_rate": 1.2949795302736481e-05,
938
+ "loss": 0.0058,
939
+ "step": 6550
940
+ },
941
+ {
942
+ "epoch": 1.0665804783451842,
943
+ "grad_norm": 0.03767074644565582,
944
+ "learning_rate": 1.2895927601809957e-05,
945
+ "loss": 0.0049,
946
+ "step": 6600
947
+ },
948
+ {
949
+ "epoch": 1.0746606334841629,
950
+ "grad_norm": 0.049506109207868576,
951
+ "learning_rate": 1.2842059900883433e-05,
952
+ "loss": 0.0061,
953
+ "step": 6650
954
+ },
955
+ {
956
+ "epoch": 1.0827407886231415,
957
+ "grad_norm": 0.040579311549663544,
958
+ "learning_rate": 1.2788192199956907e-05,
959
+ "loss": 0.0053,
960
+ "step": 6700
961
+ },
962
+ {
963
+ "epoch": 1.0908209437621201,
964
+ "grad_norm": 0.06605598330497742,
965
+ "learning_rate": 1.273432449903038e-05,
966
+ "loss": 0.0049,
967
+ "step": 6750
968
+ },
969
+ {
970
+ "epoch": 1.098901098901099,
971
+ "grad_norm": 0.0573626309633255,
972
+ "learning_rate": 1.2680456798103857e-05,
973
+ "loss": 0.0058,
974
+ "step": 6800
975
+ },
976
+ {
977
+ "epoch": 1.1069812540400776,
978
+ "grad_norm": 0.04869833588600159,
979
+ "learning_rate": 1.2626589097177332e-05,
980
+ "loss": 0.0054,
981
+ "step": 6850
982
+ },
983
+ {
984
+ "epoch": 1.1150614091790563,
985
+ "grad_norm": 0.030207501724362373,
986
+ "learning_rate": 1.2572721396250808e-05,
987
+ "loss": 0.0049,
988
+ "step": 6900
989
+ },
990
+ {
991
+ "epoch": 1.123141564318035,
992
+ "grad_norm": 0.04019474983215332,
993
+ "learning_rate": 1.2518853695324284e-05,
994
+ "loss": 0.0054,
995
+ "step": 6950
996
+ },
997
+ {
998
+ "epoch": 1.1312217194570136,
999
+ "grad_norm": 0.03316131606698036,
1000
+ "learning_rate": 1.246498599439776e-05,
1001
+ "loss": 0.0063,
1002
+ "step": 7000
1003
+ },
1004
+ {
1005
+ "epoch": 1.1393018745959922,
1006
+ "grad_norm": 0.04495147988200188,
1007
+ "learning_rate": 1.2411118293471236e-05,
1008
+ "loss": 0.006,
1009
+ "step": 7050
1010
+ },
1011
+ {
1012
+ "epoch": 1.1473820297349708,
1013
+ "grad_norm": 0.029968004673719406,
1014
+ "learning_rate": 1.2357250592544711e-05,
1015
+ "loss": 0.0055,
1016
+ "step": 7100
1017
+ },
1018
+ {
1019
+ "epoch": 1.1554621848739495,
1020
+ "grad_norm": 0.05552554875612259,
1021
+ "learning_rate": 1.2303382891618187e-05,
1022
+ "loss": 0.0056,
1023
+ "step": 7150
1024
+ },
1025
+ {
1026
+ "epoch": 1.1635423400129283,
1027
+ "grad_norm": 0.040211454033851624,
1028
+ "learning_rate": 1.2249515190691663e-05,
1029
+ "loss": 0.0059,
1030
+ "step": 7200
1031
+ },
1032
+ {
1033
+ "epoch": 1.171622495151907,
1034
+ "grad_norm": 0.030323076993227005,
1035
+ "learning_rate": 1.2195647489765139e-05,
1036
+ "loss": 0.0057,
1037
+ "step": 7250
1038
+ },
1039
+ {
1040
+ "epoch": 1.1797026502908856,
1041
+ "grad_norm": 0.040990181267261505,
1042
+ "learning_rate": 1.2141779788838613e-05,
1043
+ "loss": 0.0053,
1044
+ "step": 7300
1045
+ },
1046
+ {
1047
+ "epoch": 1.1877828054298643,
1048
+ "grad_norm": 0.03895975649356842,
1049
+ "learning_rate": 1.2087912087912089e-05,
1050
+ "loss": 0.0054,
1051
+ "step": 7350
1052
+ },
1053
+ {
1054
+ "epoch": 1.195862960568843,
1055
+ "grad_norm": 0.04454527050256729,
1056
+ "learning_rate": 1.2034044386985565e-05,
1057
+ "loss": 0.0053,
1058
+ "step": 7400
1059
+ },
1060
+ {
1061
+ "epoch": 1.2039431157078215,
1062
+ "grad_norm": 0.04071690887212753,
1063
+ "learning_rate": 1.198017668605904e-05,
1064
+ "loss": 0.0053,
1065
+ "step": 7450
1066
+ },
1067
+ {
1068
+ "epoch": 1.2120232708468002,
1069
+ "grad_norm": 0.03768669813871384,
1070
+ "learning_rate": 1.1926308985132516e-05,
1071
+ "loss": 0.0059,
1072
+ "step": 7500
1073
+ },
1074
+ {
1075
+ "epoch": 1.220103425985779,
1076
+ "grad_norm": 0.048281479626894,
1077
+ "learning_rate": 1.187244128420599e-05,
1078
+ "loss": 0.0057,
1079
+ "step": 7550
1080
+ },
1081
+ {
1082
+ "epoch": 1.2281835811247577,
1083
+ "grad_norm": 0.037021659314632416,
1084
+ "learning_rate": 1.1818573583279466e-05,
1085
+ "loss": 0.0059,
1086
+ "step": 7600
1087
+ },
1088
+ {
1089
+ "epoch": 1.2362637362637363,
1090
+ "grad_norm": 0.060549281537532806,
1091
+ "learning_rate": 1.1764705882352942e-05,
1092
+ "loss": 0.0054,
1093
+ "step": 7650
1094
+ },
1095
+ {
1096
+ "epoch": 1.244343891402715,
1097
+ "grad_norm": 0.06345050781965256,
1098
+ "learning_rate": 1.1710838181426418e-05,
1099
+ "loss": 0.0057,
1100
+ "step": 7700
1101
+ },
1102
+ {
1103
+ "epoch": 1.2524240465416936,
1104
+ "grad_norm": 0.03186087682843208,
1105
+ "learning_rate": 1.1656970480499893e-05,
1106
+ "loss": 0.0055,
1107
+ "step": 7750
1108
+ },
1109
+ {
1110
+ "epoch": 1.2605042016806722,
1111
+ "grad_norm": 0.057463087141513824,
1112
+ "learning_rate": 1.160310277957337e-05,
1113
+ "loss": 0.0057,
1114
+ "step": 7800
1115
+ },
1116
+ {
1117
+ "epoch": 1.2685843568196509,
1118
+ "grad_norm": 0.04167677462100983,
1119
+ "learning_rate": 1.1549235078646843e-05,
1120
+ "loss": 0.0056,
1121
+ "step": 7850
1122
+ },
1123
+ {
1124
+ "epoch": 1.2766645119586295,
1125
+ "grad_norm": 0.04780175909399986,
1126
+ "learning_rate": 1.149536737772032e-05,
1127
+ "loss": 0.0056,
1128
+ "step": 7900
1129
+ },
1130
+ {
1131
+ "epoch": 1.2847446670976082,
1132
+ "grad_norm": 0.06335488706827164,
1133
+ "learning_rate": 1.1441499676793795e-05,
1134
+ "loss": 0.0055,
1135
+ "step": 7950
1136
+ },
1137
+ {
1138
+ "epoch": 1.292824822236587,
1139
+ "grad_norm": 0.04902550205588341,
1140
+ "learning_rate": 1.138763197586727e-05,
1141
+ "loss": 0.0062,
1142
+ "step": 8000
1143
+ },
1144
+ {
1145
+ "epoch": 1.3009049773755657,
1146
+ "grad_norm": 0.0339086689054966,
1147
+ "learning_rate": 1.1333764274940747e-05,
1148
+ "loss": 0.0049,
1149
+ "step": 8050
1150
+ },
1151
+ {
1152
+ "epoch": 1.3089851325145443,
1153
+ "grad_norm": 0.044165465980768204,
1154
+ "learning_rate": 1.1279896574014222e-05,
1155
+ "loss": 0.0058,
1156
+ "step": 8100
1157
+ },
1158
+ {
1159
+ "epoch": 1.317065287653523,
1160
+ "grad_norm": 0.037159230560064316,
1161
+ "learning_rate": 1.1226028873087698e-05,
1162
+ "loss": 0.0053,
1163
+ "step": 8150
1164
+ },
1165
+ {
1166
+ "epoch": 1.3251454427925016,
1167
+ "grad_norm": 0.03820132464170456,
1168
+ "learning_rate": 1.1172161172161174e-05,
1169
+ "loss": 0.0053,
1170
+ "step": 8200
1171
+ },
1172
+ {
1173
+ "epoch": 1.3332255979314802,
1174
+ "grad_norm": 0.024112703278660774,
1175
+ "learning_rate": 1.111829347123465e-05,
1176
+ "loss": 0.0054,
1177
+ "step": 8250
1178
+ },
1179
+ {
1180
+ "epoch": 1.341305753070459,
1181
+ "grad_norm": 0.029049362987279892,
1182
+ "learning_rate": 1.1064425770308126e-05,
1183
+ "loss": 0.005,
1184
+ "step": 8300
1185
+ },
1186
+ {
1187
+ "epoch": 1.3493859082094377,
1188
+ "grad_norm": 0.0295393168926239,
1189
+ "learning_rate": 1.1010558069381601e-05,
1190
+ "loss": 0.0053,
1191
+ "step": 8350
1192
+ },
1193
+ {
1194
+ "epoch": 1.3574660633484164,
1195
+ "grad_norm": 0.04328558221459389,
1196
+ "learning_rate": 1.0956690368455075e-05,
1197
+ "loss": 0.005,
1198
+ "step": 8400
1199
+ },
1200
+ {
1201
+ "epoch": 1.365546218487395,
1202
+ "grad_norm": 0.058262139558792114,
1203
+ "learning_rate": 1.090282266752855e-05,
1204
+ "loss": 0.0053,
1205
+ "step": 8450
1206
+ },
1207
+ {
1208
+ "epoch": 1.3736263736263736,
1209
+ "grad_norm": 0.033369556069374084,
1210
+ "learning_rate": 1.0848954966602025e-05,
1211
+ "loss": 0.0058,
1212
+ "step": 8500
1213
+ },
1214
+ {
1215
+ "epoch": 1.3817065287653523,
1216
+ "grad_norm": 0.07817134261131287,
1217
+ "learning_rate": 1.0795087265675501e-05,
1218
+ "loss": 0.0053,
1219
+ "step": 8550
1220
+ },
1221
+ {
1222
+ "epoch": 1.389786683904331,
1223
+ "grad_norm": 0.0364365428686142,
1224
+ "learning_rate": 1.0741219564748977e-05,
1225
+ "loss": 0.0049,
1226
+ "step": 8600
1227
+ },
1228
+ {
1229
+ "epoch": 1.3978668390433096,
1230
+ "grad_norm": 0.047975849360227585,
1231
+ "learning_rate": 1.0687351863822453e-05,
1232
+ "loss": 0.0054,
1233
+ "step": 8650
1234
+ },
1235
+ {
1236
+ "epoch": 1.4059469941822882,
1237
+ "grad_norm": 0.05053960904479027,
1238
+ "learning_rate": 1.0633484162895929e-05,
1239
+ "loss": 0.0049,
1240
+ "step": 8700
1241
+ },
1242
+ {
1243
+ "epoch": 1.4140271493212668,
1244
+ "grad_norm": 0.05517440661787987,
1245
+ "learning_rate": 1.0579616461969404e-05,
1246
+ "loss": 0.0053,
1247
+ "step": 8750
1248
+ },
1249
+ {
1250
+ "epoch": 1.4221073044602457,
1251
+ "grad_norm": 0.045634444802999496,
1252
+ "learning_rate": 1.052574876104288e-05,
1253
+ "loss": 0.0051,
1254
+ "step": 8800
1255
+ },
1256
+ {
1257
+ "epoch": 1.4301874595992243,
1258
+ "grad_norm": 0.06119120493531227,
1259
+ "learning_rate": 1.0471881060116356e-05,
1260
+ "loss": 0.005,
1261
+ "step": 8850
1262
+ },
1263
+ {
1264
+ "epoch": 1.438267614738203,
1265
+ "grad_norm": 0.037451136857271194,
1266
+ "learning_rate": 1.0418013359189832e-05,
1267
+ "loss": 0.005,
1268
+ "step": 8900
1269
+ },
1270
+ {
1271
+ "epoch": 1.4463477698771816,
1272
+ "grad_norm": 0.045001059770584106,
1273
+ "learning_rate": 1.0364145658263308e-05,
1274
+ "loss": 0.0055,
1275
+ "step": 8950
1276
+ },
1277
+ {
1278
+ "epoch": 1.4544279250161603,
1279
+ "grad_norm": 0.027605222538113594,
1280
+ "learning_rate": 1.031027795733678e-05,
1281
+ "loss": 0.0047,
1282
+ "step": 9000
1283
+ },
1284
+ {
1285
+ "epoch": 1.4625080801551391,
1286
+ "grad_norm": 0.04454193264245987,
1287
+ "learning_rate": 1.0256410256410256e-05,
1288
+ "loss": 0.0054,
1289
+ "step": 9050
1290
+ },
1291
+ {
1292
+ "epoch": 1.4705882352941178,
1293
+ "grad_norm": 0.023829152807593346,
1294
+ "learning_rate": 1.0202542555483732e-05,
1295
+ "loss": 0.0051,
1296
+ "step": 9100
1297
+ },
1298
+ {
1299
+ "epoch": 1.4786683904330964,
1300
+ "grad_norm": 0.04157187044620514,
1301
+ "learning_rate": 1.0148674854557207e-05,
1302
+ "loss": 0.0047,
1303
+ "step": 9150
1304
+ },
1305
+ {
1306
+ "epoch": 1.486748545572075,
1307
+ "grad_norm": 0.03874518349766731,
1308
+ "learning_rate": 1.0094807153630683e-05,
1309
+ "loss": 0.0053,
1310
+ "step": 9200
1311
+ },
1312
+ {
1313
+ "epoch": 1.4948287007110537,
1314
+ "grad_norm": 0.026905696839094162,
1315
+ "learning_rate": 1.0040939452704159e-05,
1316
+ "loss": 0.005,
1317
+ "step": 9250
1318
+ },
1319
+ {
1320
+ "epoch": 1.5029088558500323,
1321
+ "grad_norm": 0.06382673233747482,
1322
+ "learning_rate": 9.987071751777635e-06,
1323
+ "loss": 0.005,
1324
+ "step": 9300
1325
+ },
1326
+ {
1327
+ "epoch": 1.510989010989011,
1328
+ "grad_norm": 0.02449849620461464,
1329
+ "learning_rate": 9.93320405085111e-06,
1330
+ "loss": 0.0053,
1331
+ "step": 9350
1332
+ },
1333
+ {
1334
+ "epoch": 1.5190691661279896,
1335
+ "grad_norm": 0.04602253809571266,
1336
+ "learning_rate": 9.879336349924586e-06,
1337
+ "loss": 0.0058,
1338
+ "step": 9400
1339
+ },
1340
+ {
1341
+ "epoch": 1.5271493212669682,
1342
+ "grad_norm": 0.026318348944187164,
1343
+ "learning_rate": 9.82546864899806e-06,
1344
+ "loss": 0.005,
1345
+ "step": 9450
1346
+ },
1347
+ {
1348
+ "epoch": 1.5352294764059469,
1349
+ "grad_norm": 0.028364863246679306,
1350
+ "learning_rate": 9.771600948071536e-06,
1351
+ "loss": 0.0047,
1352
+ "step": 9500
1353
+ },
1354
+ {
1355
+ "epoch": 1.5433096315449255,
1356
+ "grad_norm": 0.03204864263534546,
1357
+ "learning_rate": 9.717733247145012e-06,
1358
+ "loss": 0.0046,
1359
+ "step": 9550
1360
+ },
1361
+ {
1362
+ "epoch": 1.5513897866839044,
1363
+ "grad_norm": 0.023740077391266823,
1364
+ "learning_rate": 9.663865546218488e-06,
1365
+ "loss": 0.0057,
1366
+ "step": 9600
1367
+ },
1368
+ {
1369
+ "epoch": 1.559469941822883,
1370
+ "grad_norm": 0.028953751549124718,
1371
+ "learning_rate": 9.609997845291964e-06,
1372
+ "loss": 0.0049,
1373
+ "step": 9650
1374
+ },
1375
+ {
1376
+ "epoch": 1.5675500969618616,
1377
+ "grad_norm": 0.039458662271499634,
1378
+ "learning_rate": 9.55613014436544e-06,
1379
+ "loss": 0.0052,
1380
+ "step": 9700
1381
+ },
1382
+ {
1383
+ "epoch": 1.5756302521008403,
1384
+ "grad_norm": 0.02466548979282379,
1385
+ "learning_rate": 9.502262443438914e-06,
1386
+ "loss": 0.0053,
1387
+ "step": 9750
1388
+ },
1389
+ {
1390
+ "epoch": 1.5837104072398192,
1391
+ "grad_norm": 0.09884428232908249,
1392
+ "learning_rate": 9.44839474251239e-06,
1393
+ "loss": 0.0045,
1394
+ "step": 9800
1395
+ },
1396
+ {
1397
+ "epoch": 1.5917905623787978,
1398
+ "grad_norm": 0.052319470793008804,
1399
+ "learning_rate": 9.394527041585865e-06,
1400
+ "loss": 0.0047,
1401
+ "step": 9850
1402
+ },
1403
+ {
1404
+ "epoch": 1.5998707175177764,
1405
+ "grad_norm": 0.04534400627017021,
1406
+ "learning_rate": 9.340659340659341e-06,
1407
+ "loss": 0.0042,
1408
+ "step": 9900
1409
+ },
1410
+ {
1411
+ "epoch": 1.607950872656755,
1412
+ "grad_norm": 0.031061217188835144,
1413
+ "learning_rate": 9.286791639732817e-06,
1414
+ "loss": 0.0053,
1415
+ "step": 9950
1416
+ },
1417
+ {
1418
+ "epoch": 1.6160310277957337,
1419
+ "grad_norm": 0.04152417555451393,
1420
+ "learning_rate": 9.232923938806293e-06,
1421
+ "loss": 0.0044,
1422
+ "step": 10000
1423
+ },
1424
+ {
1425
+ "epoch": 1.6241111829347123,
1426
+ "grad_norm": 0.06364952027797699,
1427
+ "learning_rate": 9.179056237879767e-06,
1428
+ "loss": 0.0051,
1429
+ "step": 10050
1430
+ },
1431
+ {
1432
+ "epoch": 1.632191338073691,
1433
+ "grad_norm": 0.05075689032673836,
1434
+ "learning_rate": 9.125188536953243e-06,
1435
+ "loss": 0.005,
1436
+ "step": 10100
1437
+ },
1438
+ {
1439
+ "epoch": 1.6402714932126696,
1440
+ "grad_norm": 0.05718667805194855,
1441
+ "learning_rate": 9.071320836026718e-06,
1442
+ "loss": 0.005,
1443
+ "step": 10150
1444
+ },
1445
+ {
1446
+ "epoch": 1.6483516483516483,
1447
+ "grad_norm": 0.05176397040486336,
1448
+ "learning_rate": 9.017453135100194e-06,
1449
+ "loss": 0.005,
1450
+ "step": 10200
1451
+ },
1452
+ {
1453
+ "epoch": 1.656431803490627,
1454
+ "grad_norm": 0.05737081915140152,
1455
+ "learning_rate": 8.96358543417367e-06,
1456
+ "loss": 0.0054,
1457
+ "step": 10250
1458
+ },
1459
+ {
1460
+ "epoch": 1.6645119586296055,
1461
+ "grad_norm": 0.02792266197502613,
1462
+ "learning_rate": 8.909717733247146e-06,
1463
+ "loss": 0.0044,
1464
+ "step": 10300
1465
+ },
1466
+ {
1467
+ "epoch": 1.6725921137685844,
1468
+ "grad_norm": 0.029061343520879745,
1469
+ "learning_rate": 8.855850032320622e-06,
1470
+ "loss": 0.0052,
1471
+ "step": 10350
1472
+ },
1473
+ {
1474
+ "epoch": 1.680672268907563,
1475
+ "grad_norm": 0.03089820221066475,
1476
+ "learning_rate": 8.801982331394097e-06,
1477
+ "loss": 0.005,
1478
+ "step": 10400
1479
+ },
1480
+ {
1481
+ "epoch": 1.6887524240465417,
1482
+ "grad_norm": 0.046603500843048096,
1483
+ "learning_rate": 8.748114630467572e-06,
1484
+ "loss": 0.006,
1485
+ "step": 10450
1486
+ },
1487
+ {
1488
+ "epoch": 1.6968325791855203,
1489
+ "grad_norm": 0.033478520810604095,
1490
+ "learning_rate": 8.694246929541047e-06,
1491
+ "loss": 0.0045,
1492
+ "step": 10500
1493
+ },
1494
+ {
1495
+ "epoch": 1.7049127343244992,
1496
+ "grad_norm": 0.045349959284067154,
1497
+ "learning_rate": 8.640379228614523e-06,
1498
+ "loss": 0.0043,
1499
+ "step": 10550
1500
+ },
1501
+ {
1502
+ "epoch": 1.7129928894634778,
1503
+ "grad_norm": 0.04198373854160309,
1504
+ "learning_rate": 8.586511527687999e-06,
1505
+ "loss": 0.0046,
1506
+ "step": 10600
1507
+ },
1508
+ {
1509
+ "epoch": 1.7210730446024565,
1510
+ "grad_norm": 0.030365299433469772,
1511
+ "learning_rate": 8.532643826761475e-06,
1512
+ "loss": 0.0047,
1513
+ "step": 10650
1514
+ },
1515
+ {
1516
+ "epoch": 1.729153199741435,
1517
+ "grad_norm": 0.053815387189388275,
1518
+ "learning_rate": 8.47877612583495e-06,
1519
+ "loss": 0.0053,
1520
+ "step": 10700
1521
+ },
1522
+ {
1523
+ "epoch": 1.7372333548804137,
1524
+ "grad_norm": 0.040949735790491104,
1525
+ "learning_rate": 8.424908424908426e-06,
1526
+ "loss": 0.0049,
1527
+ "step": 10750
1528
+ },
1529
+ {
1530
+ "epoch": 1.7453135100193924,
1531
+ "grad_norm": 0.02742874063551426,
1532
+ "learning_rate": 8.371040723981902e-06,
1533
+ "loss": 0.0049,
1534
+ "step": 10800
1535
+ },
1536
+ {
1537
+ "epoch": 1.753393665158371,
1538
+ "grad_norm": 0.06784753501415253,
1539
+ "learning_rate": 8.317173023055376e-06,
1540
+ "loss": 0.0058,
1541
+ "step": 10850
1542
+ },
1543
+ {
1544
+ "epoch": 1.7614738202973497,
1545
+ "grad_norm": 0.03332887962460518,
1546
+ "learning_rate": 8.263305322128852e-06,
1547
+ "loss": 0.0046,
1548
+ "step": 10900
1549
+ },
1550
+ {
1551
+ "epoch": 1.7695539754363283,
1552
+ "grad_norm": 0.031116908416152,
1553
+ "learning_rate": 8.209437621202328e-06,
1554
+ "loss": 0.0046,
1555
+ "step": 10950
1556
+ },
1557
+ {
1558
+ "epoch": 1.777634130575307,
1559
+ "grad_norm": 0.03276669979095459,
1560
+ "learning_rate": 8.155569920275804e-06,
1561
+ "loss": 0.0045,
1562
+ "step": 11000
1563
+ },
1564
+ {
1565
+ "epoch": 1.7857142857142856,
1566
+ "grad_norm": 0.04121123626828194,
1567
+ "learning_rate": 8.10170221934928e-06,
1568
+ "loss": 0.0057,
1569
+ "step": 11050
1570
+ },
1571
+ {
1572
+ "epoch": 1.7937944408532642,
1573
+ "grad_norm": 0.05228004604578018,
1574
+ "learning_rate": 8.047834518422755e-06,
1575
+ "loss": 0.005,
1576
+ "step": 11100
1577
+ },
1578
+ {
1579
+ "epoch": 1.801874595992243,
1580
+ "grad_norm": 0.03658825531601906,
1581
+ "learning_rate": 7.993966817496231e-06,
1582
+ "loss": 0.0048,
1583
+ "step": 11150
1584
+ },
1585
+ {
1586
+ "epoch": 1.8099547511312217,
1587
+ "grad_norm": 0.029890988022089005,
1588
+ "learning_rate": 7.940099116569705e-06,
1589
+ "loss": 0.0045,
1590
+ "step": 11200
1591
+ },
1592
+ {
1593
+ "epoch": 1.8180349062702004,
1594
+ "grad_norm": 0.057183150202035904,
1595
+ "learning_rate": 7.886231415643181e-06,
1596
+ "loss": 0.0046,
1597
+ "step": 11250
1598
+ },
1599
+ {
1600
+ "epoch": 1.826115061409179,
1601
+ "grad_norm": 0.032826654613018036,
1602
+ "learning_rate": 7.832363714716657e-06,
1603
+ "loss": 0.0044,
1604
+ "step": 11300
1605
+ },
1606
+ {
1607
+ "epoch": 1.8341952165481579,
1608
+ "grad_norm": 0.08467372506856918,
1609
+ "learning_rate": 7.778496013790133e-06,
1610
+ "loss": 0.0048,
1611
+ "step": 11350
1612
+ },
1613
+ {
1614
+ "epoch": 1.8422753716871365,
1615
+ "grad_norm": 0.03478661924600601,
1616
+ "learning_rate": 7.724628312863608e-06,
1617
+ "loss": 0.005,
1618
+ "step": 11400
1619
+ },
1620
+ {
1621
+ "epoch": 1.8503555268261151,
1622
+ "grad_norm": 0.05386711657047272,
1623
+ "learning_rate": 7.670760611937084e-06,
1624
+ "loss": 0.0048,
1625
+ "step": 11450
1626
+ },
1627
+ {
1628
+ "epoch": 1.8584356819650938,
1629
+ "grad_norm": 0.03354140743613243,
1630
+ "learning_rate": 7.616892911010558e-06,
1631
+ "loss": 0.0044,
1632
+ "step": 11500
1633
+ },
1634
+ {
1635
+ "epoch": 1.8665158371040724,
1636
+ "grad_norm": 0.043414924293756485,
1637
+ "learning_rate": 7.563025210084034e-06,
1638
+ "loss": 0.0055,
1639
+ "step": 11550
1640
+ },
1641
+ {
1642
+ "epoch": 1.874595992243051,
1643
+ "grad_norm": 0.040471382439136505,
1644
+ "learning_rate": 7.50915750915751e-06,
1645
+ "loss": 0.0052,
1646
+ "step": 11600
1647
+ },
1648
+ {
1649
+ "epoch": 1.8826761473820297,
1650
+ "grad_norm": 0.06200335547327995,
1651
+ "learning_rate": 7.455289808230986e-06,
1652
+ "loss": 0.0053,
1653
+ "step": 11650
1654
+ },
1655
+ {
1656
+ "epoch": 1.8907563025210083,
1657
+ "grad_norm": 0.04366638883948326,
1658
+ "learning_rate": 7.4014221073044616e-06,
1659
+ "loss": 0.0046,
1660
+ "step": 11700
1661
+ },
1662
+ {
1663
+ "epoch": 1.898836457659987,
1664
+ "grad_norm": 0.022821014747023582,
1665
+ "learning_rate": 7.3475544063779365e-06,
1666
+ "loss": 0.0045,
1667
+ "step": 11750
1668
+ },
1669
+ {
1670
+ "epoch": 1.9069166127989656,
1671
+ "grad_norm": 0.038873497396707535,
1672
+ "learning_rate": 7.2936867054514115e-06,
1673
+ "loss": 0.0046,
1674
+ "step": 11800
1675
+ },
1676
+ {
1677
+ "epoch": 1.9149967679379443,
1678
+ "grad_norm": 0.04890233278274536,
1679
+ "learning_rate": 7.239819004524887e-06,
1680
+ "loss": 0.0057,
1681
+ "step": 11850
1682
+ },
1683
+ {
1684
+ "epoch": 1.9230769230769231,
1685
+ "grad_norm": 0.04092305526137352,
1686
+ "learning_rate": 7.185951303598363e-06,
1687
+ "loss": 0.005,
1688
+ "step": 11900
1689
+ },
1690
+ {
1691
+ "epoch": 1.9311570782159018,
1692
+ "grad_norm": 0.05939971283078194,
1693
+ "learning_rate": 7.132083602671839e-06,
1694
+ "loss": 0.0046,
1695
+ "step": 11950
1696
+ },
1697
+ {
1698
+ "epoch": 1.9392372333548804,
1699
+ "grad_norm": 0.037901926785707474,
1700
+ "learning_rate": 7.078215901745315e-06,
1701
+ "loss": 0.0045,
1702
+ "step": 12000
1703
+ },
1704
+ {
1705
+ "epoch": 1.947317388493859,
1706
+ "grad_norm": 0.0488058477640152,
1707
+ "learning_rate": 7.024348200818789e-06,
1708
+ "loss": 0.005,
1709
+ "step": 12050
1710
+ },
1711
+ {
1712
+ "epoch": 1.955397543632838,
1713
+ "grad_norm": 0.06671205163002014,
1714
+ "learning_rate": 6.970480499892265e-06,
1715
+ "loss": 0.0053,
1716
+ "step": 12100
1717
+ },
1718
+ {
1719
+ "epoch": 1.9634776987718165,
1720
+ "grad_norm": 0.03580876812338829,
1721
+ "learning_rate": 6.91661279896574e-06,
1722
+ "loss": 0.0048,
1723
+ "step": 12150
1724
+ },
1725
+ {
1726
+ "epoch": 1.9715578539107952,
1727
+ "grad_norm": 0.05258365720510483,
1728
+ "learning_rate": 6.862745098039216e-06,
1729
+ "loss": 0.0047,
1730
+ "step": 12200
1731
+ },
1732
+ {
1733
+ "epoch": 1.9796380090497738,
1734
+ "grad_norm": 0.035823095589876175,
1735
+ "learning_rate": 6.808877397112692e-06,
1736
+ "loss": 0.0053,
1737
+ "step": 12250
1738
+ },
1739
+ {
1740
+ "epoch": 1.9877181641887525,
1741
+ "grad_norm": 0.03747252747416496,
1742
+ "learning_rate": 6.755009696186168e-06,
1743
+ "loss": 0.0052,
1744
+ "step": 12300
1745
+ },
1746
+ {
1747
+ "epoch": 1.995798319327731,
1748
+ "grad_norm": 0.029116889461874962,
1749
+ "learning_rate": 6.701141995259643e-06,
1750
+ "loss": 0.0045,
1751
+ "step": 12350
1752
+ },
1753
+ {
1754
+ "epoch": 2.0,
1755
+ "eval_loss": 0.003754823002964258,
1756
+ "eval_rouge1": 87.21845608272304,
1757
+ "eval_rouge2": 83.41556886218162,
1758
+ "eval_rougeL": 85.9862609239223,
1759
+ "eval_rougeLsum": 85.95382052592191,
1760
+ "eval_runtime": 48.1802,
1761
+ "eval_samples_per_second": 10.378,
1762
+ "eval_steps_per_second": 1.308,
1763
+ "step": 12376
1764
+ },
1765
+ {
1766
+ "epoch": 2.0038784744667097,
1767
+ "grad_norm": 0.040494147688150406,
1768
+ "learning_rate": 6.647274294333118e-06,
1769
+ "loss": 0.0051,
1770
+ "step": 12400
1771
+ },
1772
+ {
1773
+ "epoch": 2.0119586296056884,
1774
+ "grad_norm": 0.021118978038430214,
1775
+ "learning_rate": 6.5934065934065935e-06,
1776
+ "loss": 0.0044,
1777
+ "step": 12450
1778
+ },
1779
+ {
1780
+ "epoch": 2.020038784744667,
1781
+ "grad_norm": 0.03655942156910896,
1782
+ "learning_rate": 6.539538892480069e-06,
1783
+ "loss": 0.0046,
1784
+ "step": 12500
1785
+ },
1786
+ {
1787
+ "epoch": 2.0281189398836457,
1788
+ "grad_norm": 0.033596962690353394,
1789
+ "learning_rate": 6.485671191553545e-06,
1790
+ "loss": 0.0049,
1791
+ "step": 12550
1792
+ },
1793
+ {
1794
+ "epoch": 2.0361990950226243,
1795
+ "grad_norm": 0.04082285612821579,
1796
+ "learning_rate": 6.431803490627021e-06,
1797
+ "loss": 0.0046,
1798
+ "step": 12600
1799
+ },
1800
+ {
1801
+ "epoch": 2.044279250161603,
1802
+ "grad_norm": 0.035328153520822525,
1803
+ "learning_rate": 6.377935789700496e-06,
1804
+ "loss": 0.0047,
1805
+ "step": 12650
1806
+ },
1807
+ {
1808
+ "epoch": 2.0523594053005816,
1809
+ "grad_norm": 0.06532145291566849,
1810
+ "learning_rate": 6.324068088773972e-06,
1811
+ "loss": 0.0046,
1812
+ "step": 12700
1813
+ },
1814
+ {
1815
+ "epoch": 2.0604395604395602,
1816
+ "grad_norm": 0.021467560902237892,
1817
+ "learning_rate": 6.2702003878474475e-06,
1818
+ "loss": 0.0044,
1819
+ "step": 12750
1820
+ },
1821
+ {
1822
+ "epoch": 2.0685197155785393,
1823
+ "grad_norm": 0.028903750702738762,
1824
+ "learning_rate": 6.2163326869209225e-06,
1825
+ "loss": 0.0047,
1826
+ "step": 12800
1827
+ },
1828
+ {
1829
+ "epoch": 2.076599870717518,
1830
+ "grad_norm": 0.04827199503779411,
1831
+ "learning_rate": 6.162464985994398e-06,
1832
+ "loss": 0.0046,
1833
+ "step": 12850
1834
+ },
1835
+ {
1836
+ "epoch": 2.0846800258564966,
1837
+ "grad_norm": 0.05190654471516609,
1838
+ "learning_rate": 6.108597285067874e-06,
1839
+ "loss": 0.0044,
1840
+ "step": 12900
1841
+ },
1842
+ {
1843
+ "epoch": 2.0927601809954752,
1844
+ "grad_norm": 0.043597374111413956,
1845
+ "learning_rate": 6.054729584141349e-06,
1846
+ "loss": 0.0039,
1847
+ "step": 12950
1848
+ },
1849
+ {
1850
+ "epoch": 2.100840336134454,
1851
+ "grad_norm": 0.025249801576137543,
1852
+ "learning_rate": 6.000861883214825e-06,
1853
+ "loss": 0.0049,
1854
+ "step": 13000
1855
+ },
1856
+ {
1857
+ "epoch": 2.1089204912734325,
1858
+ "grad_norm": 0.04429004713892937,
1859
+ "learning_rate": 5.946994182288301e-06,
1860
+ "loss": 0.0045,
1861
+ "step": 13050
1862
+ },
1863
+ {
1864
+ "epoch": 2.117000646412411,
1865
+ "grad_norm": 0.05018601194024086,
1866
+ "learning_rate": 5.8931264813617764e-06,
1867
+ "loss": 0.0047,
1868
+ "step": 13100
1869
+ },
1870
+ {
1871
+ "epoch": 2.12508080155139,
1872
+ "grad_norm": 0.0563606433570385,
1873
+ "learning_rate": 5.839258780435252e-06,
1874
+ "loss": 0.0049,
1875
+ "step": 13150
1876
+ },
1877
+ {
1878
+ "epoch": 2.1331609566903684,
1879
+ "grad_norm": 0.036379583179950714,
1880
+ "learning_rate": 5.785391079508727e-06,
1881
+ "loss": 0.0045,
1882
+ "step": 13200
1883
+ },
1884
+ {
1885
+ "epoch": 2.141241111829347,
1886
+ "grad_norm": 0.03966435417532921,
1887
+ "learning_rate": 5.731523378582202e-06,
1888
+ "loss": 0.0046,
1889
+ "step": 13250
1890
+ },
1891
+ {
1892
+ "epoch": 2.1493212669683257,
1893
+ "grad_norm": 0.03525066375732422,
1894
+ "learning_rate": 5.677655677655678e-06,
1895
+ "loss": 0.004,
1896
+ "step": 13300
1897
+ },
1898
+ {
1899
+ "epoch": 2.1574014221073043,
1900
+ "grad_norm": 0.04028931260108948,
1901
+ "learning_rate": 5.623787976729154e-06,
1902
+ "loss": 0.0045,
1903
+ "step": 13350
1904
+ },
1905
+ {
1906
+ "epoch": 2.165481577246283,
1907
+ "grad_norm": 0.027697792276740074,
1908
+ "learning_rate": 5.5699202758026296e-06,
1909
+ "loss": 0.0049,
1910
+ "step": 13400
1911
+ },
1912
+ {
1913
+ "epoch": 2.1735617323852616,
1914
+ "grad_norm": 0.02208828553557396,
1915
+ "learning_rate": 5.516052574876105e-06,
1916
+ "loss": 0.0044,
1917
+ "step": 13450
1918
+ },
1919
+ {
1920
+ "epoch": 2.1816418875242403,
1921
+ "grad_norm": 0.03327793627977371,
1922
+ "learning_rate": 5.4621848739495795e-06,
1923
+ "loss": 0.0052,
1924
+ "step": 13500
1925
+ },
1926
+ {
1927
+ "epoch": 2.1897220426632193,
1928
+ "grad_norm": 0.040238089859485626,
1929
+ "learning_rate": 5.408317173023055e-06,
1930
+ "loss": 0.0044,
1931
+ "step": 13550
1932
+ },
1933
+ {
1934
+ "epoch": 2.197802197802198,
1935
+ "grad_norm": 0.02015913464128971,
1936
+ "learning_rate": 5.354449472096531e-06,
1937
+ "loss": 0.0049,
1938
+ "step": 13600
1939
+ },
1940
+ {
1941
+ "epoch": 2.2058823529411766,
1942
+ "grad_norm": 0.018138017505407333,
1943
+ "learning_rate": 5.300581771170007e-06,
1944
+ "loss": 0.0048,
1945
+ "step": 13650
1946
+ },
1947
+ {
1948
+ "epoch": 2.2139625080801553,
1949
+ "grad_norm": 0.050266802310943604,
1950
+ "learning_rate": 5.246714070243483e-06,
1951
+ "loss": 0.0043,
1952
+ "step": 13700
1953
+ },
1954
+ {
1955
+ "epoch": 2.222042663219134,
1956
+ "grad_norm": 0.04515570029616356,
1957
+ "learning_rate": 5.1928463693169585e-06,
1958
+ "loss": 0.0036,
1959
+ "step": 13750
1960
+ },
1961
+ {
1962
+ "epoch": 2.2301228183581125,
1963
+ "grad_norm": 0.039447471499443054,
1964
+ "learning_rate": 5.138978668390433e-06,
1965
+ "loss": 0.0044,
1966
+ "step": 13800
1967
+ },
1968
+ {
1969
+ "epoch": 2.238202973497091,
1970
+ "grad_norm": 0.03310653567314148,
1971
+ "learning_rate": 5.085110967463908e-06,
1972
+ "loss": 0.0044,
1973
+ "step": 13850
1974
+ },
1975
+ {
1976
+ "epoch": 2.24628312863607,
1977
+ "grad_norm": 0.014222861267626286,
1978
+ "learning_rate": 5.031243266537384e-06,
1979
+ "loss": 0.0047,
1980
+ "step": 13900
1981
+ },
1982
+ {
1983
+ "epoch": 2.2543632837750485,
1984
+ "grad_norm": 0.016546355560421944,
1985
+ "learning_rate": 4.97737556561086e-06,
1986
+ "loss": 0.0047,
1987
+ "step": 13950
1988
+ },
1989
+ {
1990
+ "epoch": 2.262443438914027,
1991
+ "grad_norm": 0.05192546918988228,
1992
+ "learning_rate": 4.923507864684336e-06,
1993
+ "loss": 0.0043,
1994
+ "step": 14000
1995
+ },
1996
+ {
1997
+ "epoch": 2.2705235940530057,
1998
+ "grad_norm": 0.04964493215084076,
1999
+ "learning_rate": 4.869640163757811e-06,
2000
+ "loss": 0.0047,
2001
+ "step": 14050
2002
+ },
2003
+ {
2004
+ "epoch": 2.2786037491919844,
2005
+ "grad_norm": 0.01690448634326458,
2006
+ "learning_rate": 4.8157724628312866e-06,
2007
+ "loss": 0.0043,
2008
+ "step": 14100
2009
+ },
2010
+ {
2011
+ "epoch": 2.286683904330963,
2012
+ "grad_norm": 0.03871385008096695,
2013
+ "learning_rate": 4.761904761904762e-06,
2014
+ "loss": 0.0054,
2015
+ "step": 14150
2016
+ },
2017
+ {
2018
+ "epoch": 2.2947640594699417,
2019
+ "grad_norm": 0.029631048440933228,
2020
+ "learning_rate": 4.708037060978238e-06,
2021
+ "loss": 0.0042,
2022
+ "step": 14200
2023
+ },
2024
+ {
2025
+ "epoch": 2.3028442146089203,
2026
+ "grad_norm": 0.031350765377283096,
2027
+ "learning_rate": 4.654169360051713e-06,
2028
+ "loss": 0.0045,
2029
+ "step": 14250
2030
+ },
2031
+ {
2032
+ "epoch": 2.310924369747899,
2033
+ "grad_norm": 0.05931168794631958,
2034
+ "learning_rate": 4.600301659125189e-06,
2035
+ "loss": 0.0051,
2036
+ "step": 14300
2037
+ },
2038
+ {
2039
+ "epoch": 2.3190045248868776,
2040
+ "grad_norm": 0.04504646733403206,
2041
+ "learning_rate": 4.546433958198665e-06,
2042
+ "loss": 0.0043,
2043
+ "step": 14350
2044
+ },
2045
+ {
2046
+ "epoch": 2.3270846800258567,
2047
+ "grad_norm": 0.04591371491551399,
2048
+ "learning_rate": 4.4925662572721405e-06,
2049
+ "loss": 0.0046,
2050
+ "step": 14400
2051
+ },
2052
+ {
2053
+ "epoch": 2.3351648351648353,
2054
+ "grad_norm": 0.030743196606636047,
2055
+ "learning_rate": 4.4386985563456155e-06,
2056
+ "loss": 0.004,
2057
+ "step": 14450
2058
+ },
2059
+ {
2060
+ "epoch": 2.343244990303814,
2061
+ "grad_norm": 0.04723818972706795,
2062
+ "learning_rate": 4.384830855419091e-06,
2063
+ "loss": 0.0036,
2064
+ "step": 14500
2065
+ },
2066
+ {
2067
+ "epoch": 2.3513251454427926,
2068
+ "grad_norm": 0.02913173846900463,
2069
+ "learning_rate": 4.330963154492567e-06,
2070
+ "loss": 0.0049,
2071
+ "step": 14550
2072
+ },
2073
+ {
2074
+ "epoch": 2.3594053005817712,
2075
+ "grad_norm": 0.025342822074890137,
2076
+ "learning_rate": 4.277095453566042e-06,
2077
+ "loss": 0.0052,
2078
+ "step": 14600
2079
+ },
2080
+ {
2081
+ "epoch": 2.36748545572075,
2082
+ "grad_norm": 0.04897177964448929,
2083
+ "learning_rate": 4.223227752639518e-06,
2084
+ "loss": 0.0046,
2085
+ "step": 14650
2086
+ },
2087
+ {
2088
+ "epoch": 2.3755656108597285,
2089
+ "grad_norm": 0.05571192875504494,
2090
+ "learning_rate": 4.169360051712994e-06,
2091
+ "loss": 0.0045,
2092
+ "step": 14700
2093
+ },
2094
+ {
2095
+ "epoch": 2.383645765998707,
2096
+ "grad_norm": 0.04304831102490425,
2097
+ "learning_rate": 4.115492350786469e-06,
2098
+ "loss": 0.0045,
2099
+ "step": 14750
2100
+ },
2101
+ {
2102
+ "epoch": 2.391725921137686,
2103
+ "grad_norm": 0.04351252317428589,
2104
+ "learning_rate": 4.0616246498599444e-06,
2105
+ "loss": 0.0046,
2106
+ "step": 14800
2107
+ },
2108
+ {
2109
+ "epoch": 2.3998060762766644,
2110
+ "grad_norm": 0.07481127232313156,
2111
+ "learning_rate": 4.00775694893342e-06,
2112
+ "loss": 0.0044,
2113
+ "step": 14850
2114
+ },
2115
+ {
2116
+ "epoch": 2.407886231415643,
2117
+ "grad_norm": 0.06555662304162979,
2118
+ "learning_rate": 3.953889248006895e-06,
2119
+ "loss": 0.0046,
2120
+ "step": 14900
2121
+ },
2122
+ {
2123
+ "epoch": 2.4159663865546217,
2124
+ "grad_norm": 0.03455435112118721,
2125
+ "learning_rate": 3.900021547080371e-06,
2126
+ "loss": 0.0047,
2127
+ "step": 14950
2128
+ },
2129
+ {
2130
+ "epoch": 2.4240465416936003,
2131
+ "grad_norm": 0.0476142056286335,
2132
+ "learning_rate": 3.846153846153847e-06,
2133
+ "loss": 0.0046,
2134
+ "step": 15000
2135
+ },
2136
+ {
2137
+ "epoch": 2.4321266968325794,
2138
+ "grad_norm": 0.07432708144187927,
2139
+ "learning_rate": 3.7922861452273218e-06,
2140
+ "loss": 0.0044,
2141
+ "step": 15050
2142
+ },
2143
+ {
2144
+ "epoch": 2.440206851971558,
2145
+ "grad_norm": 0.018862377852201462,
2146
+ "learning_rate": 3.7384184443007976e-06,
2147
+ "loss": 0.0042,
2148
+ "step": 15100
2149
+ },
2150
+ {
2151
+ "epoch": 2.4482870071105367,
2152
+ "grad_norm": 0.0463634617626667,
2153
+ "learning_rate": 3.6845507433742734e-06,
2154
+ "loss": 0.0051,
2155
+ "step": 15150
2156
+ },
2157
+ {
2158
+ "epoch": 2.4563671622495153,
2159
+ "grad_norm": 0.0470375195145607,
2160
+ "learning_rate": 3.6306830424477483e-06,
2161
+ "loss": 0.0046,
2162
+ "step": 15200
2163
+ },
2164
+ {
2165
+ "epoch": 2.464447317388494,
2166
+ "grad_norm": 0.028038673102855682,
2167
+ "learning_rate": 3.576815341521224e-06,
2168
+ "loss": 0.0045,
2169
+ "step": 15250
2170
+ },
2171
+ {
2172
+ "epoch": 2.4725274725274726,
2173
+ "grad_norm": 0.03303570672869682,
2174
+ "learning_rate": 3.5229476405947e-06,
2175
+ "loss": 0.0048,
2176
+ "step": 15300
2177
+ },
2178
+ {
2179
+ "epoch": 2.4806076276664513,
2180
+ "grad_norm": 0.040639448910951614,
2181
+ "learning_rate": 3.4690799396681753e-06,
2182
+ "loss": 0.0045,
2183
+ "step": 15350
2184
+ },
2185
+ {
2186
+ "epoch": 2.48868778280543,
2187
+ "grad_norm": 0.03696522116661072,
2188
+ "learning_rate": 3.4152122387416507e-06,
2189
+ "loss": 0.0047,
2190
+ "step": 15400
2191
+ },
2192
+ {
2193
+ "epoch": 2.4967679379444085,
2194
+ "grad_norm": 0.06647258996963501,
2195
+ "learning_rate": 3.3613445378151265e-06,
2196
+ "loss": 0.0046,
2197
+ "step": 15450
2198
+ },
2199
+ {
2200
+ "epoch": 2.504848093083387,
2201
+ "grad_norm": 0.039001937955617905,
2202
+ "learning_rate": 3.307476836888602e-06,
2203
+ "loss": 0.0052,
2204
+ "step": 15500
2205
+ },
2206
+ {
2207
+ "epoch": 2.512928248222366,
2208
+ "grad_norm": 0.02684204652905464,
2209
+ "learning_rate": 3.2536091359620777e-06,
2210
+ "loss": 0.0043,
2211
+ "step": 15550
2212
+ },
2213
+ {
2214
+ "epoch": 2.5210084033613445,
2215
+ "grad_norm": 0.04314061999320984,
2216
+ "learning_rate": 3.1997414350355526e-06,
2217
+ "loss": 0.0047,
2218
+ "step": 15600
2219
+ },
2220
+ {
2221
+ "epoch": 2.529088558500323,
2222
+ "grad_norm": 0.04125179722905159,
2223
+ "learning_rate": 3.1458737341090284e-06,
2224
+ "loss": 0.0046,
2225
+ "step": 15650
2226
+ },
2227
+ {
2228
+ "epoch": 2.5371687136393017,
2229
+ "grad_norm": 0.01851014606654644,
2230
+ "learning_rate": 3.0920060331825042e-06,
2231
+ "loss": 0.0045,
2232
+ "step": 15700
2233
+ },
2234
+ {
2235
+ "epoch": 2.5452488687782804,
2236
+ "grad_norm": 0.03928118199110031,
2237
+ "learning_rate": 3.038138332255979e-06,
2238
+ "loss": 0.0043,
2239
+ "step": 15750
2240
+ },
2241
+ {
2242
+ "epoch": 2.553329023917259,
2243
+ "grad_norm": 0.0691729187965393,
2244
+ "learning_rate": 2.984270631329455e-06,
2245
+ "loss": 0.005,
2246
+ "step": 15800
2247
+ },
2248
+ {
2249
+ "epoch": 2.5614091790562377,
2250
+ "grad_norm": 0.016138378530740738,
2251
+ "learning_rate": 2.930402930402931e-06,
2252
+ "loss": 0.0041,
2253
+ "step": 15850
2254
+ },
2255
+ {
2256
+ "epoch": 2.5694893341952163,
2257
+ "grad_norm": 0.020654356107115746,
2258
+ "learning_rate": 2.8765352294764057e-06,
2259
+ "loss": 0.004,
2260
+ "step": 15900
2261
+ },
2262
+ {
2263
+ "epoch": 2.577569489334195,
2264
+ "grad_norm": 0.04678305238485336,
2265
+ "learning_rate": 2.8226675285498815e-06,
2266
+ "loss": 0.0045,
2267
+ "step": 15950
2268
+ },
2269
+ {
2270
+ "epoch": 2.585649644473174,
2271
+ "grad_norm": 0.035098664462566376,
2272
+ "learning_rate": 2.7687998276233574e-06,
2273
+ "loss": 0.0049,
2274
+ "step": 16000
2275
+ },
2276
+ {
2277
+ "epoch": 2.5937297996121527,
2278
+ "grad_norm": 0.02151743695139885,
2279
+ "learning_rate": 2.7149321266968327e-06,
2280
+ "loss": 0.0049,
2281
+ "step": 16050
2282
+ },
2283
+ {
2284
+ "epoch": 2.6018099547511313,
2285
+ "grad_norm": 0.008306082338094711,
2286
+ "learning_rate": 2.6610644257703085e-06,
2287
+ "loss": 0.0043,
2288
+ "step": 16100
2289
+ },
2290
+ {
2291
+ "epoch": 2.60989010989011,
2292
+ "grad_norm": 0.03021089918911457,
2293
+ "learning_rate": 2.607196724843784e-06,
2294
+ "loss": 0.0042,
2295
+ "step": 16150
2296
+ },
2297
+ {
2298
+ "epoch": 2.6179702650290886,
2299
+ "grad_norm": 0.032146211713552475,
2300
+ "learning_rate": 2.5533290239172593e-06,
2301
+ "loss": 0.0041,
2302
+ "step": 16200
2303
+ },
2304
+ {
2305
+ "epoch": 2.6260504201680672,
2306
+ "grad_norm": 0.030957765877246857,
2307
+ "learning_rate": 2.499461322990735e-06,
2308
+ "loss": 0.0041,
2309
+ "step": 16250
2310
+ },
2311
+ {
2312
+ "epoch": 2.634130575307046,
2313
+ "grad_norm": 0.04607204720377922,
2314
+ "learning_rate": 2.4455936220642105e-06,
2315
+ "loss": 0.0051,
2316
+ "step": 16300
2317
+ },
2318
+ {
2319
+ "epoch": 2.6422107304460245,
2320
+ "grad_norm": 0.02674623765051365,
2321
+ "learning_rate": 2.3917259211376863e-06,
2322
+ "loss": 0.0044,
2323
+ "step": 16350
2324
+ },
2325
+ {
2326
+ "epoch": 2.650290885585003,
2327
+ "grad_norm": 0.016672629863023758,
2328
+ "learning_rate": 2.3378582202111617e-06,
2329
+ "loss": 0.0036,
2330
+ "step": 16400
2331
+ },
2332
+ {
2333
+ "epoch": 2.658371040723982,
2334
+ "grad_norm": 0.03345870599150658,
2335
+ "learning_rate": 2.283990519284637e-06,
2336
+ "loss": 0.0042,
2337
+ "step": 16450
2338
+ },
2339
+ {
2340
+ "epoch": 2.6664511958629604,
2341
+ "grad_norm": 0.03514959663152695,
2342
+ "learning_rate": 2.230122818358113e-06,
2343
+ "loss": 0.0049,
2344
+ "step": 16500
2345
+ },
2346
+ {
2347
+ "epoch": 2.6745313510019395,
2348
+ "grad_norm": 0.03409695625305176,
2349
+ "learning_rate": 2.1762551174315882e-06,
2350
+ "loss": 0.0044,
2351
+ "step": 16550
2352
+ },
2353
+ {
2354
+ "epoch": 2.682611506140918,
2355
+ "grad_norm": 0.021505704149603844,
2356
+ "learning_rate": 2.1223874165050636e-06,
2357
+ "loss": 0.0039,
2358
+ "step": 16600
2359
+ },
2360
+ {
2361
+ "epoch": 2.690691661279897,
2362
+ "grad_norm": 0.142180934548378,
2363
+ "learning_rate": 2.068519715578539e-06,
2364
+ "loss": 0.0049,
2365
+ "step": 16650
2366
+ },
2367
+ {
2368
+ "epoch": 2.6987718164188754,
2369
+ "grad_norm": 0.05118989571928978,
2370
+ "learning_rate": 2.0146520146520148e-06,
2371
+ "loss": 0.0044,
2372
+ "step": 16700
2373
+ },
2374
+ {
2375
+ "epoch": 2.706851971557854,
2376
+ "grad_norm": 0.03433993086218834,
2377
+ "learning_rate": 1.96078431372549e-06,
2378
+ "loss": 0.0042,
2379
+ "step": 16750
2380
+ },
2381
+ {
2382
+ "epoch": 2.7149321266968327,
2383
+ "grad_norm": 0.05495297163724899,
2384
+ "learning_rate": 1.9069166127989658e-06,
2385
+ "loss": 0.0044,
2386
+ "step": 16800
2387
+ },
2388
+ {
2389
+ "epoch": 2.7230122818358113,
2390
+ "grad_norm": 0.03106830269098282,
2391
+ "learning_rate": 1.8530489118724416e-06,
2392
+ "loss": 0.0042,
2393
+ "step": 16850
2394
+ },
2395
+ {
2396
+ "epoch": 2.73109243697479,
2397
+ "grad_norm": 0.05960262566804886,
2398
+ "learning_rate": 1.799181210945917e-06,
2399
+ "loss": 0.004,
2400
+ "step": 16900
2401
+ },
2402
+ {
2403
+ "epoch": 2.7391725921137686,
2404
+ "grad_norm": 0.0477134995162487,
2405
+ "learning_rate": 1.7453135100193923e-06,
2406
+ "loss": 0.0045,
2407
+ "step": 16950
2408
+ },
2409
+ {
2410
+ "epoch": 2.7472527472527473,
2411
+ "grad_norm": 0.04596434533596039,
2412
+ "learning_rate": 1.6925231631113985e-06,
2413
+ "loss": 0.0051,
2414
+ "step": 17000
2415
+ },
2416
+ {
2417
+ "epoch": 2.755332902391726,
2418
+ "grad_norm": 0.02121753990650177,
2419
+ "learning_rate": 1.6386554621848741e-06,
2420
+ "loss": 0.0046,
2421
+ "step": 17050
2422
+ },
2423
+ {
2424
+ "epoch": 2.7634130575307045,
2425
+ "grad_norm": 0.04902210831642151,
2426
+ "learning_rate": 1.5847877612583495e-06,
2427
+ "loss": 0.005,
2428
+ "step": 17100
2429
+ },
2430
+ {
2431
+ "epoch": 2.771493212669683,
2432
+ "grad_norm": 0.03566383942961693,
2433
+ "learning_rate": 1.5309200603318253e-06,
2434
+ "loss": 0.0039,
2435
+ "step": 17150
2436
+ },
2437
+ {
2438
+ "epoch": 2.779573367808662,
2439
+ "grad_norm": 0.03547670692205429,
2440
+ "learning_rate": 1.4770523594053007e-06,
2441
+ "loss": 0.0045,
2442
+ "step": 17200
2443
+ },
2444
+ {
2445
+ "epoch": 2.7876535229476405,
2446
+ "grad_norm": 0.03021397814154625,
2447
+ "learning_rate": 1.423184658478776e-06,
2448
+ "loss": 0.0043,
2449
+ "step": 17250
2450
+ },
2451
+ {
2452
+ "epoch": 2.795733678086619,
2453
+ "grad_norm": 0.03953844681382179,
2454
+ "learning_rate": 1.3693169575522519e-06,
2455
+ "loss": 0.0039,
2456
+ "step": 17300
2457
+ },
2458
+ {
2459
+ "epoch": 2.8038138332255977,
2460
+ "grad_norm": 0.03536642715334892,
2461
+ "learning_rate": 1.3154492566257273e-06,
2462
+ "loss": 0.0041,
2463
+ "step": 17350
2464
+ },
2465
+ {
2466
+ "epoch": 2.8118939883645764,
2467
+ "grad_norm": 0.03634963929653168,
2468
+ "learning_rate": 1.2615815556992029e-06,
2469
+ "loss": 0.005,
2470
+ "step": 17400
2471
+ },
2472
+ {
2473
+ "epoch": 2.819974143503555,
2474
+ "grad_norm": 0.032898109406232834,
2475
+ "learning_rate": 1.2077138547726784e-06,
2476
+ "loss": 0.004,
2477
+ "step": 17450
2478
+ },
2479
+ {
2480
+ "epoch": 2.8280542986425337,
2481
+ "grad_norm": 0.05191650986671448,
2482
+ "learning_rate": 1.153846153846154e-06,
2483
+ "loss": 0.0046,
2484
+ "step": 17500
2485
+ },
2486
+ {
2487
+ "epoch": 2.8361344537815127,
2488
+ "grad_norm": 0.02623840421438217,
2489
+ "learning_rate": 1.0999784529196294e-06,
2490
+ "loss": 0.0042,
2491
+ "step": 17550
2492
+ },
2493
+ {
2494
+ "epoch": 2.8442146089204914,
2495
+ "grad_norm": 0.05044868588447571,
2496
+ "learning_rate": 1.046110751993105e-06,
2497
+ "loss": 0.0044,
2498
+ "step": 17600
2499
+ },
2500
+ {
2501
+ "epoch": 2.85229476405947,
2502
+ "grad_norm": 0.12745575606822968,
2503
+ "learning_rate": 9.922430510665806e-07,
2504
+ "loss": 0.0046,
2505
+ "step": 17650
2506
+ },
2507
+ {
2508
+ "epoch": 2.8603749191984487,
2509
+ "grad_norm": 0.04590355604887009,
2510
+ "learning_rate": 9.383753501400561e-07,
2511
+ "loss": 0.0041,
2512
+ "step": 17700
2513
+ },
2514
+ {
2515
+ "epoch": 2.8684550743374273,
2516
+ "grad_norm": 0.027806632220745087,
2517
+ "learning_rate": 8.845076492135317e-07,
2518
+ "loss": 0.0049,
2519
+ "step": 17750
2520
+ },
2521
+ {
2522
+ "epoch": 2.876535229476406,
2523
+ "grad_norm": 0.047230854630470276,
2524
+ "learning_rate": 8.306399482870072e-07,
2525
+ "loss": 0.0044,
2526
+ "step": 17800
2527
+ },
2528
+ {
2529
+ "epoch": 2.8846153846153846,
2530
+ "grad_norm": 0.023929964751005173,
2531
+ "learning_rate": 7.767722473604828e-07,
2532
+ "loss": 0.0041,
2533
+ "step": 17850
2534
+ },
2535
+ {
2536
+ "epoch": 2.892695539754363,
2537
+ "grad_norm": 0.01972135528922081,
2538
+ "learning_rate": 7.229045464339583e-07,
2539
+ "loss": 0.0038,
2540
+ "step": 17900
2541
+ },
2542
+ {
2543
+ "epoch": 2.900775694893342,
2544
+ "grad_norm": 0.06653473526239395,
2545
+ "learning_rate": 6.690368455074338e-07,
2546
+ "loss": 0.0043,
2547
+ "step": 17950
2548
+ },
2549
+ {
2550
+ "epoch": 2.9088558500323205,
2551
+ "grad_norm": 0.03229772299528122,
2552
+ "learning_rate": 6.151691445809093e-07,
2553
+ "loss": 0.0045,
2554
+ "step": 18000
2555
+ },
2556
+ {
2557
+ "epoch": 2.916936005171299,
2558
+ "grad_norm": 0.027306850999593735,
2559
+ "learning_rate": 5.613014436543849e-07,
2560
+ "loss": 0.0044,
2561
+ "step": 18050
2562
+ },
2563
+ {
2564
+ "epoch": 2.9250161603102782,
2565
+ "grad_norm": 0.04258955270051956,
2566
+ "learning_rate": 5.074337427278604e-07,
2567
+ "loss": 0.0044,
2568
+ "step": 18100
2569
+ },
2570
+ {
2571
+ "epoch": 2.933096315449257,
2572
+ "grad_norm": 0.05304836109280586,
2573
+ "learning_rate": 4.5356604180133593e-07,
2574
+ "loss": 0.0042,
2575
+ "step": 18150
2576
+ },
2577
+ {
2578
+ "epoch": 2.9411764705882355,
2579
+ "grad_norm": 0.03534824028611183,
2580
+ "learning_rate": 3.9969834087481147e-07,
2581
+ "loss": 0.0044,
2582
+ "step": 18200
2583
+ },
2584
+ {
2585
+ "epoch": 2.949256625727214,
2586
+ "grad_norm": 0.04045730456709862,
2587
+ "learning_rate": 3.4583063994828706e-07,
2588
+ "loss": 0.0046,
2589
+ "step": 18250
2590
+ },
2591
+ {
2592
+ "epoch": 2.957336780866193,
2593
+ "grad_norm": 0.022856054827570915,
2594
+ "learning_rate": 2.919629390217626e-07,
2595
+ "loss": 0.0046,
2596
+ "step": 18300
2597
+ },
2598
+ {
2599
+ "epoch": 2.9654169360051714,
2600
+ "grad_norm": 0.04489414766430855,
2601
+ "learning_rate": 2.3809523809523811e-07,
2602
+ "loss": 0.0041,
2603
+ "step": 18350
2604
+ },
2605
+ {
2606
+ "epoch": 2.97349709114415,
2607
+ "grad_norm": 0.022563565522432327,
2608
+ "learning_rate": 1.8422753716871365e-07,
2609
+ "loss": 0.0045,
2610
+ "step": 18400
2611
+ },
2612
+ {
2613
+ "epoch": 2.9815772462831287,
2614
+ "grad_norm": 0.05544481799006462,
2615
+ "learning_rate": 1.303598362421892e-07,
2616
+ "loss": 0.0042,
2617
+ "step": 18450
2618
+ },
2619
+ {
2620
+ "epoch": 2.9896574014221073,
2621
+ "grad_norm": 0.03954526409506798,
2622
+ "learning_rate": 7.649213531566473e-08,
2623
+ "loss": 0.0045,
2624
+ "step": 18500
2625
+ },
2626
+ {
2627
+ "epoch": 2.997737556561086,
2628
+ "grad_norm": 0.10584747046232224,
2629
+ "learning_rate": 2.2624434389140274e-08,
2630
+ "loss": 0.0045,
2631
+ "step": 18550
2632
+ }
2633
+ ],
2634
+ "logging_steps": 50,
2635
+ "max_steps": 18564,
2636
+ "num_input_tokens_seen": 0,
2637
+ "num_train_epochs": 3,
2638
+ "save_steps": 500,
2639
+ "stateful_callbacks": {
2640
+ "TrainerControl": {
2641
+ "args": {
2642
+ "should_epoch_stop": false,
2643
+ "should_evaluate": false,
2644
+ "should_log": false,
2645
+ "should_save": true,
2646
+ "should_training_stop": true
2647
+ },
2648
+ "attributes": {}
2649
+ }
2650
+ },
2651
+ "total_flos": 9.043024674816e+16,
2652
+ "train_batch_size": 8,
2653
+ "trial_name": null,
2654
+ "trial_params": null
2655
+ }
ptt5-cronosflow_ai_public/checkpoint-18564/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34e93f42a27804d870f9882bcb1911bb1a6b24e02a2c5af6c116bbf06d3b37a
3
+ size 5905
ptt5-cronosflow_ai_public/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.54.1",
29
+ "use_cache": true,
30
+ "vocab_size": 32128
31
+ }
ptt5-cronosflow_ai_public/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.54.1"
6
+ }
ptt5-cronosflow_ai_public/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9994e1a896341001e10534c4188235730aa16a0244427d1212089a330bba22e
3
+ size 891644712
ptt5-cronosflow_ai_public/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
ptt5-cronosflow_ai_public/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb25b1d67f04fce0e710d58430b606b4ee9887144fa2da22d123c44061cc62e
3
+ size 755569
ptt5-cronosflow_ai_public/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ptt5-cronosflow_ai_public/tokenizer_config.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": false,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "legacy": true,
936
+ "model_max_length": 1000000000000000019884624838656,
937
+ "pad_token": "<pad>",
938
+ "sp_model_kwargs": {},
939
+ "tokenizer_class": "T5Tokenizer",
940
+ "unk_token": "<unk>"
941
+ }
ptt5-cronosflow_ai_public/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34e93f42a27804d870f9882bcb1911bb1a6b24e02a2c5af6c116bbf06d3b37a
3
+ size 5905