atta123 commited on
Commit
a061a87
·
verified ·
1 Parent(s): 1f72076

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .config/.last_opt_in_prompt.yaml +1 -0
  2. .config/.last_survey_prompt.yaml +1 -0
  3. .config/.last_update_check.json +1 -0
  4. .config/active_config +1 -0
  5. .config/config_sentinel +0 -0
  6. .config/configurations/config_default +6 -0
  7. .config/default_configs.db +0 -0
  8. .config/gce +1 -0
  9. .config/hidden_gcloud_config_universe_descriptor_data_cache_configs.db +0 -0
  10. .config/logs/2024.10.02/13.24.56.056128.log +764 -0
  11. .config/logs/2024.10.02/13.25.16.787495.log +5 -0
  12. .config/logs/2024.10.02/13.25.28.231611.log +123 -0
  13. .config/logs/2024.10.02/13.25.29.095888.log +5 -0
  14. .config/logs/2024.10.02/13.25.40.484117.log +8 -0
  15. .config/logs/2024.10.02/13.25.41.118585.log +8 -0
  16. .gitattributes +2 -0
  17. results/checkpoint-14000/added_tokens.json +102 -0
  18. results/checkpoint-14000/config.json +61 -0
  19. results/checkpoint-14000/generation_config.json +6 -0
  20. results/checkpoint-14000/model.safetensors +3 -0
  21. results/checkpoint-14000/optimizer.pt +3 -0
  22. results/checkpoint-14000/rng_state.pth +3 -0
  23. results/checkpoint-14000/scheduler.pt +3 -0
  24. results/checkpoint-14000/special_tokens_map.json +125 -0
  25. results/checkpoint-14000/spiece.model +3 -0
  26. results/checkpoint-14000/tokenizer_config.json +940 -0
  27. results/checkpoint-14000/trainer_state.json +2497 -0
  28. results/checkpoint-14000/training_args.bin +3 -0
  29. results/checkpoint-14500/added_tokens.json +102 -0
  30. results/checkpoint-14500/config.json +61 -0
  31. results/checkpoint-14500/generation_config.json +6 -0
  32. results/checkpoint-14500/model.safetensors +3 -0
  33. results/checkpoint-14500/optimizer.pt +3 -0
  34. results/checkpoint-14500/rng_state.pth +3 -0
  35. results/checkpoint-14500/scheduler.pt +3 -0
  36. results/checkpoint-14500/special_tokens_map.json +125 -0
  37. results/checkpoint-14500/spiece.model +3 -0
  38. results/checkpoint-14500/tokenizer_config.json +940 -0
  39. results/checkpoint-14500/trainer_state.json +2576 -0
  40. results/checkpoint-14500/training_args.bin +3 -0
  41. results/checkpoint-14800/added_tokens.json +102 -0
  42. results/checkpoint-14800/config.json +61 -0
  43. results/checkpoint-14800/generation_config.json +6 -0
  44. results/checkpoint-14800/model.safetensors +3 -0
  45. results/checkpoint-14800/optimizer.pt +3 -0
  46. results/checkpoint-14800/rng_state.pth +3 -0
  47. results/checkpoint-14800/scheduler.pt +3 -0
  48. results/checkpoint-14800/special_tokens_map.json +125 -0
  49. results/checkpoint-14800/spiece.model +3 -0
  50. results/checkpoint-14800/tokenizer_config.json +940 -0
.config/.last_opt_in_prompt.yaml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
.config/.last_survey_prompt.yaml ADDED
@@ -0,0 +1 @@
 
 
1
+ last_prompt_time: 1727875527.6556063
.config/.last_update_check.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"last_update_check_time": 1727875528.625252, "last_update_check_revision": 20240927140238, "notifications": [], "last_nag_times": {}}
.config/active_config ADDED
@@ -0,0 +1 @@
 
 
1
+ default
.config/config_sentinel ADDED
File without changes
.config/configurations/config_default ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ [component_manager]
2
+ disable_update_check = true
3
+
4
+ [compute]
5
+ gce_metadata_read_timeout_sec = 0
6
+
.config/default_configs.db ADDED
Binary file (12.3 kB). View file
 
.config/gce ADDED
@@ -0,0 +1 @@
 
 
1
+ False
.config/hidden_gcloud_config_universe_descriptor_data_cache_configs.db ADDED
Binary file (12.3 kB). View file
 
.config/logs/2024.10.02/13.24.56.056128.log ADDED
@@ -0,0 +1,764 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-10-02 13:25:08,083 DEBUG root Loaded Command Group: ['gcloud', 'components']
2
+ 2024-10-02 13:25:08,090 DEBUG root Loaded Command Group: ['gcloud', 'components', 'update']
3
+ 2024-10-02 13:25:08,094 DEBUG root Running [gcloud.components.update] with arguments: [--compile-python: "True", --quiet: "True", COMPONENT-IDS:6: "['core', 'gcloud-deps', 'bq', 'gcloud', 'gcloud-crc32c', 'gsutil']"]
4
+ 2024-10-02 13:25:08,096 INFO ___FILE_ONLY___ Beginning update. This process may take several minutes.
5
+
6
+ 2024-10-02 13:25:08,142 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
7
+ 2024-10-02 13:25:08,208 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/components-2.json HTTP/1.1" 200 227002
8
+ 2024-10-02 13:25:08,228 INFO ___FILE_ONLY___
9
+
10
+ 2024-10-02 13:25:08,228 INFO ___FILE_ONLY___
11
+ Your current Google Cloud CLI version is: 495.0.0
12
+
13
+ 2024-10-02 13:25:08,229 INFO ___FILE_ONLY___ Installing components from version: 495.0.0
14
+
15
+ 2024-10-02 13:25:08,229 INFO ___FILE_ONLY___
16
+
17
+ 2024-10-02 13:25:08,229 DEBUG root Chosen display Format:table[box,title="These components will be removed."](details.display_name:label=Name:align=left,version.version_string:label=Version:align=right,data.size.size(zero="",min=1048576):label=Size:align=right)
18
+ 2024-10-02 13:25:08,230 DEBUG root Chosen display Format:table[box,title="These components will be updated."](details.display_name:label=Name:align=left,version.version_string:label=Version:align=right,data.size.size(zero="",min=1048576):label=Size:align=right)
19
+ 2024-10-02 13:25:08,231 DEBUG root Chosen display Format:table[box,title="These components will be installed."](details.display_name:label=Name:align=left,version.version_string:label=Version:align=right,data.size.size(zero="",min=1048576):label=Size:align=right)
20
+ 2024-10-02 13:25:08,273 INFO ___FILE_ONLY___ ┌─────────────────────────────────────────────────────────────────────────────┐
21
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___
22
+
23
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___ │ These components will be installed. │
24
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___
25
+
26
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___ ├─────────────────────────────────────────────────────┬────────────┬──────────┤
27
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___
28
+
29
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___ │ Name │ Version │ Size │
30
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___
31
+
32
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___ ├─────────────────────────────────────────────────────┼────────────┼──────────┤
33
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___
34
+
35
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___ │
36
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___ BigQuery Command Line Tool
37
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___
38
+ 2024-10-02 13:25:08,274 INFO ___FILE_ONLY___ │
39
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___ 2.1.8
40
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___
41
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___ │
42
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___ 1.7 MiB
43
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___
44
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___ │
45
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___
46
+
47
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___ │
48
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___ BigQuery Command Line Tool (Platform Specific)
49
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___
50
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___ │
51
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___ 2.1.8
52
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___
53
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___ │
54
+ 2024-10-02 13:25:08,275 INFO ___FILE_ONLY___ < 1 MiB
55
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___
56
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___ │
57
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___
58
+
59
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___ │
60
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___ Bundled Python 3.11 (Platform Specific)
61
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___
62
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___ │
63
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___ 3.11.9
64
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___
65
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___ │
66
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___ 74.4 MiB
67
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___
68
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___ │
69
+ 2024-10-02 13:25:08,276 INFO ___FILE_ONLY___
70
+
71
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___ │
72
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___ Cloud Storage Command Line Tool
73
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___
74
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___ │
75
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___ 5.30
76
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___
77
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___ │
78
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___ 11.3 MiB
79
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___
80
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___ │
81
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___
82
+
83
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___ │
84
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___ Cloud Storage Command Line Tool (Platform Specific)
85
+ 2024-10-02 13:25:08,277 INFO ___FILE_ONLY___
86
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___ │
87
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___ 5.30
88
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___
89
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___ │
90
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___ < 1 MiB
91
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___
92
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___ │
93
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___
94
+
95
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___ │
96
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___ Google Cloud CLI Core Libraries (Platform Specific)
97
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___
98
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___ │
99
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___ 2024.08.30
100
+ 2024-10-02 13:25:08,278 INFO ___FILE_ONLY___
101
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___ │
102
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___ < 1 MiB
103
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___
104
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___ │
105
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___
106
+
107
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___ │
108
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___ Google Cloud CRC32C Hash Tool (Platform Specific)
109
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___
110
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___ │
111
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___ 1.0.0
112
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___
113
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___ │
114
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___ 1.3 MiB
115
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___
116
+ 2024-10-02 13:25:08,279 INFO ___FILE_ONLY___ │
117
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___
118
+
119
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___ │
120
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___ gcloud cli dependencies (Platform Specific)
121
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___
122
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___ │
123
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___ 2021.04.16
124
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___
125
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___ │
126
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___ < 1 MiB
127
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___
128
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___ │
129
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___
130
+
131
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___ └─────────────────────────────────────────────────────┴────────────┴──────────┘
132
+ 2024-10-02 13:25:08,280 INFO ___FILE_ONLY___
133
+
134
+ 2024-10-02 13:25:08,281 INFO ___FILE_ONLY___
135
+
136
+ 2024-10-02 13:25:08,284 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
137
+ 2024-10-02 13:25:08,346 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/RELEASE_NOTES HTTP/1.1" 200 1281712
138
+ 2024-10-02 13:25:08,406 INFO ___FILE_ONLY___ For the latest full release notes, please visit:
139
+ https://cloud.google.com/sdk/release_notes
140
+
141
+
142
+ 2024-10-02 13:25:08,407 INFO ___FILE_ONLY___ Performing in place update...
143
+
144
+
145
+ 2024-10-02 13:25:08,409 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
146
+
147
+ 2024-10-02 13:25:08,409 INFO ___FILE_ONLY___ ╠═ Downloading: BigQuery Command Line Tool ═╣
148
+
149
+ 2024-10-02 13:25:08,409 INFO ___FILE_ONLY___ ╚
150
+ 2024-10-02 13:25:08,412 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
151
+ 2024-10-02 13:25:08,508 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/components/google-cloud-sdk-bq-20240816183020.tar.gz HTTP/1.1" 200 1818208
152
+ 2024-10-02 13:25:08,519 INFO ___FILE_ONLY___ ═
153
+ 2024-10-02 13:25:08,519 INFO ___FILE_ONLY___ ═
154
+ 2024-10-02 13:25:08,520 INFO ___FILE_ONLY___ ═
155
+ 2024-10-02 13:25:08,520 INFO ___FILE_ONLY___ ═
156
+ 2024-10-02 13:25:08,520 INFO ___FILE_ONLY___ ═
157
+ 2024-10-02 13:25:08,520 INFO ___FILE_ONLY___ ═
158
+ 2024-10-02 13:25:08,520 INFO ___FILE_ONLY___ ═
159
+ 2024-10-02 13:25:08,520 INFO ___FILE_ONLY___ ═
160
+ 2024-10-02 13:25:08,520 INFO ___FILE_ONLY___ ═
161
+ 2024-10-02 13:25:08,520 INFO ___FILE_ONLY___ ═
162
+ 2024-10-02 13:25:08,520 INFO ___FILE_ONLY___ ═
163
+ 2024-10-02 13:25:08,521 INFO ___FILE_ONLY___ ═
164
+ 2024-10-02 13:25:08,521 INFO ___FILE_ONLY___ ═
165
+ 2024-10-02 13:25:08,521 INFO ___FILE_ONLY___ ═
166
+ 2024-10-02 13:25:08,521 INFO ___FILE_ONLY___ ═
167
+ 2024-10-02 13:25:08,521 INFO ___FILE_ONLY___ ═
168
+ 2024-10-02 13:25:08,521 INFO ___FILE_ONLY___ ═
169
+ 2024-10-02 13:25:08,521 INFO ___FILE_ONLY___ ═
170
+ 2024-10-02 13:25:08,521 INFO ___FILE_ONLY___ ═
171
+ 2024-10-02 13:25:08,521 INFO ___FILE_ONLY___ ═
172
+ 2024-10-02 13:25:08,522 INFO ___FILE_ONLY___ ═
173
+ 2024-10-02 13:25:08,522 INFO ___FILE_ONLY___ ═
174
+ 2024-10-02 13:25:08,522 INFO ___FILE_ONLY___ ═
175
+ 2024-10-02 13:25:08,522 INFO ___FILE_ONLY___ ═
176
+ 2024-10-02 13:25:08,522 INFO ___FILE_ONLY___ ═
177
+ 2024-10-02 13:25:08,522 INFO ___FILE_ONLY___ ═
178
+ 2024-10-02 13:25:08,522 INFO ___FILE_ONLY___ ═
179
+ 2024-10-02 13:25:08,522 INFO ___FILE_ONLY___ ═
180
+ 2024-10-02 13:25:08,522 INFO ___FILE_ONLY___ ═
181
+ 2024-10-02 13:25:08,523 INFO ___FILE_ONLY___ ═
182
+ 2024-10-02 13:25:08,523 INFO ___FILE_ONLY___ ═
183
+ 2024-10-02 13:25:08,523 INFO ___FILE_ONLY___ ═
184
+ 2024-10-02 13:25:08,523 INFO ___FILE_ONLY___ ═
185
+ 2024-10-02 13:25:08,523 INFO ___FILE_ONLY___ ═
186
+ 2024-10-02 13:25:08,523 INFO ___FILE_ONLY___ ═
187
+ 2024-10-02 13:25:08,523 INFO ___FILE_ONLY___ ═
188
+ 2024-10-02 13:25:08,523 INFO ___FILE_ONLY___ ═
189
+ 2024-10-02 13:25:08,523 INFO ___FILE_ONLY___ ═
190
+ 2024-10-02 13:25:08,524 INFO ___FILE_ONLY___ ═
191
+ 2024-10-02 13:25:08,524 INFO ___FILE_ONLY___ ═
192
+ 2024-10-02 13:25:08,524 INFO ___FILE_ONLY___ ═
193
+ 2024-10-02 13:25:08,524 INFO ___FILE_ONLY___ ═
194
+ 2024-10-02 13:25:08,524 INFO ___FILE_ONLY___ ═
195
+ 2024-10-02 13:25:08,524 INFO ___FILE_ONLY___ ═
196
+ 2024-10-02 13:25:08,524 INFO ___FILE_ONLY___ ═
197
+ 2024-10-02 13:25:08,524 INFO ___FILE_ONLY___ ═
198
+ 2024-10-02 13:25:08,524 INFO ___FILE_ONLY___ ═
199
+ 2024-10-02 13:25:08,525 INFO ___FILE_ONLY___ ═
200
+ 2024-10-02 13:25:08,525 INFO ___FILE_ONLY___ ═
201
+ 2024-10-02 13:25:08,525 INFO ___FILE_ONLY___ ═
202
+ 2024-10-02 13:25:08,525 INFO ___FILE_ONLY___ ═
203
+ 2024-10-02 13:25:08,525 INFO ___FILE_ONLY___ ═
204
+ 2024-10-02 13:25:08,525 INFO ___FILE_ONLY___ ═
205
+ 2024-10-02 13:25:08,525 INFO ___FILE_ONLY___ ═
206
+ 2024-10-02 13:25:08,525 INFO ___FILE_ONLY___ ═
207
+ 2024-10-02 13:25:08,525 INFO ___FILE_ONLY___ ═
208
+ 2024-10-02 13:25:08,525 INFO ___FILE_ONLY___ ═
209
+ 2024-10-02 13:25:08,526 INFO ___FILE_ONLY___ ═
210
+ 2024-10-02 13:25:08,526 INFO ___FILE_ONLY___ ═
211
+ 2024-10-02 13:25:08,526 INFO ___FILE_ONLY___ ═
212
+ 2024-10-02 13:25:08,526 INFO ___FILE_ONLY___ ╝
213
+
214
+ 2024-10-02 13:25:08,528 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
215
+
216
+ 2024-10-02 13:25:08,528 INFO ___FILE_ONLY___ ╠═ Downloading: BigQuery Command Line Tool (Platform Spe... ═╣
217
+
218
+ 2024-10-02 13:25:08,528 INFO ___FILE_ONLY___ ╚
219
+ 2024-10-02 13:25:08,531 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
220
+ 2024-10-02 13:25:08,590 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/components/google-cloud-sdk-bq-nix-20240830134514.tar.gz HTTP/1.1" 200 1914
221
+ 2024-10-02 13:25:08,591 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
222
+ 2024-10-02 13:25:08,591 INFO ___FILE_ONLY___ ╝
223
+
224
+ 2024-10-02 13:25:08,593 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
225
+
226
+ 2024-10-02 13:25:08,593 INFO ___FILE_ONLY___ ╠═ Downloading: Bundled Python 3.11 ═╣
227
+
228
+ 2024-10-02 13:25:08,593 INFO ___FILE_ONLY___ ╚
229
+ 2024-10-02 13:25:08,593 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
230
+ 2024-10-02 13:25:08,593 INFO ___FILE_ONLY___ ╝
231
+
232
+ 2024-10-02 13:25:08,595 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
233
+
234
+ 2024-10-02 13:25:08,595 INFO ___FILE_ONLY___ ╠═ Downloading: Bundled Python 3.11 (Platform Specific) ═╣
235
+
236
+ 2024-10-02 13:25:08,595 INFO ___FILE_ONLY___ ╚
237
+ 2024-10-02 13:25:08,599 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
238
+ 2024-10-02 13:25:08,655 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/components/google-cloud-sdk-bundled-python3-unix-linux-x86_64-20240920144119.tar.gz HTTP/1.1" 200 78001783
239
+ 2024-10-02 13:25:09,005 INFO ___FILE_ONLY___ ═
240
+ 2024-10-02 13:25:09,007 INFO ___FILE_ONLY___ ═
241
+ 2024-10-02 13:25:09,009 INFO ___FILE_ONLY___ ═
242
+ 2024-10-02 13:25:09,011 INFO ___FILE_ONLY___ ═
243
+ 2024-10-02 13:25:09,013 INFO ___FILE_ONLY___ ═
244
+ 2024-10-02 13:25:09,015 INFO ___FILE_ONLY___ ═
245
+ 2024-10-02 13:25:09,017 INFO ___FILE_ONLY___ ═
246
+ 2024-10-02 13:25:09,019 INFO ___FILE_ONLY___ ═
247
+ 2024-10-02 13:25:09,021 INFO ___FILE_ONLY___ ═
248
+ 2024-10-02 13:25:09,023 INFO ___FILE_ONLY___ ═
249
+ 2024-10-02 13:25:09,025 INFO ___FILE_ONLY___ ═
250
+ 2024-10-02 13:25:09,027 INFO ___FILE_ONLY___ ═
251
+ 2024-10-02 13:25:09,029 INFO ___FILE_ONLY___ ═
252
+ 2024-10-02 13:25:09,031 INFO ___FILE_ONLY___ ═
253
+ 2024-10-02 13:25:09,034 INFO ___FILE_ONLY___ ═
254
+ 2024-10-02 13:25:09,036 INFO ___FILE_ONLY___ ═
255
+ 2024-10-02 13:25:09,038 INFO ___FILE_ONLY___ ═
256
+ 2024-10-02 13:25:09,040 INFO ___FILE_ONLY___ ═
257
+ 2024-10-02 13:25:09,042 INFO ___FILE_ONLY___ ═
258
+ 2024-10-02 13:25:09,044 INFO ___FILE_ONLY___ ═
259
+ 2024-10-02 13:25:09,046 INFO ___FILE_ONLY___ ═
260
+ 2024-10-02 13:25:09,048 INFO ___FILE_ONLY___ ═
261
+ 2024-10-02 13:25:09,050 INFO ___FILE_ONLY___ ═
262
+ 2024-10-02 13:25:09,053 INFO ___FILE_ONLY___ ═
263
+ 2024-10-02 13:25:09,056 INFO ___FILE_ONLY___ ═
264
+ 2024-10-02 13:25:09,058 INFO ___FILE_ONLY___ ═
265
+ 2024-10-02 13:25:09,060 INFO ___FILE_ONLY___ ═
266
+ 2024-10-02 13:25:09,062 INFO ___FILE_ONLY___ ═
267
+ 2024-10-02 13:25:09,064 INFO ___FILE_ONLY___ ═
268
+ 2024-10-02 13:25:09,067 INFO ___FILE_ONLY___ ═
269
+ 2024-10-02 13:25:09,069 INFO ___FILE_ONLY___ ═
270
+ 2024-10-02 13:25:09,070 INFO ___FILE_ONLY___ ═
271
+ 2024-10-02 13:25:09,072 INFO ___FILE_ONLY___ ═
272
+ 2024-10-02 13:25:09,074 INFO ___FILE_ONLY___ ═
273
+ 2024-10-02 13:25:09,075 INFO ___FILE_ONLY___ ═
274
+ 2024-10-02 13:25:09,077 INFO ___FILE_ONLY___ ═
275
+ 2024-10-02 13:25:09,079 INFO ___FILE_ONLY___ ═
276
+ 2024-10-02 13:25:09,080 INFO ___FILE_ONLY___ ═
277
+ 2024-10-02 13:25:09,082 INFO ___FILE_ONLY___ ═
278
+ 2024-10-02 13:25:09,084 INFO ___FILE_ONLY___ ═
279
+ 2024-10-02 13:25:09,085 INFO ___FILE_ONLY___ ═
280
+ 2024-10-02 13:25:09,087 INFO ___FILE_ONLY___ ═
281
+ 2024-10-02 13:25:09,089 INFO ___FILE_ONLY___ ═
282
+ 2024-10-02 13:25:09,090 INFO ___FILE_ONLY___ ═
283
+ 2024-10-02 13:25:09,092 INFO ___FILE_ONLY___ ═
284
+ 2024-10-02 13:25:09,094 INFO ___FILE_ONLY___ ═
285
+ 2024-10-02 13:25:09,095 INFO ___FILE_ONLY___ ═
286
+ 2024-10-02 13:25:09,097 INFO ___FILE_ONLY___ ═
287
+ 2024-10-02 13:25:09,099 INFO ___FILE_ONLY___ ═
288
+ 2024-10-02 13:25:09,101 INFO ___FILE_ONLY___ ═
289
+ 2024-10-02 13:25:09,102 INFO ___FILE_ONLY___ ═
290
+ 2024-10-02 13:25:09,104 INFO ___FILE_ONLY___ ═
291
+ 2024-10-02 13:25:09,106 INFO ___FILE_ONLY___ ═
292
+ 2024-10-02 13:25:09,107 INFO ___FILE_ONLY___ ═
293
+ 2024-10-02 13:25:09,109 INFO ___FILE_ONLY___ ═
294
+ 2024-10-02 13:25:09,111 INFO ___FILE_ONLY___ ═
295
+ 2024-10-02 13:25:09,113 INFO ___FILE_ONLY___ ═
296
+ 2024-10-02 13:25:09,114 INFO ___FILE_ONLY___ ═
297
+ 2024-10-02 13:25:09,116 INFO ___FILE_ONLY___ ═
298
+ 2024-10-02 13:25:09,118 INFO ___FILE_ONLY___ ═
299
+ 2024-10-02 13:25:09,118 INFO ___FILE_ONLY___ ╝
300
+
301
+ 2024-10-02 13:25:09,120 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
302
+
303
+ 2024-10-02 13:25:09,120 INFO ___FILE_ONLY___ ╠═ Downloading: Cloud Storage Command Line Tool ═╣
304
+
305
+ 2024-10-02 13:25:09,121 INFO ___FILE_ONLY___ ╚
306
+ 2024-10-02 13:25:09,130 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
307
+ 2024-10-02 13:25:09,190 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/components/google-cloud-sdk-gsutil-20240614142823.tar.gz HTTP/1.1" 200 11883175
308
+ 2024-10-02 13:25:09,232 INFO ___FILE_ONLY___ ═
309
+ 2024-10-02 13:25:09,232 INFO ___FILE_ONLY___ ═
310
+ 2024-10-02 13:25:09,233 INFO ___FILE_ONLY___ ═
311
+ 2024-10-02 13:25:09,233 INFO ___FILE_ONLY___ ═
312
+ 2024-10-02 13:25:09,234 INFO ___FILE_ONLY___ ═
313
+ 2024-10-02 13:25:09,234 INFO ___FILE_ONLY___ ═
314
+ 2024-10-02 13:25:09,234 INFO ___FILE_ONLY___ ═
315
+ 2024-10-02 13:25:09,235 INFO ___FILE_ONLY___ ═
316
+ 2024-10-02 13:25:09,235 INFO ___FILE_ONLY___ ═
317
+ 2024-10-02 13:25:09,235 INFO ___FILE_ONLY___ ═
318
+ 2024-10-02 13:25:09,236 INFO ___FILE_ONLY___ ═
319
+ 2024-10-02 13:25:09,236 INFO ___FILE_ONLY___ ═
320
+ 2024-10-02 13:25:09,236 INFO ___FILE_ONLY___ ═
321
+ 2024-10-02 13:25:09,237 INFO ___FILE_ONLY___ ═
322
+ 2024-10-02 13:25:09,237 INFO ___FILE_ONLY___ ═
323
+ 2024-10-02 13:25:09,237 INFO ___FILE_ONLY___ ═
324
+ 2024-10-02 13:25:09,237 INFO ___FILE_ONLY___ ═
325
+ 2024-10-02 13:25:09,238 INFO ___FILE_ONLY___ ═
326
+ 2024-10-02 13:25:09,238 INFO ___FILE_ONLY___ ═
327
+ 2024-10-02 13:25:09,238 INFO ___FILE_ONLY___ ═
328
+ 2024-10-02 13:25:09,239 INFO ___FILE_ONLY___ ═
329
+ 2024-10-02 13:25:09,239 INFO ___FILE_ONLY___ ═
330
+ 2024-10-02 13:25:09,239 INFO ___FILE_ONLY___ ═
331
+ 2024-10-02 13:25:09,240 INFO ___FILE_ONLY___ ═
332
+ 2024-10-02 13:25:09,240 INFO ___FILE_ONLY___ ═
333
+ 2024-10-02 13:25:09,240 INFO ___FILE_ONLY___ ═
334
+ 2024-10-02 13:25:09,241 INFO ___FILE_ONLY___ ═
335
+ 2024-10-02 13:25:09,241 INFO ___FILE_ONLY___ ═
336
+ 2024-10-02 13:25:09,241 INFO ___FILE_ONLY___ ═
337
+ 2024-10-02 13:25:09,242 INFO ___FILE_ONLY___ ═
338
+ 2024-10-02 13:25:09,242 INFO ___FILE_ONLY___ ═
339
+ 2024-10-02 13:25:09,242 INFO ___FILE_ONLY___ ═
340
+ 2024-10-02 13:25:09,243 INFO ___FILE_ONLY___ ═
341
+ 2024-10-02 13:25:09,243 INFO ___FILE_ONLY___ ═
342
+ 2024-10-02 13:25:09,243 INFO ___FILE_ONLY___ ═
343
+ 2024-10-02 13:25:09,244 INFO ___FILE_ONLY___ ═
344
+ 2024-10-02 13:25:09,244 INFO ___FILE_ONLY___ ═
345
+ 2024-10-02 13:25:09,244 INFO ___FILE_ONLY___ ═
346
+ 2024-10-02 13:25:09,245 INFO ___FILE_ONLY___ ═
347
+ 2024-10-02 13:25:09,245 INFO ___FILE_ONLY___ ═
348
+ 2024-10-02 13:25:09,245 INFO ___FILE_ONLY___ ═
349
+ 2024-10-02 13:25:09,246 INFO ___FILE_ONLY___ ═
350
+ 2024-10-02 13:25:09,246 INFO ___FILE_ONLY___ ═
351
+ 2024-10-02 13:25:09,246 INFO ___FILE_ONLY___ ═
352
+ 2024-10-02 13:25:09,247 INFO ___FILE_ONLY___ ═
353
+ 2024-10-02 13:25:09,247 INFO ___FILE_ONLY___ ═
354
+ 2024-10-02 13:25:09,247 INFO ___FILE_ONLY___ ═
355
+ 2024-10-02 13:25:09,248 INFO ___FILE_ONLY___ ═
356
+ 2024-10-02 13:25:09,248 INFO ___FILE_ONLY___ ═
357
+ 2024-10-02 13:25:09,248 INFO ___FILE_ONLY___ ═
358
+ 2024-10-02 13:25:09,249 INFO ___FILE_ONLY___ ═
359
+ 2024-10-02 13:25:09,249 INFO ___FILE_ONLY___ ═
360
+ 2024-10-02 13:25:09,249 INFO ___FILE_ONLY___ ═
361
+ 2024-10-02 13:25:09,250 INFO ___FILE_ONLY___ ═
362
+ 2024-10-02 13:25:09,250 INFO ___FILE_ONLY___ ═
363
+ 2024-10-02 13:25:09,250 INFO ___FILE_ONLY___ ═
364
+ 2024-10-02 13:25:09,251 INFO ___FILE_ONLY___ ═
365
+ 2024-10-02 13:25:09,251 INFO ___FILE_ONLY___ ═
366
+ 2024-10-02 13:25:09,251 INFO ___FILE_ONLY___ ═
367
+ 2024-10-02 13:25:09,252 INFO ___FILE_ONLY___ ═
368
+ 2024-10-02 13:25:09,252 INFO ___FILE_ONLY___ ╝
369
+
370
+ 2024-10-02 13:25:09,254 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
371
+
372
+ 2024-10-02 13:25:09,254 INFO ___FILE_ONLY___ ╠═ Downloading: Cloud Storage Command Line Tool (Platfor... ═╣
373
+
374
+ 2024-10-02 13:25:09,254 INFO ___FILE_ONLY___ ╚
375
+ 2024-10-02 13:25:09,258 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
376
+ 2024-10-02 13:25:09,316 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/components/google-cloud-sdk-gsutil-nix-20240830134514.tar.gz HTTP/1.1" 200 1928
377
+ 2024-10-02 13:25:09,317 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
378
+ 2024-10-02 13:25:09,317 INFO ___FILE_ONLY___ ╝
379
+
380
+ 2024-10-02 13:25:09,319 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
381
+
382
+ 2024-10-02 13:25:09,319 INFO ___FILE_ONLY___ ╠═ Downloading: Default set of gcloud commands ═╣
383
+
384
+ 2024-10-02 13:25:09,319 INFO ___FILE_ONLY___ ╚
385
+ 2024-10-02 13:25:09,319 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
386
+ 2024-10-02 13:25:09,319 INFO ___FILE_ONLY___ ╝
387
+
388
+ 2024-10-02 13:25:09,321 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
389
+
390
+ 2024-10-02 13:25:09,321 INFO ___FILE_ONLY___ ╠═ Downloading: Google Cloud CLI Core Libraries (Platfor... ═╣
391
+
392
+ 2024-10-02 13:25:09,321 INFO ___FILE_ONLY___ ╚
393
+ 2024-10-02 13:25:09,325 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
394
+ 2024-10-02 13:25:09,389 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/components/google-cloud-sdk-core-nix-20240830134514.tar.gz HTTP/1.1" 200 2306
395
+ 2024-10-02 13:25:09,390 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
396
+ 2024-10-02 13:25:09,390 INFO ___FILE_ONLY___ ╝
397
+
398
+ 2024-10-02 13:25:09,392 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
399
+
400
+ 2024-10-02 13:25:09,393 INFO ___FILE_ONLY___ ╠═ Downloading: Google Cloud CRC32C Hash Tool ═╣
401
+
402
+ 2024-10-02 13:25:09,393 INFO ___FILE_ONLY___ ╚
403
+ 2024-10-02 13:25:09,393 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
404
+ 2024-10-02 13:25:09,393 INFO ___FILE_ONLY___ ╝
405
+
406
+ 2024-10-02 13:25:09,395 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
407
+
408
+ 2024-10-02 13:25:09,395 INFO ___FILE_ONLY___ ╠═ Downloading: Google Cloud CRC32C Hash Tool (Platform ... ═╣
409
+
410
+ 2024-10-02 13:25:09,395 INFO ___FILE_ONLY___ ╚
411
+ 2024-10-02 13:25:09,398 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
412
+ 2024-10-02 13:25:09,457 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/components/google-cloud-sdk-gcloud-crc32c-linux-x86_64-20240712142834.tar.gz HTTP/1.1" 200 1350263
413
+ 2024-10-02 13:25:09,468 INFO ___FILE_ONLY___ ═
414
+ 2024-10-02 13:25:09,468 INFO ___FILE_ONLY___ ═
415
+ 2024-10-02 13:25:09,468 INFO ___FILE_ONLY___ ═
416
+ 2024-10-02 13:25:09,468 INFO ___FILE_ONLY___ ═
417
+ 2024-10-02 13:25:09,468 INFO ___FILE_ONLY___ ═
418
+ 2024-10-02 13:25:09,468 INFO ___FILE_ONLY___ ═
419
+ 2024-10-02 13:25:09,468 INFO ___FILE_ONLY___ ═
420
+ 2024-10-02 13:25:09,468 INFO ___FILE_ONLY___ ═
421
+ 2024-10-02 13:25:09,468 INFO ___FILE_ONLY___ ═
422
+ 2024-10-02 13:25:09,468 INFO ___FILE_ONLY___ ═
423
+ 2024-10-02 13:25:09,469 INFO ___FILE_ONLY___ ═
424
+ 2024-10-02 13:25:09,469 INFO ___FILE_ONLY___ ═
425
+ 2024-10-02 13:25:09,469 INFO ___FILE_ONLY___ ═
426
+ 2024-10-02 13:25:09,469 INFO ___FILE_ONLY___ ═
427
+ 2024-10-02 13:25:09,469 INFO ___FILE_ONLY___ ═
428
+ 2024-10-02 13:25:09,469 INFO ___FILE_ONLY___ ═
429
+ 2024-10-02 13:25:09,469 INFO ___FILE_ONLY___ ═
430
+ 2024-10-02 13:25:09,469 INFO ___FILE_ONLY___ ═
431
+ 2024-10-02 13:25:09,469 INFO ___FILE_ONLY___ ═
432
+ 2024-10-02 13:25:09,469 INFO ___FILE_ONLY___ ═
433
+ 2024-10-02 13:25:09,470 INFO ___FILE_ONLY___ ═
434
+ 2024-10-02 13:25:09,470 INFO ___FILE_ONLY___ ═
435
+ 2024-10-02 13:25:09,470 INFO ___FILE_ONLY___ ═
436
+ 2024-10-02 13:25:09,470 INFO ___FILE_ONLY___ ═
437
+ 2024-10-02 13:25:09,470 INFO ___FILE_ONLY___ ═
438
+ 2024-10-02 13:25:09,470 INFO ___FILE_ONLY___ ═
439
+ 2024-10-02 13:25:09,470 INFO ___FILE_ONLY___ ═
440
+ 2024-10-02 13:25:09,470 INFO ___FILE_ONLY___ ═
441
+ 2024-10-02 13:25:09,470 INFO ___FILE_ONLY___ ═
442
+ 2024-10-02 13:25:09,471 INFO ___FILE_ONLY___ ═
443
+ 2024-10-02 13:25:09,471 INFO ___FILE_ONLY___ ═
444
+ 2024-10-02 13:25:09,471 INFO ___FILE_ONLY___ ═
445
+ 2024-10-02 13:25:09,471 INFO ___FILE_ONLY___ ═
446
+ 2024-10-02 13:25:09,471 INFO ___FILE_ONLY___ ═
447
+ 2024-10-02 13:25:09,471 INFO ___FILE_ONLY___ ═
448
+ 2024-10-02 13:25:09,471 INFO ___FILE_ONLY___ ═
449
+ 2024-10-02 13:25:09,471 INFO ___FILE_ONLY___ ═
450
+ 2024-10-02 13:25:09,471 INFO ___FILE_ONLY___ ═
451
+ 2024-10-02 13:25:09,471 INFO ___FILE_ONLY___ ═
452
+ 2024-10-02 13:25:09,471 INFO ___FILE_ONLY___ ═
453
+ 2024-10-02 13:25:09,472 INFO ___FILE_ONLY___ ═
454
+ 2024-10-02 13:25:09,472 INFO ___FILE_ONLY___ ═
455
+ 2024-10-02 13:25:09,472 INFO ___FILE_ONLY___ ═
456
+ 2024-10-02 13:25:09,472 INFO ___FILE_ONLY___ ═
457
+ 2024-10-02 13:25:09,472 INFO ___FILE_ONLY___ ═
458
+ 2024-10-02 13:25:09,472 INFO ___FILE_ONLY___ ═
459
+ 2024-10-02 13:25:09,472 INFO ___FILE_ONLY___ ═
460
+ 2024-10-02 13:25:09,472 INFO ___FILE_ONLY___ ═
461
+ 2024-10-02 13:25:09,472 INFO ___FILE_ONLY___ ═
462
+ 2024-10-02 13:25:09,472 INFO ___FILE_ONLY___ ═
463
+ 2024-10-02 13:25:09,473 INFO ___FILE_ONLY___ ═
464
+ 2024-10-02 13:25:09,473 INFO ___FILE_ONLY___ ═
465
+ 2024-10-02 13:25:09,473 INFO ___FILE_ONLY___ ═
466
+ 2024-10-02 13:25:09,473 INFO ___FILE_ONLY___ ═
467
+ 2024-10-02 13:25:09,473 INFO ___FILE_ONLY___ ═
468
+ 2024-10-02 13:25:09,473 INFO ___FILE_ONLY___ ═
469
+ 2024-10-02 13:25:09,473 INFO ___FILE_ONLY___ ═
470
+ 2024-10-02 13:25:09,473 INFO ___FILE_ONLY___ ═
471
+ 2024-10-02 13:25:09,473 INFO ___FILE_ONLY___ ═
472
+ 2024-10-02 13:25:09,473 INFO ___FILE_ONLY___ ═
473
+ 2024-10-02 13:25:09,474 INFO ___FILE_ONLY___ ╝
474
+
475
+ 2024-10-02 13:25:09,475 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
476
+
477
+ 2024-10-02 13:25:09,476 INFO ___FILE_ONLY___ ╠═ Downloading: gcloud cli dependencies (Platform Specific) ═╣
478
+
479
+ 2024-10-02 13:25:09,476 INFO ___FILE_ONLY___ ╚
480
+ 2024-10-02 13:25:09,479 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
481
+ 2024-10-02 13:25:09,539 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/components/google-cloud-sdk-gcloud-deps-linux-x86_64-20210416153011.tar.gz HTTP/1.1" 200 104
482
+ 2024-10-02 13:25:09,539 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
483
+ 2024-10-02 13:25:09,540 INFO ___FILE_ONLY___ ╝
484
+
485
+ 2024-10-02 13:25:09,542 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
486
+
487
+ 2024-10-02 13:25:09,542 INFO ___FILE_ONLY___ ╠═ Installing: BigQuery Command Line Tool ═╣
488
+
489
+ 2024-10-02 13:25:09,542 INFO ___FILE_ONLY___ ╚
490
+ 2024-10-02 13:25:09,663 INFO ___FILE_ONLY___ ═
491
+ 2024-10-02 13:25:09,666 INFO ___FILE_ONLY___ ═
492
+ 2024-10-02 13:25:09,669 INFO ___FILE_ONLY___ ═
493
+ 2024-10-02 13:25:09,672 INFO ___FILE_ONLY___ ═
494
+ 2024-10-02 13:25:09,675 INFO ___FILE_ONLY___ ═
495
+ 2024-10-02 13:25:09,677 INFO ___FILE_ONLY___ ═
496
+ 2024-10-02 13:25:09,679 INFO ___FILE_ONLY___ ═
497
+ 2024-10-02 13:25:09,682 INFO ___FILE_ONLY___ ═
498
+ 2024-10-02 13:25:09,685 INFO ___FILE_ONLY___ ═
499
+ 2024-10-02 13:25:09,687 INFO ___FILE_ONLY___ ═
500
+ 2024-10-02 13:25:09,689 INFO ___FILE_ONLY___ ═
501
+ 2024-10-02 13:25:09,692 INFO ___FILE_ONLY___ ═
502
+ 2024-10-02 13:25:09,695 INFO ___FILE_ONLY___ ═
503
+ 2024-10-02 13:25:09,697 INFO ___FILE_ONLY___ ═
504
+ 2024-10-02 13:25:09,700 INFO ___FILE_ONLY___ ═
505
+ 2024-10-02 13:25:09,702 INFO ___FILE_ONLY___ ═
506
+ 2024-10-02 13:25:09,705 INFO ___FILE_ONLY___ ═
507
+ 2024-10-02 13:25:09,708 INFO ___FILE_ONLY___ ═
508
+ 2024-10-02 13:25:09,711 INFO ___FILE_ONLY___ ═
509
+ 2024-10-02 13:25:09,714 INFO ___FILE_ONLY___ ═
510
+ 2024-10-02 13:25:09,716 INFO ___FILE_ONLY___ ═
511
+ 2024-10-02 13:25:09,719 INFO ___FILE_ONLY___ ═
512
+ 2024-10-02 13:25:09,720 INFO ___FILE_ONLY___ ═
513
+ 2024-10-02 13:25:09,723 INFO ___FILE_ONLY___ ═
514
+ 2024-10-02 13:25:09,726 INFO ___FILE_ONLY___ ═
515
+ 2024-10-02 13:25:09,728 INFO ___FILE_ONLY___ ═
516
+ 2024-10-02 13:25:09,730 INFO ___FILE_ONLY___ ═
517
+ 2024-10-02 13:25:09,735 INFO ___FILE_ONLY___ ═
518
+ 2024-10-02 13:25:09,737 INFO ___FILE_ONLY___ ═
519
+ 2024-10-02 13:25:09,739 INFO ___FILE_ONLY___ ═
520
+ 2024-10-02 13:25:09,741 INFO ___FILE_ONLY___ ═
521
+ 2024-10-02 13:25:09,744 INFO ___FILE_ONLY___ ═
522
+ 2024-10-02 13:25:09,747 INFO ___FILE_ONLY___ ═
523
+ 2024-10-02 13:25:09,752 INFO ___FILE_ONLY___ ═
524
+ 2024-10-02 13:25:09,760 INFO ___FILE_ONLY___ ═
525
+ 2024-10-02 13:25:09,761 INFO ___FILE_ONLY___ ═
526
+ 2024-10-02 13:25:09,764 INFO ___FILE_ONLY___ ═
527
+ 2024-10-02 13:25:09,769 INFO ___FILE_ONLY___ ═
528
+ 2024-10-02 13:25:09,771 INFO ___FILE_ONLY___ ═
529
+ 2024-10-02 13:25:09,774 INFO ___FILE_ONLY___ ═
530
+ 2024-10-02 13:25:09,776 INFO ___FILE_ONLY___ ═
531
+ 2024-10-02 13:25:09,779 INFO ___FILE_ONLY___ ═
532
+ 2024-10-02 13:25:09,783 INFO ___FILE_ONLY___ ═
533
+ 2024-10-02 13:25:09,785 INFO ___FILE_ONLY___ ═
534
+ 2024-10-02 13:25:09,787 INFO ___FILE_ONLY___ ═
535
+ 2024-10-02 13:25:09,790 INFO ___FILE_ONLY___ ═
536
+ 2024-10-02 13:25:09,792 INFO ___FILE_ONLY___ ═
537
+ 2024-10-02 13:25:09,795 INFO ___FILE_ONLY___ ═
538
+ 2024-10-02 13:25:09,797 INFO ___FILE_ONLY___ ═
539
+ 2024-10-02 13:25:09,799 INFO ___FILE_ONLY___ ═
540
+ 2024-10-02 13:25:09,801 INFO ___FILE_ONLY___ ═
541
+ 2024-10-02 13:25:09,803 INFO ___FILE_ONLY___ ═
542
+ 2024-10-02 13:25:09,806 INFO ___FILE_ONLY___ ═
543
+ 2024-10-02 13:25:09,808 INFO ___FILE_ONLY___ ═
544
+ 2024-10-02 13:25:09,810 INFO ___FILE_ONLY___ ═
545
+ 2024-10-02 13:25:09,812 INFO ___FILE_ONLY___ ═
546
+ 2024-10-02 13:25:09,815 INFO ___FILE_ONLY___ ═
547
+ 2024-10-02 13:25:09,818 INFO ___FILE_ONLY___ ═
548
+ 2024-10-02 13:25:09,820 INFO ___FILE_ONLY___ ═
549
+ 2024-10-02 13:25:09,823 INFO ___FILE_ONLY___ ═
550
+ 2024-10-02 13:25:09,823 INFO ___FILE_ONLY___ ╝
551
+
552
+ 2024-10-02 13:25:09,838 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
553
+
554
+ 2024-10-02 13:25:09,839 INFO ___FILE_ONLY___ ╠═ Installing: BigQuery Command Line Tool (Platform Spec... ═╣
555
+
556
+ 2024-10-02 13:25:09,839 INFO ___FILE_ONLY___ ╚
557
+ 2024-10-02 13:25:09,840 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
558
+ 2024-10-02 13:25:09,840 INFO ___FILE_ONLY___ ╝
559
+
560
+ 2024-10-02 13:25:09,847 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
561
+
562
+ 2024-10-02 13:25:09,847 INFO ___FILE_ONLY___ ╠═ Installing: Bundled Python 3.11 ═╣
563
+
564
+ 2024-10-02 13:25:09,847 INFO ___FILE_ONLY___ ╚
565
+ 2024-10-02 13:25:09,852 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
566
+ 2024-10-02 13:25:09,852 INFO ___FILE_ONLY___ ╝
567
+
568
+ 2024-10-02 13:25:09,854 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
569
+
570
+ 2024-10-02 13:25:09,854 INFO ___FILE_ONLY___ ╠═ Installing: Bundled Python 3.11 (Platform Specific) ═╣
571
+
572
+ 2024-10-02 13:25:09,854 INFO ___FILE_ONLY___ ╚
573
+ 2024-10-02 13:25:11,953 INFO ___FILE_ONLY___ ═
574
+ 2024-10-02 13:25:11,970 INFO ___FILE_ONLY___ ═
575
+ 2024-10-02 13:25:11,985 INFO ___FILE_ONLY___ ═
576
+ 2024-10-02 13:25:11,998 INFO ___FILE_ONLY___ ═
577
+ 2024-10-02 13:25:12,011 INFO ___FILE_ONLY___ ═
578
+ 2024-10-02 13:25:12,025 INFO ___FILE_ONLY___ ═
579
+ 2024-10-02 13:25:12,039 INFO ___FILE_ONLY___ ═
580
+ 2024-10-02 13:25:12,052 INFO ___FILE_ONLY___ ═
581
+ 2024-10-02 13:25:12,066 INFO ___FILE_ONLY___ ═
582
+ 2024-10-02 13:25:12,079 INFO ___FILE_ONLY___ ═
583
+ 2024-10-02 13:25:12,093 INFO ___FILE_ONLY___ ═
584
+ 2024-10-02 13:25:12,105 INFO ___FILE_ONLY___ ═
585
+ 2024-10-02 13:25:12,119 INFO ___FILE_ONLY___ ═
586
+ 2024-10-02 13:25:12,133 INFO ___FILE_ONLY___ ═
587
+ 2024-10-02 13:25:12,147 INFO ___FILE_ONLY___ ═
588
+ 2024-10-02 13:25:12,160 INFO ___FILE_ONLY___ ═
589
+ 2024-10-02 13:25:12,174 INFO ___FILE_ONLY___ ═
590
+ 2024-10-02 13:25:12,186 INFO ___FILE_ONLY___ ═
591
+ 2024-10-02 13:25:12,200 INFO ___FILE_ONLY___ ═
592
+ 2024-10-02 13:25:12,213 INFO ___FILE_ONLY___ ═
593
+ 2024-10-02 13:25:12,225 INFO ___FILE_ONLY___ ═
594
+ 2024-10-02 13:25:12,239 INFO ___FILE_ONLY___ ═
595
+ 2024-10-02 13:25:12,252 INFO ___FILE_ONLY___ ═
596
+ 2024-10-02 13:25:12,264 INFO ___FILE_ONLY___ ═
597
+ 2024-10-02 13:25:12,279 INFO ___FILE_ONLY___ ═
598
+ 2024-10-02 13:25:12,292 INFO ___FILE_ONLY___ ═
599
+ 2024-10-02 13:25:12,305 INFO ___FILE_ONLY___ ═
600
+ 2024-10-02 13:25:12,318 INFO ___FILE_ONLY___ ═
601
+ 2024-10-02 13:25:12,331 INFO ___FILE_ONLY___ ═
602
+ 2024-10-02 13:25:12,344 INFO ___FILE_ONLY___ ═
603
+ 2024-10-02 13:25:12,357 INFO ___FILE_ONLY___ ═
604
+ 2024-10-02 13:25:12,370 INFO ___FILE_ONLY___ ═
605
+ 2024-10-02 13:25:12,383 INFO ___FILE_ONLY___ ═
606
+ 2024-10-02 13:25:12,395 INFO ___FILE_ONLY___ ═
607
+ 2024-10-02 13:25:12,408 INFO ___FILE_ONLY___ ═
608
+ 2024-10-02 13:25:12,421 INFO ___FILE_ONLY___ ═
609
+ 2024-10-02 13:25:13,152 INFO ___FILE_ONLY___ ═
610
+ 2024-10-02 13:25:13,180 INFO ___FILE_ONLY___ ═
611
+ 2024-10-02 13:25:13,206 INFO ___FILE_ONLY___ ═
612
+ 2024-10-02 13:25:13,228 INFO ___FILE_ONLY___ ═
613
+ 2024-10-02 13:25:13,251 INFO ___FILE_ONLY___ ═
614
+ 2024-10-02 13:25:13,393 INFO ___FILE_ONLY___ ═
615
+ 2024-10-02 13:25:13,423 INFO ___FILE_ONLY___ ═
616
+ 2024-10-02 13:25:13,444 INFO ___FILE_ONLY___ ═
617
+ 2024-10-02 13:25:13,463 INFO ___FILE_ONLY___ ═
618
+ 2024-10-02 13:25:13,484 INFO ___FILE_ONLY___ ═
619
+ 2024-10-02 13:25:13,514 INFO ___FILE_ONLY___ ═
620
+ 2024-10-02 13:25:13,536 INFO ___FILE_ONLY___ ═
621
+ 2024-10-02 13:25:13,554 INFO ___FILE_ONLY___ ═
622
+ 2024-10-02 13:25:13,569 INFO ___FILE_ONLY___ ═
623
+ 2024-10-02 13:25:13,660 INFO ___FILE_ONLY___ ═
624
+ 2024-10-02 13:25:13,680 INFO ___FILE_ONLY___ ═
625
+ 2024-10-02 13:25:13,700 INFO ___FILE_ONLY___ ═
626
+ 2024-10-02 13:25:13,719 INFO ___FILE_ONLY___ ═
627
+ 2024-10-02 13:25:13,763 INFO ___FILE_ONLY___ ═
628
+ 2024-10-02 13:25:14,127 INFO ___FILE_ONLY___ ═
629
+ 2024-10-02 13:25:14,146 INFO ___FILE_ONLY___ ═
630
+ 2024-10-02 13:25:14,167 INFO ___FILE_ONLY___ ═
631
+ 2024-10-02 13:25:14,185 INFO ___FILE_ONLY___ ═
632
+ 2024-10-02 13:25:14,578 INFO ___FILE_ONLY___ ═
633
+ 2024-10-02 13:25:14,579 INFO ___FILE_ONLY___ ╝
634
+
635
+ 2024-10-02 13:25:14,684 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
636
+
637
+ 2024-10-02 13:25:14,684 INFO ___FILE_ONLY___ ╠═ Installing: Cloud Storage Command Line Tool ═╣
638
+
639
+ 2024-10-02 13:25:14,684 INFO ___FILE_ONLY___ ╚
640
+ 2024-10-02 13:25:15,337 INFO ___FILE_ONLY___ ═
641
+ 2024-10-02 13:25:15,349 INFO ___FILE_ONLY___ ═
642
+ 2024-10-02 13:25:15,363 INFO ___FILE_ONLY___ ═
643
+ 2024-10-02 13:25:15,382 INFO ___FILE_ONLY___ ═
644
+ 2024-10-02 13:25:15,398 INFO ___FILE_ONLY___ ═
645
+ 2024-10-02 13:25:15,414 INFO ___FILE_ONLY___ ═
646
+ 2024-10-02 13:25:15,428 INFO ___FILE_ONLY___ ═
647
+ 2024-10-02 13:25:15,450 INFO ___FILE_ONLY___ ═
648
+ 2024-10-02 13:25:15,463 INFO ___FILE_ONLY___ ═
649
+ 2024-10-02 13:25:15,474 INFO ___FILE_ONLY___ ═
650
+ 2024-10-02 13:25:15,486 INFO ___FILE_ONLY___ ═
651
+ 2024-10-02 13:25:15,524 INFO ___FILE_ONLY___ ═
652
+ 2024-10-02 13:25:15,536 INFO ___FILE_ONLY___ ═
653
+ 2024-10-02 13:25:15,550 INFO ___FILE_ONLY___ ═
654
+ 2024-10-02 13:25:15,563 INFO ___FILE_ONLY___ ═
655
+ 2024-10-02 13:25:15,572 INFO ___FILE_ONLY___ ═
656
+ 2024-10-02 13:25:15,582 INFO ___FILE_ONLY___ ═
657
+ 2024-10-02 13:25:15,593 INFO ___FILE_ONLY___ ═
658
+ 2024-10-02 13:25:15,603 INFO ___FILE_ONLY___ ═
659
+ 2024-10-02 13:25:15,615 INFO ___FILE_ONLY___ ═
660
+ 2024-10-02 13:25:15,625 INFO ___FILE_ONLY___ ═
661
+ 2024-10-02 13:25:15,635 INFO ___FILE_ONLY___ ═
662
+ 2024-10-02 13:25:15,645 INFO ___FILE_ONLY___ ═
663
+ 2024-10-02 13:25:15,658 INFO ___FILE_ONLY___ ═
664
+ 2024-10-02 13:25:15,668 INFO ___FILE_ONLY___ ═
665
+ 2024-10-02 13:25:15,681 INFO ___FILE_ONLY___ ═
666
+ 2024-10-02 13:25:15,696 INFO ___FILE_ONLY___ ═
667
+ 2024-10-02 13:25:15,711 INFO ___FILE_ONLY___ ═
668
+ 2024-10-02 13:25:15,724 INFO ___FILE_ONLY___ ═
669
+ 2024-10-02 13:25:15,743 INFO ___FILE_ONLY___ ═
670
+ 2024-10-02 13:25:15,754 INFO ___FILE_ONLY___ ═
671
+ 2024-10-02 13:25:15,766 INFO ___FILE_ONLY___ ═
672
+ 2024-10-02 13:25:15,777 INFO ___FILE_ONLY___ ═
673
+ 2024-10-02 13:25:15,793 INFO ___FILE_ONLY___ ═
674
+ 2024-10-02 13:25:15,804 INFO ___FILE_ONLY___ ═
675
+ 2024-10-02 13:25:15,816 INFO ___FILE_ONLY___ ═
676
+ 2024-10-02 13:25:15,831 INFO ___FILE_ONLY___ ═
677
+ 2024-10-02 13:25:15,846 INFO ___FILE_ONLY___ ═
678
+ 2024-10-02 13:25:15,861 INFO ___FILE_ONLY___ ═
679
+ 2024-10-02 13:25:15,878 INFO ___FILE_ONLY___ ═
680
+ 2024-10-02 13:25:15,892 INFO ___FILE_ONLY___ ═
681
+ 2024-10-02 13:25:15,903 INFO ___FILE_ONLY___ ═
682
+ 2024-10-02 13:25:15,914 INFO ___FILE_ONLY___ ═
683
+ 2024-10-02 13:25:15,928 INFO ___FILE_ONLY___ ═
684
+ 2024-10-02 13:25:15,942 INFO ___FILE_ONLY___ ═
685
+ 2024-10-02 13:25:15,957 INFO ___FILE_ONLY___ ═
686
+ 2024-10-02 13:25:15,971 INFO ___FILE_ONLY___ ═
687
+ 2024-10-02 13:25:15,984 INFO ___FILE_ONLY___ ═
688
+ 2024-10-02 13:25:16,000 INFO ___FILE_ONLY___ ═
689
+ 2024-10-02 13:25:16,014 INFO ___FILE_ONLY___ ═
690
+ 2024-10-02 13:25:16,026 INFO ___FILE_ONLY___ ═
691
+ 2024-10-02 13:25:16,039 INFO ___FILE_ONLY___ ═
692
+ 2024-10-02 13:25:16,053 INFO ___FILE_ONLY___ ═
693
+ 2024-10-02 13:25:16,065 INFO ___FILE_ONLY___ ═
694
+ 2024-10-02 13:25:16,077 INFO ___FILE_ONLY___ ═
695
+ 2024-10-02 13:25:16,089 INFO ___FILE_ONLY___ ═
696
+ 2024-10-02 13:25:16,101 INFO ___FILE_ONLY___ ═
697
+ 2024-10-02 13:25:16,124 INFO ___FILE_ONLY___ ═
698
+ 2024-10-02 13:25:16,142 INFO ___FILE_ONLY___ ═
699
+ 2024-10-02 13:25:16,161 INFO ___FILE_ONLY___ ═
700
+ 2024-10-02 13:25:16,162 INFO ___FILE_ONLY___ ╝
701
+
702
+ 2024-10-02 13:25:16,235 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
703
+
704
+ 2024-10-02 13:25:16,235 INFO ___FILE_ONLY___ ╠═ Installing: Cloud Storage Command Line Tool (Platform... ═╣
705
+
706
+ 2024-10-02 13:25:16,235 INFO ___FILE_ONLY___ ╚
707
+ 2024-10-02 13:25:16,236 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
708
+ 2024-10-02 13:25:16,237 INFO ___FILE_ONLY___ ╝
709
+
710
+ 2024-10-02 13:25:16,244 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
711
+
712
+ 2024-10-02 13:25:16,244 INFO ___FILE_ONLY___ ╠═ Installing: Default set of gcloud commands ═╣
713
+
714
+ 2024-10-02 13:25:16,244 INFO ___FILE_ONLY___ ╚
715
+ 2024-10-02 13:25:16,250 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
716
+ 2024-10-02 13:25:16,250 INFO ___FILE_ONLY___ ╝
717
+
718
+ 2024-10-02 13:25:16,251 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
719
+
720
+ 2024-10-02 13:25:16,252 INFO ___FILE_ONLY___ ╠═ Installing: Google Cloud CLI Core Libraries (Platform... ═╣
721
+
722
+ 2024-10-02 13:25:16,252 INFO ___FILE_ONLY___ ╚
723
+ 2024-10-02 13:25:16,253 INFO ___FILE_ONLY___ ══════════════════════════════
724
+ 2024-10-02 13:25:16,253 INFO ___FILE_ONLY___ ══════════════════════════════
725
+ 2024-10-02 13:25:16,253 INFO ___FILE_ONLY___ ╝
726
+
727
+ 2024-10-02 13:25:16,260 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
728
+
729
+ 2024-10-02 13:25:16,261 INFO ___FILE_ONLY___ ╠═ Installing: Google Cloud CRC32C Hash Tool ═╣
730
+
731
+ 2024-10-02 13:25:16,261 INFO ___FILE_ONLY___ ╚
732
+ 2024-10-02 13:25:16,266 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
733
+ 2024-10-02 13:25:16,266 INFO ___FILE_ONLY___ ╝
734
+
735
+ 2024-10-02 13:25:16,268 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
736
+
737
+ 2024-10-02 13:25:16,268 INFO ___FILE_ONLY___ ╠═ Installing: Google Cloud CRC32C Hash Tool (Platform S... ═╣
738
+
739
+ 2024-10-02 13:25:16,268 INFO ___FILE_ONLY___ ╚
740
+ 2024-10-02 13:25:16,302 INFO ___FILE_ONLY___ ══════════════════════════════
741
+ 2024-10-02 13:25:16,302 INFO ___FILE_ONLY___ ══════════════════════════════
742
+ 2024-10-02 13:25:16,302 INFO ___FILE_ONLY___ ╝
743
+
744
+ 2024-10-02 13:25:16,310 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
745
+
746
+ 2024-10-02 13:25:16,310 INFO ___FILE_ONLY___ ╠═ Installing: gcloud cli dependencies (Platform Specific) ═╣
747
+
748
+ 2024-10-02 13:25:16,311 INFO ___FILE_ONLY___ ╚
749
+ 2024-10-02 13:25:16,311 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
750
+ 2024-10-02 13:25:16,311 INFO ___FILE_ONLY___ ╝
751
+
752
+ 2024-10-02 13:25:16,320 DEBUG root Updating notification cache...
753
+ 2024-10-02 13:25:16,321 INFO ___FILE_ONLY___
754
+
755
+ 2024-10-02 13:25:16,323 INFO ___FILE_ONLY___ Performing post processing steps...
756
+ 2024-10-02 13:25:16,323 DEBUG root Executing command: ['/tools/google-cloud-sdk/bin/gcloud', 'components', 'post-process']
757
+ 2024-10-02 13:25:27,561 DEBUG ___FILE_ONLY___
758
+ 2024-10-02 13:25:27,562 DEBUG ___FILE_ONLY___
759
+ 2024-10-02 13:25:27,650 INFO ___FILE_ONLY___
760
+ Update done!
761
+
762
+
763
+ 2024-10-02 13:25:27,654 DEBUG root Chosen display Format:none
764
+ 2024-10-02 13:25:27,654 INFO root Display format: "none"
.config/logs/2024.10.02/13.25.16.787495.log ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ 2024-10-02 13:25:16,788 DEBUG root Loaded Command Group: ['gcloud', 'components']
2
+ 2024-10-02 13:25:16,790 DEBUG root Loaded Command Group: ['gcloud', 'components', 'post_process']
3
+ 2024-10-02 13:25:16,792 DEBUG root Running [gcloud.components.post-process] with arguments: []
4
+ 2024-10-02 13:25:27,477 DEBUG root Chosen display Format:none
5
+ 2024-10-02 13:25:27,477 INFO root Display format: "none"
.config/logs/2024.10.02/13.25.28.231611.log ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-10-02 13:25:28,232 DEBUG root Loaded Command Group: ['gcloud', 'components']
2
+ 2024-10-02 13:25:28,234 DEBUG root Loaded Command Group: ['gcloud', 'components', 'update']
3
+ 2024-10-02 13:25:28,237 DEBUG root Running [gcloud.components.update] with arguments: [--quiet: "True", COMPONENT-IDS:8: "['gcloud', 'core', 'bq', 'gsutil', 'compute', 'preview', 'alpha', 'beta']"]
4
+ 2024-10-02 13:25:28,238 INFO ___FILE_ONLY___ Beginning update. This process may take several minutes.
5
+
6
+ 2024-10-02 13:25:28,248 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
7
+ 2024-10-02 13:25:28,308 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/components-2.json HTTP/1.1" 200 227002
8
+ 2024-10-02 13:25:28,327 WARNING root Component [compute] no longer exists.
9
+ 2024-10-02 13:25:28,327 WARNING root Component [preview] no longer exists.
10
+ 2024-10-02 13:25:28,328 INFO ___FILE_ONLY___
11
+
12
+ 2024-10-02 13:25:28,328 INFO ___FILE_ONLY___
13
+ Your current Google Cloud CLI version is: 495.0.0
14
+
15
+ 2024-10-02 13:25:28,328 INFO ___FILE_ONLY___ Installing components from version: 495.0.0
16
+
17
+ 2024-10-02 13:25:28,328 INFO ___FILE_ONLY___
18
+
19
+ 2024-10-02 13:25:28,329 DEBUG root Chosen display Format:table[box,title="These components will be removed."](details.display_name:label=Name:align=left,version.version_string:label=Version:align=right,data.size.size(zero="",min=1048576):label=Size:align=right)
20
+ 2024-10-02 13:25:28,329 DEBUG root Chosen display Format:table[box,title="These components will be updated."](details.display_name:label=Name:align=left,version.version_string:label=Version:align=right,data.size.size(zero="",min=1048576):label=Size:align=right)
21
+ 2024-10-02 13:25:28,330 DEBUG root Chosen display Format:table[box,title="These components will be installed."](details.display_name:label=Name:align=left,version.version_string:label=Version:align=right,data.size.size(zero="",min=1048576):label=Size:align=right)
22
+ 2024-10-02 13:25:28,348 INFO ___FILE_ONLY___ ┌──────────────────────────────────────────────┐
23
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___
24
+
25
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___ │ These components will be installed. │
26
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___
27
+
28
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___ ├───────────────────────┬────────────┬─────────┤
29
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___
30
+
31
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___ │ Name │ Version │ Size │
32
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___
33
+
34
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___ ├───────────────────────┼────────────┼─────────┤
35
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___
36
+
37
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___ │
38
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___ gcloud Alpha Commands
39
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___
40
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___ │
41
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___ 2024.09.27
42
+ 2024-10-02 13:25:28,349 INFO ___FILE_ONLY___
43
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___ │
44
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___ < 1 MiB
45
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___
46
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___ │
47
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___
48
+
49
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___ │
50
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___ gcloud Beta Commands
51
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___
52
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___ │
53
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___ 2024.09.27
54
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___
55
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___ │
56
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___ < 1 MiB
57
+ 2024-10-02 13:25:28,350 INFO ___FILE_ONLY___
58
+ 2024-10-02 13:25:28,351 INFO ___FILE_ONLY___ │
59
+ 2024-10-02 13:25:28,351 INFO ___FILE_ONLY___
60
+
61
+ 2024-10-02 13:25:28,351 INFO ___FILE_ONLY___ └───────────────────────┴────────────┴─────────┘
62
+ 2024-10-02 13:25:28,351 INFO ___FILE_ONLY___
63
+
64
+ 2024-10-02 13:25:28,351 INFO ___FILE_ONLY___
65
+
66
+ 2024-10-02 13:25:28,354 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
67
+ 2024-10-02 13:25:28,415 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/RELEASE_NOTES HTTP/1.1" 200 1281712
68
+ 2024-10-02 13:25:28,477 INFO ___FILE_ONLY___ For the latest full release notes, please visit:
69
+ https://cloud.google.com/sdk/release_notes
70
+
71
+
72
+ 2024-10-02 13:25:28,477 INFO ___FILE_ONLY___ Performing in place update...
73
+
74
+
75
+ 2024-10-02 13:25:28,479 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
76
+
77
+ 2024-10-02 13:25:28,479 INFO ___FILE_ONLY___ ╠═ Downloading: gcloud Alpha Commands ═╣
78
+
79
+ 2024-10-02 13:25:28,479 INFO ___FILE_ONLY___ ╚
80
+ 2024-10-02 13:25:28,482 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
81
+ 2024-10-02 13:25:28,539 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/components/google-cloud-sdk-alpha-20240927140238.tar.gz HTTP/1.1" 200 800
82
+ 2024-10-02 13:25:28,539 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
83
+ 2024-10-02 13:25:28,539 INFO ___FILE_ONLY___ ╝
84
+
85
+ 2024-10-02 13:25:28,541 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
86
+
87
+ 2024-10-02 13:25:28,542 INFO ___FILE_ONLY___ ╠═ Downloading: gcloud Beta Commands ═╣
88
+
89
+ 2024-10-02 13:25:28,542 INFO ___FILE_ONLY___ ╚
90
+ 2024-10-02 13:25:28,545 DEBUG urllib3.connectionpool Starting new HTTPS connection (1): dl.google.com:443
91
+ 2024-10-02 13:25:28,603 DEBUG urllib3.connectionpool https://dl.google.com:443 "GET /dl/cloudsdk/channels/rapid/components/google-cloud-sdk-beta-20240927140238.tar.gz HTTP/1.1" 200 797
92
+ 2024-10-02 13:25:28,603 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
93
+ 2024-10-02 13:25:28,603 INFO ___FILE_ONLY___ ╝
94
+
95
+ 2024-10-02 13:25:28,605 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
96
+
97
+ 2024-10-02 13:25:28,605 INFO ___FILE_ONLY___ ╠═ Installing: gcloud Alpha Commands ═╣
98
+
99
+ 2024-10-02 13:25:28,606 INFO ___FILE_ONLY___ ╚
100
+ 2024-10-02 13:25:28,606 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
101
+ 2024-10-02 13:25:28,607 INFO ___FILE_ONLY___ ╝
102
+
103
+ 2024-10-02 13:25:28,615 INFO ___FILE_ONLY___ ╔════════════════════════════════════════════════════════════╗
104
+
105
+ 2024-10-02 13:25:28,615 INFO ___FILE_ONLY___ ╠═ Installing: gcloud Beta Commands ═╣
106
+
107
+ 2024-10-02 13:25:28,615 INFO ___FILE_ONLY___ ╚
108
+ 2024-10-02 13:25:28,616 INFO ___FILE_ONLY___ ════════════════════════════════════════════════════════════
109
+ 2024-10-02 13:25:28,616 INFO ___FILE_ONLY___ ╝
110
+
111
+ 2024-10-02 13:25:28,625 DEBUG root Updating notification cache...
112
+ 2024-10-02 13:25:28,625 INFO ___FILE_ONLY___
113
+
114
+ 2024-10-02 13:25:28,627 INFO ___FILE_ONLY___ Performing post processing steps...
115
+ 2024-10-02 13:25:28,627 DEBUG root Executing command: ['/tools/google-cloud-sdk/bin/gcloud', 'components', 'post-process']
116
+ 2024-10-02 13:25:39,883 DEBUG ___FILE_ONLY___
117
+ 2024-10-02 13:25:39,883 DEBUG ___FILE_ONLY___
118
+ 2024-10-02 13:25:39,903 INFO ___FILE_ONLY___
119
+ Update done!
120
+
121
+
122
+ 2024-10-02 13:25:39,907 DEBUG root Chosen display Format:none
123
+ 2024-10-02 13:25:39,907 INFO root Display format: "none"
.config/logs/2024.10.02/13.25.29.095888.log ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ 2024-10-02 13:25:29,096 DEBUG root Loaded Command Group: ['gcloud', 'components']
2
+ 2024-10-02 13:25:29,098 DEBUG root Loaded Command Group: ['gcloud', 'components', 'post_process']
3
+ 2024-10-02 13:25:29,100 DEBUG root Running [gcloud.components.post-process] with arguments: []
4
+ 2024-10-02 13:25:39,795 DEBUG root Chosen display Format:none
5
+ 2024-10-02 13:25:39,795 INFO root Display format: "none"
.config/logs/2024.10.02/13.25.40.484117.log ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ 2024-10-02 13:25:40,486 DEBUG root Loaded Command Group: ['gcloud', 'config']
2
+ 2024-10-02 13:25:40,535 DEBUG root Loaded Command Group: ['gcloud', 'config', 'set']
3
+ 2024-10-02 13:25:40,538 DEBUG root Running [gcloud.config.set] with arguments: [SECTION/PROPERTY: "component_manager/disable_update_check", VALUE: "true"]
4
+ 2024-10-02 13:25:40,539 INFO ___FILE_ONLY___ Updated property [component_manager/disable_update_check].
5
+
6
+ 2024-10-02 13:25:40,540 DEBUG root Chosen display Format:default
7
+ 2024-10-02 13:25:40,541 INFO root Display format: "default"
8
+ 2024-10-02 13:25:40,541 DEBUG root SDK update checks are disabled.
.config/logs/2024.10.02/13.25.41.118585.log ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ 2024-10-02 13:25:41,120 DEBUG root Loaded Command Group: ['gcloud', 'config']
2
+ 2024-10-02 13:25:41,169 DEBUG root Loaded Command Group: ['gcloud', 'config', 'set']
3
+ 2024-10-02 13:25:41,172 DEBUG root Running [gcloud.config.set] with arguments: [SECTION/PROPERTY: "compute/gce_metadata_read_timeout_sec", VALUE: "0"]
4
+ 2024-10-02 13:25:41,173 INFO ___FILE_ONLY___ Updated property [compute/gce_metadata_read_timeout_sec].
5
+
6
+ 2024-10-02 13:25:41,174 DEBUG root Chosen display Format:default
7
+ 2024-10-02 13:25:41,174 INFO root Display format: "default"
8
+ 2024-10-02 13:25:41,175 DEBUG root SDK update checks are disabled.
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ sample_data/mnist_test.csv filter=lfs diff=lfs merge=lfs -text
37
+ sample_data/mnist_train_small.csv filter=lfs diff=lfs merge=lfs -text
results/checkpoint-14000/added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }
results/checkpoint-14000/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.44.2",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
results/checkpoint-14000/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": "4.44.2"
6
+ }
results/checkpoint-14000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14960ece8648f21ec096246ae1e9d7a3c159947da6c4b4c7032b10176d701037
3
+ size 242041896
results/checkpoint-14000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba8e16ede9d03fe006e58cd95ff05aa6ac13f9a9d9dc14eb1bb2d664a0dab8e
3
+ size 484163514
results/checkpoint-14000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edc07be0c15062c321cfa1af8340d077801378a352c12bf83375dd8181c14cc0
3
+ size 14244
results/checkpoint-14000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898993b49ee88a01c5b22bf654c2226386cd1d2123b15aa2a32a214182a49c00
3
+ size 1064
results/checkpoint-14000/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
+ }
results/checkpoint-14000/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
results/checkpoint-14000/tokenizer_config.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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": true,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "legacy": true,
935
+ "model_max_length": 512,
936
+ "pad_token": "<pad>",
937
+ "sp_model_kwargs": {},
938
+ "tokenizer_class": "T5Tokenizer",
939
+ "unk_token": "<unk>"
940
+ }
results/checkpoint-14000/trainer_state.json ADDED
@@ -0,0 +1,2497 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 189.1891891891892,
5
+ "eval_steps": 500,
6
+ "global_step": 14000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 1.8613592386245728,
14
+ "eval_rouge1": 0.4786345373045099,
15
+ "eval_rouge2": 0.37180882574119667,
16
+ "eval_rougeL": 0.45993348459469097,
17
+ "eval_rougeLsum": 0.46473759136147386,
18
+ "eval_runtime": 6.5152,
19
+ "eval_samples_per_second": 9.823,
20
+ "eval_steps_per_second": 2.456,
21
+ "step": 74
22
+ },
23
+ {
24
+ "epoch": 2.0,
25
+ "eval_loss": 1.9003169536590576,
26
+ "eval_rouge1": 0.48640604321499575,
27
+ "eval_rouge2": 0.37989220372871,
28
+ "eval_rougeL": 0.4679360920147918,
29
+ "eval_rougeLsum": 0.4730461956934725,
30
+ "eval_runtime": 6.8749,
31
+ "eval_samples_per_second": 9.309,
32
+ "eval_steps_per_second": 2.327,
33
+ "step": 148
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 1.8439046144485474,
38
+ "eval_rouge1": 0.4878659052451008,
39
+ "eval_rouge2": 0.37862931599963434,
40
+ "eval_rougeL": 0.4686655551573986,
41
+ "eval_rougeLsum": 0.4745397729079822,
42
+ "eval_runtime": 6.9056,
43
+ "eval_samples_per_second": 9.268,
44
+ "eval_steps_per_second": 2.317,
45
+ "step": 222
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_loss": 1.859361171722412,
50
+ "eval_rouge1": 0.4899970322537004,
51
+ "eval_rouge2": 0.39712825251075856,
52
+ "eval_rougeL": 0.47922614340714226,
53
+ "eval_rougeLsum": 0.4845442547862512,
54
+ "eval_runtime": 6.8081,
55
+ "eval_samples_per_second": 9.401,
56
+ "eval_steps_per_second": 2.35,
57
+ "step": 296
58
+ },
59
+ {
60
+ "epoch": 5.0,
61
+ "eval_loss": 1.9181809425354004,
62
+ "eval_rouge1": 0.5019986152414111,
63
+ "eval_rouge2": 0.39075144771524173,
64
+ "eval_rougeL": 0.48288657869037616,
65
+ "eval_rougeLsum": 0.4897115650226128,
66
+ "eval_runtime": 6.7301,
67
+ "eval_samples_per_second": 9.51,
68
+ "eval_steps_per_second": 2.377,
69
+ "step": 370
70
+ },
71
+ {
72
+ "epoch": 6.0,
73
+ "eval_loss": 1.9439482688903809,
74
+ "eval_rouge1": 0.5017635218691469,
75
+ "eval_rouge2": 0.40394299359796604,
76
+ "eval_rougeL": 0.4856876042232454,
77
+ "eval_rougeLsum": 0.4902182125463155,
78
+ "eval_runtime": 8.3277,
79
+ "eval_samples_per_second": 7.685,
80
+ "eval_steps_per_second": 1.921,
81
+ "step": 444
82
+ },
83
+ {
84
+ "epoch": 6.756756756756757,
85
+ "grad_norm": 3.515812635421753,
86
+ "learning_rate": 0.00028986486486486487,
87
+ "loss": 1.0738,
88
+ "step": 500
89
+ },
90
+ {
91
+ "epoch": 7.0,
92
+ "eval_loss": 1.9816868305206299,
93
+ "eval_rouge1": 0.48981665251409034,
94
+ "eval_rouge2": 0.38940540670364077,
95
+ "eval_rougeL": 0.4756157468523289,
96
+ "eval_rougeLsum": 0.47786350441316916,
97
+ "eval_runtime": 6.7892,
98
+ "eval_samples_per_second": 9.427,
99
+ "eval_steps_per_second": 2.357,
100
+ "step": 518
101
+ },
102
+ {
103
+ "epoch": 8.0,
104
+ "eval_loss": 1.9661787748336792,
105
+ "eval_rouge1": 0.503527283682017,
106
+ "eval_rouge2": 0.3907616822377492,
107
+ "eval_rougeL": 0.48117377461776023,
108
+ "eval_rougeLsum": 0.48596520984967795,
109
+ "eval_runtime": 7.1304,
110
+ "eval_samples_per_second": 8.976,
111
+ "eval_steps_per_second": 2.244,
112
+ "step": 592
113
+ },
114
+ {
115
+ "epoch": 9.0,
116
+ "eval_loss": 2.0364491939544678,
117
+ "eval_rouge1": 0.49655106473304944,
118
+ "eval_rouge2": 0.4026512074564483,
119
+ "eval_rougeL": 0.48182640465396503,
120
+ "eval_rougeLsum": 0.48682277089096093,
121
+ "eval_runtime": 7.2868,
122
+ "eval_samples_per_second": 8.783,
123
+ "eval_steps_per_second": 2.196,
124
+ "step": 666
125
+ },
126
+ {
127
+ "epoch": 10.0,
128
+ "eval_loss": 2.0958075523376465,
129
+ "eval_rouge1": 0.5027632027654159,
130
+ "eval_rouge2": 0.405224140796529,
131
+ "eval_rougeL": 0.487341765630358,
132
+ "eval_rougeLsum": 0.49286491460972326,
133
+ "eval_runtime": 7.5086,
134
+ "eval_samples_per_second": 8.524,
135
+ "eval_steps_per_second": 2.131,
136
+ "step": 740
137
+ },
138
+ {
139
+ "epoch": 11.0,
140
+ "eval_loss": 2.1330082416534424,
141
+ "eval_rouge1": 0.4959996625037898,
142
+ "eval_rouge2": 0.39173324347256133,
143
+ "eval_rougeL": 0.47707298584837665,
144
+ "eval_rougeLsum": 0.4801611854873997,
145
+ "eval_runtime": 7.2859,
146
+ "eval_samples_per_second": 8.784,
147
+ "eval_steps_per_second": 2.196,
148
+ "step": 814
149
+ },
150
+ {
151
+ "epoch": 12.0,
152
+ "eval_loss": 2.1985864639282227,
153
+ "eval_rouge1": 0.49880201305687655,
154
+ "eval_rouge2": 0.39953137212155626,
155
+ "eval_rougeL": 0.47742278166430285,
156
+ "eval_rougeLsum": 0.4805222964063607,
157
+ "eval_runtime": 7.603,
158
+ "eval_samples_per_second": 8.418,
159
+ "eval_steps_per_second": 2.104,
160
+ "step": 888
161
+ },
162
+ {
163
+ "epoch": 13.0,
164
+ "eval_loss": 2.199228525161743,
165
+ "eval_rouge1": 0.49651192761571294,
166
+ "eval_rouge2": 0.3996406381133431,
167
+ "eval_rougeL": 0.48019273990957534,
168
+ "eval_rougeLsum": 0.4830744303463099,
169
+ "eval_runtime": 7.41,
170
+ "eval_samples_per_second": 8.637,
171
+ "eval_steps_per_second": 2.159,
172
+ "step": 962
173
+ },
174
+ {
175
+ "epoch": 13.513513513513514,
176
+ "grad_norm": 1.04505455493927,
177
+ "learning_rate": 0.0002797297297297297,
178
+ "loss": 0.5758,
179
+ "step": 1000
180
+ },
181
+ {
182
+ "epoch": 14.0,
183
+ "eval_loss": 2.2532949447631836,
184
+ "eval_rouge1": 0.4974175527416956,
185
+ "eval_rouge2": 0.3938967736606859,
186
+ "eval_rougeL": 0.47594155912589253,
187
+ "eval_rougeLsum": 0.47750953126404355,
188
+ "eval_runtime": 6.7122,
189
+ "eval_samples_per_second": 9.535,
190
+ "eval_steps_per_second": 2.384,
191
+ "step": 1036
192
+ },
193
+ {
194
+ "epoch": 15.0,
195
+ "eval_loss": 2.288240671157837,
196
+ "eval_rouge1": 0.5002431437874408,
197
+ "eval_rouge2": 0.4044372576278309,
198
+ "eval_rougeL": 0.4840219965379457,
199
+ "eval_rougeLsum": 0.4857965014846245,
200
+ "eval_runtime": 7.012,
201
+ "eval_samples_per_second": 9.127,
202
+ "eval_steps_per_second": 2.282,
203
+ "step": 1110
204
+ },
205
+ {
206
+ "epoch": 16.0,
207
+ "eval_loss": 2.3295252323150635,
208
+ "eval_rouge1": 0.49837277766128096,
209
+ "eval_rouge2": 0.400153779173206,
210
+ "eval_rougeL": 0.4787384592897309,
211
+ "eval_rougeLsum": 0.4811181898511001,
212
+ "eval_runtime": 7.1846,
213
+ "eval_samples_per_second": 8.908,
214
+ "eval_steps_per_second": 2.227,
215
+ "step": 1184
216
+ },
217
+ {
218
+ "epoch": 17.0,
219
+ "eval_loss": 2.4045495986938477,
220
+ "eval_rouge1": 0.4978315032043237,
221
+ "eval_rouge2": 0.40024152683134784,
222
+ "eval_rougeL": 0.4779140878590623,
223
+ "eval_rougeLsum": 0.482043049548367,
224
+ "eval_runtime": 7.0985,
225
+ "eval_samples_per_second": 9.016,
226
+ "eval_steps_per_second": 2.254,
227
+ "step": 1258
228
+ },
229
+ {
230
+ "epoch": 18.0,
231
+ "eval_loss": 2.407705783843994,
232
+ "eval_rouge1": 0.4926722210399497,
233
+ "eval_rouge2": 0.39489818358868434,
234
+ "eval_rougeL": 0.4741921466377443,
235
+ "eval_rougeLsum": 0.4779971741886041,
236
+ "eval_runtime": 7.1727,
237
+ "eval_samples_per_second": 8.923,
238
+ "eval_steps_per_second": 2.231,
239
+ "step": 1332
240
+ },
241
+ {
242
+ "epoch": 19.0,
243
+ "eval_loss": 2.478081703186035,
244
+ "eval_rouge1": 0.4968199981652396,
245
+ "eval_rouge2": 0.3921631193099281,
246
+ "eval_rougeL": 0.47676117839634435,
247
+ "eval_rougeLsum": 0.47994768391715004,
248
+ "eval_runtime": 7.454,
249
+ "eval_samples_per_second": 8.586,
250
+ "eval_steps_per_second": 2.146,
251
+ "step": 1406
252
+ },
253
+ {
254
+ "epoch": 20.0,
255
+ "eval_loss": 2.4524130821228027,
256
+ "eval_rouge1": 0.5080094877873333,
257
+ "eval_rouge2": 0.4032125314338061,
258
+ "eval_rougeL": 0.48666005983666427,
259
+ "eval_rougeLsum": 0.4894073793399426,
260
+ "eval_runtime": 7.2808,
261
+ "eval_samples_per_second": 8.79,
262
+ "eval_steps_per_second": 2.198,
263
+ "step": 1480
264
+ },
265
+ {
266
+ "epoch": 20.27027027027027,
267
+ "grad_norm": 1.7321689128875732,
268
+ "learning_rate": 0.0002695945945945946,
269
+ "loss": 0.3167,
270
+ "step": 1500
271
+ },
272
+ {
273
+ "epoch": 21.0,
274
+ "eval_loss": 2.534647226333618,
275
+ "eval_rouge1": 0.5022719998675416,
276
+ "eval_rouge2": 0.3965945705867416,
277
+ "eval_rougeL": 0.47982490810386763,
278
+ "eval_rougeLsum": 0.48480167185914425,
279
+ "eval_runtime": 6.8184,
280
+ "eval_samples_per_second": 9.386,
281
+ "eval_steps_per_second": 2.347,
282
+ "step": 1554
283
+ },
284
+ {
285
+ "epoch": 22.0,
286
+ "eval_loss": 2.5828959941864014,
287
+ "eval_rouge1": 0.4976653665113625,
288
+ "eval_rouge2": 0.40224136020443735,
289
+ "eval_rougeL": 0.4811444805687263,
290
+ "eval_rougeLsum": 0.48383489837790894,
291
+ "eval_runtime": 6.7252,
292
+ "eval_samples_per_second": 9.516,
293
+ "eval_steps_per_second": 2.379,
294
+ "step": 1628
295
+ },
296
+ {
297
+ "epoch": 23.0,
298
+ "eval_loss": 2.5470526218414307,
299
+ "eval_rouge1": 0.4874729550501261,
300
+ "eval_rouge2": 0.3987554141783959,
301
+ "eval_rougeL": 0.47201372208979153,
302
+ "eval_rougeLsum": 0.47412842500299435,
303
+ "eval_runtime": 7.0639,
304
+ "eval_samples_per_second": 9.06,
305
+ "eval_steps_per_second": 2.265,
306
+ "step": 1702
307
+ },
308
+ {
309
+ "epoch": 24.0,
310
+ "eval_loss": 2.630704402923584,
311
+ "eval_rouge1": 0.4896711232817296,
312
+ "eval_rouge2": 0.3955887747393345,
313
+ "eval_rougeL": 0.47391307139859873,
314
+ "eval_rougeLsum": 0.4770794334968449,
315
+ "eval_runtime": 7.3201,
316
+ "eval_samples_per_second": 8.743,
317
+ "eval_steps_per_second": 2.186,
318
+ "step": 1776
319
+ },
320
+ {
321
+ "epoch": 25.0,
322
+ "eval_loss": 2.643130302429199,
323
+ "eval_rouge1": 0.4990756076647881,
324
+ "eval_rouge2": 0.40258726349946017,
325
+ "eval_rougeL": 0.4819547441943952,
326
+ "eval_rougeLsum": 0.4882772750587064,
327
+ "eval_runtime": 7.3246,
328
+ "eval_samples_per_second": 8.738,
329
+ "eval_steps_per_second": 2.184,
330
+ "step": 1850
331
+ },
332
+ {
333
+ "epoch": 26.0,
334
+ "eval_loss": 2.6722755432128906,
335
+ "eval_rouge1": 0.49478698590012704,
336
+ "eval_rouge2": 0.4068068282048684,
337
+ "eval_rougeL": 0.47973303108617305,
338
+ "eval_rougeLsum": 0.4829897810492303,
339
+ "eval_runtime": 7.3062,
340
+ "eval_samples_per_second": 8.76,
341
+ "eval_steps_per_second": 2.19,
342
+ "step": 1924
343
+ },
344
+ {
345
+ "epoch": 27.0,
346
+ "eval_loss": 2.730930805206299,
347
+ "eval_rouge1": 0.48566293927001947,
348
+ "eval_rouge2": 0.3851552374981059,
349
+ "eval_rougeL": 0.4705474000074168,
350
+ "eval_rougeLsum": 0.4722918346693246,
351
+ "eval_runtime": 7.4221,
352
+ "eval_samples_per_second": 8.623,
353
+ "eval_steps_per_second": 2.156,
354
+ "step": 1998
355
+ },
356
+ {
357
+ "epoch": 27.027027027027028,
358
+ "grad_norm": 1.6483324766159058,
359
+ "learning_rate": 0.00025945945945945944,
360
+ "loss": 0.1748,
361
+ "step": 2000
362
+ },
363
+ {
364
+ "epoch": 28.0,
365
+ "eval_loss": 2.7344658374786377,
366
+ "eval_rouge1": 0.49051030653062777,
367
+ "eval_rouge2": 0.3941201110385898,
368
+ "eval_rougeL": 0.4719692856196016,
369
+ "eval_rougeLsum": 0.47611754141135576,
370
+ "eval_runtime": 6.5296,
371
+ "eval_samples_per_second": 9.802,
372
+ "eval_steps_per_second": 2.45,
373
+ "step": 2072
374
+ },
375
+ {
376
+ "epoch": 29.0,
377
+ "eval_loss": 2.7428927421569824,
378
+ "eval_rouge1": 0.4925127943579154,
379
+ "eval_rouge2": 0.3907254802029442,
380
+ "eval_rougeL": 0.4737655715932324,
381
+ "eval_rougeLsum": 0.4773362259172194,
382
+ "eval_runtime": 6.8059,
383
+ "eval_samples_per_second": 9.404,
384
+ "eval_steps_per_second": 2.351,
385
+ "step": 2146
386
+ },
387
+ {
388
+ "epoch": 30.0,
389
+ "eval_loss": 2.796144962310791,
390
+ "eval_rouge1": 0.49155918498382867,
391
+ "eval_rouge2": 0.3999581981140521,
392
+ "eval_rougeL": 0.47417603819102405,
393
+ "eval_rougeLsum": 0.47954892078188294,
394
+ "eval_runtime": 6.775,
395
+ "eval_samples_per_second": 9.447,
396
+ "eval_steps_per_second": 2.362,
397
+ "step": 2220
398
+ },
399
+ {
400
+ "epoch": 31.0,
401
+ "eval_loss": 2.8113179206848145,
402
+ "eval_rouge1": 0.49033614321676355,
403
+ "eval_rouge2": 0.39673932600475936,
404
+ "eval_rougeL": 0.4736746112835428,
405
+ "eval_rougeLsum": 0.4766478013171821,
406
+ "eval_runtime": 6.8964,
407
+ "eval_samples_per_second": 9.28,
408
+ "eval_steps_per_second": 2.32,
409
+ "step": 2294
410
+ },
411
+ {
412
+ "epoch": 32.0,
413
+ "eval_loss": 2.8311588764190674,
414
+ "eval_rouge1": 0.4959842681554596,
415
+ "eval_rouge2": 0.3987159642616428,
416
+ "eval_rougeL": 0.4773867458483667,
417
+ "eval_rougeLsum": 0.48240925171506055,
418
+ "eval_runtime": 6.7543,
419
+ "eval_samples_per_second": 9.475,
420
+ "eval_steps_per_second": 2.369,
421
+ "step": 2368
422
+ },
423
+ {
424
+ "epoch": 33.0,
425
+ "eval_loss": 2.8345541954040527,
426
+ "eval_rouge1": 0.4982105069215113,
427
+ "eval_rouge2": 0.4019606298133721,
428
+ "eval_rougeL": 0.4810665966926186,
429
+ "eval_rougeLsum": 0.48452636993191933,
430
+ "eval_runtime": 6.8235,
431
+ "eval_samples_per_second": 9.379,
432
+ "eval_steps_per_second": 2.345,
433
+ "step": 2442
434
+ },
435
+ {
436
+ "epoch": 33.78378378378378,
437
+ "grad_norm": 1.6361833810806274,
438
+ "learning_rate": 0.0002493243243243243,
439
+ "loss": 0.1085,
440
+ "step": 2500
441
+ },
442
+ {
443
+ "epoch": 34.0,
444
+ "eval_loss": 2.840573787689209,
445
+ "eval_rouge1": 0.4906154416517885,
446
+ "eval_rouge2": 0.3925361294228983,
447
+ "eval_rougeL": 0.47012187809673456,
448
+ "eval_rougeLsum": 0.47358672446502714,
449
+ "eval_runtime": 6.7897,
450
+ "eval_samples_per_second": 9.426,
451
+ "eval_steps_per_second": 2.357,
452
+ "step": 2516
453
+ },
454
+ {
455
+ "epoch": 35.0,
456
+ "eval_loss": 2.930208206176758,
457
+ "eval_rouge1": 0.493665848008467,
458
+ "eval_rouge2": 0.4013160803818016,
459
+ "eval_rougeL": 0.4777617853768054,
460
+ "eval_rougeLsum": 0.48104196224253826,
461
+ "eval_runtime": 6.9547,
462
+ "eval_samples_per_second": 9.202,
463
+ "eval_steps_per_second": 2.301,
464
+ "step": 2590
465
+ },
466
+ {
467
+ "epoch": 36.0,
468
+ "eval_loss": 2.956294059753418,
469
+ "eval_rouge1": 0.49463858809967287,
470
+ "eval_rouge2": 0.40143704462358853,
471
+ "eval_rougeL": 0.4794876543551684,
472
+ "eval_rougeLsum": 0.4829190918461401,
473
+ "eval_runtime": 6.8652,
474
+ "eval_samples_per_second": 9.322,
475
+ "eval_steps_per_second": 2.331,
476
+ "step": 2664
477
+ },
478
+ {
479
+ "epoch": 37.0,
480
+ "eval_loss": 2.969008207321167,
481
+ "eval_rouge1": 0.4954794072003128,
482
+ "eval_rouge2": 0.397320916674356,
483
+ "eval_rougeL": 0.4772272253428127,
484
+ "eval_rougeLsum": 0.48208663351137193,
485
+ "eval_runtime": 6.7157,
486
+ "eval_samples_per_second": 9.53,
487
+ "eval_steps_per_second": 2.382,
488
+ "step": 2738
489
+ },
490
+ {
491
+ "epoch": 38.0,
492
+ "eval_loss": 3.0091614723205566,
493
+ "eval_rouge1": 0.49714553273507894,
494
+ "eval_rouge2": 0.4043158418135101,
495
+ "eval_rougeL": 0.4795949127773593,
496
+ "eval_rougeLsum": 0.4831791208710218,
497
+ "eval_runtime": 7.1733,
498
+ "eval_samples_per_second": 8.922,
499
+ "eval_steps_per_second": 2.23,
500
+ "step": 2812
501
+ },
502
+ {
503
+ "epoch": 39.0,
504
+ "eval_loss": 3.0400657653808594,
505
+ "eval_rouge1": 0.4930990290551204,
506
+ "eval_rouge2": 0.4008358832580894,
507
+ "eval_rougeL": 0.4738879674085547,
508
+ "eval_rougeLsum": 0.4786937389741459,
509
+ "eval_runtime": 7.4692,
510
+ "eval_samples_per_second": 8.569,
511
+ "eval_steps_per_second": 2.142,
512
+ "step": 2886
513
+ },
514
+ {
515
+ "epoch": 40.0,
516
+ "eval_loss": 3.1281185150146484,
517
+ "eval_rouge1": 0.5005688791622078,
518
+ "eval_rouge2": 0.4084174900042821,
519
+ "eval_rougeL": 0.48499705961551304,
520
+ "eval_rougeLsum": 0.4874735515428569,
521
+ "eval_runtime": 7.5007,
522
+ "eval_samples_per_second": 8.533,
523
+ "eval_steps_per_second": 2.133,
524
+ "step": 2960
525
+ },
526
+ {
527
+ "epoch": 40.54054054054054,
528
+ "grad_norm": 0.9557915329933167,
529
+ "learning_rate": 0.00023918918918918917,
530
+ "loss": 0.0705,
531
+ "step": 3000
532
+ },
533
+ {
534
+ "epoch": 41.0,
535
+ "eval_loss": 3.0529465675354004,
536
+ "eval_rouge1": 0.4897934761187476,
537
+ "eval_rouge2": 0.39635503197156763,
538
+ "eval_rougeL": 0.47185062979906517,
539
+ "eval_rougeLsum": 0.4759267454340096,
540
+ "eval_runtime": 6.6953,
541
+ "eval_samples_per_second": 9.559,
542
+ "eval_steps_per_second": 2.39,
543
+ "step": 3034
544
+ },
545
+ {
546
+ "epoch": 42.0,
547
+ "eval_loss": 3.11130690574646,
548
+ "eval_rouge1": 0.4946583089357438,
549
+ "eval_rouge2": 0.3978038705482625,
550
+ "eval_rougeL": 0.47574088550447186,
551
+ "eval_rougeLsum": 0.4806888255731349,
552
+ "eval_runtime": 6.8505,
553
+ "eval_samples_per_second": 9.342,
554
+ "eval_steps_per_second": 2.336,
555
+ "step": 3108
556
+ },
557
+ {
558
+ "epoch": 43.0,
559
+ "eval_loss": 3.0772416591644287,
560
+ "eval_rouge1": 0.5030802762047029,
561
+ "eval_rouge2": 0.410314672620852,
562
+ "eval_rougeL": 0.4833954355578848,
563
+ "eval_rougeLsum": 0.4875555968866432,
564
+ "eval_runtime": 6.8413,
565
+ "eval_samples_per_second": 9.355,
566
+ "eval_steps_per_second": 2.339,
567
+ "step": 3182
568
+ },
569
+ {
570
+ "epoch": 44.0,
571
+ "eval_loss": 3.0869698524475098,
572
+ "eval_rouge1": 0.48529765931122515,
573
+ "eval_rouge2": 0.393553693154484,
574
+ "eval_rougeL": 0.4677500598095278,
575
+ "eval_rougeLsum": 0.47176121532464105,
576
+ "eval_runtime": 7.0952,
577
+ "eval_samples_per_second": 9.02,
578
+ "eval_steps_per_second": 2.255,
579
+ "step": 3256
580
+ },
581
+ {
582
+ "epoch": 45.0,
583
+ "eval_loss": 3.1311964988708496,
584
+ "eval_rouge1": 0.49150604031170264,
585
+ "eval_rouge2": 0.39344648211082733,
586
+ "eval_rougeL": 0.47140730666348807,
587
+ "eval_rougeLsum": 0.4749720765409351,
588
+ "eval_runtime": 7.0711,
589
+ "eval_samples_per_second": 9.051,
590
+ "eval_steps_per_second": 2.263,
591
+ "step": 3330
592
+ },
593
+ {
594
+ "epoch": 46.0,
595
+ "eval_loss": 3.1351137161254883,
596
+ "eval_rouge1": 0.48756191602264853,
597
+ "eval_rouge2": 0.3913618206121121,
598
+ "eval_rougeL": 0.46594848749570755,
599
+ "eval_rougeLsum": 0.4708637065525476,
600
+ "eval_runtime": 7.4988,
601
+ "eval_samples_per_second": 8.535,
602
+ "eval_steps_per_second": 2.134,
603
+ "step": 3404
604
+ },
605
+ {
606
+ "epoch": 47.0,
607
+ "eval_loss": 3.1709024906158447,
608
+ "eval_rouge1": 0.4922573774776159,
609
+ "eval_rouge2": 0.3951502957382841,
610
+ "eval_rougeL": 0.47162786210886765,
611
+ "eval_rougeLsum": 0.47819599079754893,
612
+ "eval_runtime": 7.6141,
613
+ "eval_samples_per_second": 8.406,
614
+ "eval_steps_per_second": 2.101,
615
+ "step": 3478
616
+ },
617
+ {
618
+ "epoch": 47.2972972972973,
619
+ "grad_norm": 0.05126029625535011,
620
+ "learning_rate": 0.00022905405405405403,
621
+ "loss": 0.048,
622
+ "step": 3500
623
+ },
624
+ {
625
+ "epoch": 48.0,
626
+ "eval_loss": 3.2214059829711914,
627
+ "eval_rouge1": 0.4890967944398124,
628
+ "eval_rouge2": 0.3899734025187871,
629
+ "eval_rougeL": 0.47142210483202807,
630
+ "eval_rougeLsum": 0.4747196341231704,
631
+ "eval_runtime": 6.8558,
632
+ "eval_samples_per_second": 9.335,
633
+ "eval_steps_per_second": 2.334,
634
+ "step": 3552
635
+ },
636
+ {
637
+ "epoch": 49.0,
638
+ "eval_loss": 3.212207317352295,
639
+ "eval_rouge1": 0.49216557406572503,
640
+ "eval_rouge2": 0.39842262033619624,
641
+ "eval_rougeL": 0.47319779876406254,
642
+ "eval_rougeLsum": 0.47788473282281796,
643
+ "eval_runtime": 7.1919,
644
+ "eval_samples_per_second": 8.899,
645
+ "eval_steps_per_second": 2.225,
646
+ "step": 3626
647
+ },
648
+ {
649
+ "epoch": 50.0,
650
+ "eval_loss": 3.2497425079345703,
651
+ "eval_rouge1": 0.48706134754757757,
652
+ "eval_rouge2": 0.38575444861667946,
653
+ "eval_rougeL": 0.46735785969190247,
654
+ "eval_rougeLsum": 0.4728504130518682,
655
+ "eval_runtime": 7.0702,
656
+ "eval_samples_per_second": 9.052,
657
+ "eval_steps_per_second": 2.263,
658
+ "step": 3700
659
+ },
660
+ {
661
+ "epoch": 51.0,
662
+ "eval_loss": 3.2969608306884766,
663
+ "eval_rouge1": 0.4932365455711594,
664
+ "eval_rouge2": 0.4000747029784189,
665
+ "eval_rougeL": 0.4738167823332297,
666
+ "eval_rougeLsum": 0.4772360828349106,
667
+ "eval_runtime": 6.965,
668
+ "eval_samples_per_second": 9.189,
669
+ "eval_steps_per_second": 2.297,
670
+ "step": 3774
671
+ },
672
+ {
673
+ "epoch": 52.0,
674
+ "eval_loss": 3.2699038982391357,
675
+ "eval_rouge1": 0.48578637168024275,
676
+ "eval_rouge2": 0.3899767424324475,
677
+ "eval_rougeL": 0.4655432811779165,
678
+ "eval_rougeLsum": 0.46990217980095994,
679
+ "eval_runtime": 7.1115,
680
+ "eval_samples_per_second": 8.999,
681
+ "eval_steps_per_second": 2.25,
682
+ "step": 3848
683
+ },
684
+ {
685
+ "epoch": 53.0,
686
+ "eval_loss": 3.27628755569458,
687
+ "eval_rouge1": 0.4933670872384299,
688
+ "eval_rouge2": 0.39634620451150876,
689
+ "eval_rougeL": 0.4732893971674522,
690
+ "eval_rougeLsum": 0.47671103112248703,
691
+ "eval_runtime": 7.4331,
692
+ "eval_samples_per_second": 8.61,
693
+ "eval_steps_per_second": 2.153,
694
+ "step": 3922
695
+ },
696
+ {
697
+ "epoch": 54.0,
698
+ "eval_loss": 3.3377037048339844,
699
+ "eval_rouge1": 0.49163229783499957,
700
+ "eval_rouge2": 0.39568035885308184,
701
+ "eval_rougeL": 0.4728118235854102,
702
+ "eval_rougeLsum": 0.47626488443738957,
703
+ "eval_runtime": 7.5795,
704
+ "eval_samples_per_second": 8.444,
705
+ "eval_steps_per_second": 2.111,
706
+ "step": 3996
707
+ },
708
+ {
709
+ "epoch": 54.054054054054056,
710
+ "grad_norm": 1.0509763956069946,
711
+ "learning_rate": 0.0002189189189189189,
712
+ "loss": 0.038,
713
+ "step": 4000
714
+ },
715
+ {
716
+ "epoch": 55.0,
717
+ "eval_loss": 3.3113150596618652,
718
+ "eval_rouge1": 0.48945272795521544,
719
+ "eval_rouge2": 0.3963221515559594,
720
+ "eval_rougeL": 0.4721919860446503,
721
+ "eval_rougeLsum": 0.47357799717311305,
722
+ "eval_runtime": 6.678,
723
+ "eval_samples_per_second": 9.584,
724
+ "eval_steps_per_second": 2.396,
725
+ "step": 4070
726
+ },
727
+ {
728
+ "epoch": 56.0,
729
+ "eval_loss": 3.3390731811523438,
730
+ "eval_rouge1": 0.48992251021991795,
731
+ "eval_rouge2": 0.39489410083425924,
732
+ "eval_rougeL": 0.47052371258574177,
733
+ "eval_rougeLsum": 0.4743893718036267,
734
+ "eval_runtime": 6.7362,
735
+ "eval_samples_per_second": 9.501,
736
+ "eval_steps_per_second": 2.375,
737
+ "step": 4144
738
+ },
739
+ {
740
+ "epoch": 57.0,
741
+ "eval_loss": 3.3541388511657715,
742
+ "eval_rouge1": 0.485591464354193,
743
+ "eval_rouge2": 0.3922683949911642,
744
+ "eval_rougeL": 0.467559759968952,
745
+ "eval_rougeLsum": 0.47055134836018797,
746
+ "eval_runtime": 6.7783,
747
+ "eval_samples_per_second": 9.442,
748
+ "eval_steps_per_second": 2.36,
749
+ "step": 4218
750
+ },
751
+ {
752
+ "epoch": 58.0,
753
+ "eval_loss": 3.3830862045288086,
754
+ "eval_rouge1": 0.48567933561799026,
755
+ "eval_rouge2": 0.3913114600982295,
756
+ "eval_rougeL": 0.4717197222629562,
757
+ "eval_rougeLsum": 0.4759054008130139,
758
+ "eval_runtime": 6.7362,
759
+ "eval_samples_per_second": 9.501,
760
+ "eval_steps_per_second": 2.375,
761
+ "step": 4292
762
+ },
763
+ {
764
+ "epoch": 59.0,
765
+ "eval_loss": 3.362180233001709,
766
+ "eval_rouge1": 0.4871759825945764,
767
+ "eval_rouge2": 0.39201146093813594,
768
+ "eval_rougeL": 0.46798817172512763,
769
+ "eval_rougeLsum": 0.4722525087292696,
770
+ "eval_runtime": 6.8255,
771
+ "eval_samples_per_second": 9.377,
772
+ "eval_steps_per_second": 2.344,
773
+ "step": 4366
774
+ },
775
+ {
776
+ "epoch": 60.0,
777
+ "eval_loss": 3.365551233291626,
778
+ "eval_rouge1": 0.491209709363416,
779
+ "eval_rouge2": 0.3941051958571793,
780
+ "eval_rougeL": 0.4710680943298621,
781
+ "eval_rougeLsum": 0.47543333130232784,
782
+ "eval_runtime": 7.1366,
783
+ "eval_samples_per_second": 8.968,
784
+ "eval_steps_per_second": 2.242,
785
+ "step": 4440
786
+ },
787
+ {
788
+ "epoch": 60.810810810810814,
789
+ "grad_norm": 0.5249083042144775,
790
+ "learning_rate": 0.00020878378378378376,
791
+ "loss": 0.0262,
792
+ "step": 4500
793
+ },
794
+ {
795
+ "epoch": 61.0,
796
+ "eval_loss": 3.3976566791534424,
797
+ "eval_rouge1": 0.4927070473298987,
798
+ "eval_rouge2": 0.39541083512710884,
799
+ "eval_rougeL": 0.4719375953633722,
800
+ "eval_rougeLsum": 0.4739645816900254,
801
+ "eval_runtime": 5.9466,
802
+ "eval_samples_per_second": 10.762,
803
+ "eval_steps_per_second": 2.691,
804
+ "step": 4514
805
+ },
806
+ {
807
+ "epoch": 62.0,
808
+ "eval_loss": 3.415280342102051,
809
+ "eval_rouge1": 0.4931049778367517,
810
+ "eval_rouge2": 0.3954821826304163,
811
+ "eval_rougeL": 0.4730007788710514,
812
+ "eval_rougeLsum": 0.4765290778808515,
813
+ "eval_runtime": 5.9912,
814
+ "eval_samples_per_second": 10.682,
815
+ "eval_steps_per_second": 2.671,
816
+ "step": 4588
817
+ },
818
+ {
819
+ "epoch": 63.0,
820
+ "eval_loss": 3.4405603408813477,
821
+ "eval_rouge1": 0.48902472517948936,
822
+ "eval_rouge2": 0.3912770214119093,
823
+ "eval_rougeL": 0.4678029162844149,
824
+ "eval_rougeLsum": 0.4717999074200574,
825
+ "eval_runtime": 6.0508,
826
+ "eval_samples_per_second": 10.577,
827
+ "eval_steps_per_second": 2.644,
828
+ "step": 4662
829
+ },
830
+ {
831
+ "epoch": 64.0,
832
+ "eval_loss": 3.4136810302734375,
833
+ "eval_rouge1": 0.4863383911556584,
834
+ "eval_rouge2": 0.3918101023135222,
835
+ "eval_rougeL": 0.4691773006948949,
836
+ "eval_rougeLsum": 0.4701254305876148,
837
+ "eval_runtime": 5.9957,
838
+ "eval_samples_per_second": 10.674,
839
+ "eval_steps_per_second": 2.669,
840
+ "step": 4736
841
+ },
842
+ {
843
+ "epoch": 65.0,
844
+ "eval_loss": 3.408576488494873,
845
+ "eval_rouge1": 0.48284179574608654,
846
+ "eval_rouge2": 0.3858487599642365,
847
+ "eval_rougeL": 0.4641900110562617,
848
+ "eval_rougeLsum": 0.4663033361080079,
849
+ "eval_runtime": 5.9307,
850
+ "eval_samples_per_second": 10.791,
851
+ "eval_steps_per_second": 2.698,
852
+ "step": 4810
853
+ },
854
+ {
855
+ "epoch": 66.0,
856
+ "eval_loss": 3.451409339904785,
857
+ "eval_rouge1": 0.4856531269102483,
858
+ "eval_rouge2": 0.3856457649232374,
859
+ "eval_rougeL": 0.4649051696307025,
860
+ "eval_rougeLsum": 0.46875160328429377,
861
+ "eval_runtime": 6.2318,
862
+ "eval_samples_per_second": 10.27,
863
+ "eval_steps_per_second": 2.567,
864
+ "step": 4884
865
+ },
866
+ {
867
+ "epoch": 67.0,
868
+ "eval_loss": 3.484530210494995,
869
+ "eval_rouge1": 0.48758647184312953,
870
+ "eval_rouge2": 0.3840632511768816,
871
+ "eval_rougeL": 0.4672550598356402,
872
+ "eval_rougeLsum": 0.47087847986805387,
873
+ "eval_runtime": 6.5818,
874
+ "eval_samples_per_second": 9.724,
875
+ "eval_steps_per_second": 2.431,
876
+ "step": 4958
877
+ },
878
+ {
879
+ "epoch": 67.56756756756756,
880
+ "grad_norm": 0.10448549687862396,
881
+ "learning_rate": 0.00019864864864864863,
882
+ "loss": 0.0234,
883
+ "step": 5000
884
+ },
885
+ {
886
+ "epoch": 68.0,
887
+ "eval_loss": 3.4810497760772705,
888
+ "eval_rouge1": 0.49381108636054727,
889
+ "eval_rouge2": 0.39657607052252347,
890
+ "eval_rougeL": 0.47743909398976075,
891
+ "eval_rougeLsum": 0.4800737432511466,
892
+ "eval_runtime": 5.9672,
893
+ "eval_samples_per_second": 10.725,
894
+ "eval_steps_per_second": 2.681,
895
+ "step": 5032
896
+ },
897
+ {
898
+ "epoch": 69.0,
899
+ "eval_loss": 3.4901700019836426,
900
+ "eval_rouge1": 0.4898415437441482,
901
+ "eval_rouge2": 0.3882823621363838,
902
+ "eval_rougeL": 0.47261608178486914,
903
+ "eval_rougeLsum": 0.4741921184693466,
904
+ "eval_runtime": 5.9512,
905
+ "eval_samples_per_second": 10.754,
906
+ "eval_steps_per_second": 2.689,
907
+ "step": 5106
908
+ },
909
+ {
910
+ "epoch": 70.0,
911
+ "eval_loss": 3.5320417881011963,
912
+ "eval_rouge1": 0.4947141614912596,
913
+ "eval_rouge2": 0.39465368442175086,
914
+ "eval_rougeL": 0.4734668819817565,
915
+ "eval_rougeLsum": 0.4760338682248753,
916
+ "eval_runtime": 6.1859,
917
+ "eval_samples_per_second": 10.346,
918
+ "eval_steps_per_second": 2.587,
919
+ "step": 5180
920
+ },
921
+ {
922
+ "epoch": 71.0,
923
+ "eval_loss": 3.5137100219726562,
924
+ "eval_rouge1": 0.49608835837704873,
925
+ "eval_rouge2": 0.39887453020105085,
926
+ "eval_rougeL": 0.47537134411252835,
927
+ "eval_rougeLsum": 0.4782933040241389,
928
+ "eval_runtime": 6.5425,
929
+ "eval_samples_per_second": 9.782,
930
+ "eval_steps_per_second": 2.446,
931
+ "step": 5254
932
+ },
933
+ {
934
+ "epoch": 72.0,
935
+ "eval_loss": 3.54203462600708,
936
+ "eval_rouge1": 0.4938721262652266,
937
+ "eval_rouge2": 0.3991345798512075,
938
+ "eval_rougeL": 0.473889236162382,
939
+ "eval_rougeLsum": 0.4769789156636634,
940
+ "eval_runtime": 6.6452,
941
+ "eval_samples_per_second": 9.631,
942
+ "eval_steps_per_second": 2.408,
943
+ "step": 5328
944
+ },
945
+ {
946
+ "epoch": 73.0,
947
+ "eval_loss": 3.5607151985168457,
948
+ "eval_rouge1": 0.49582537040349045,
949
+ "eval_rouge2": 0.3988131906852439,
950
+ "eval_rougeL": 0.4742133994505331,
951
+ "eval_rougeLsum": 0.4766127354706121,
952
+ "eval_runtime": 6.7249,
953
+ "eval_samples_per_second": 9.517,
954
+ "eval_steps_per_second": 2.379,
955
+ "step": 5402
956
+ },
957
+ {
958
+ "epoch": 74.0,
959
+ "eval_loss": 3.5173583030700684,
960
+ "eval_rouge1": 0.49408949503121624,
961
+ "eval_rouge2": 0.3987998981499851,
962
+ "eval_rougeL": 0.4744563588816155,
963
+ "eval_rougeLsum": 0.477003901682462,
964
+ "eval_runtime": 6.815,
965
+ "eval_samples_per_second": 9.391,
966
+ "eval_steps_per_second": 2.348,
967
+ "step": 5476
968
+ },
969
+ {
970
+ "epoch": 74.32432432432432,
971
+ "grad_norm": 1.538454294204712,
972
+ "learning_rate": 0.0001885135135135135,
973
+ "loss": 0.0206,
974
+ "step": 5500
975
+ },
976
+ {
977
+ "epoch": 75.0,
978
+ "eval_loss": 3.510671615600586,
979
+ "eval_rouge1": 0.48857041939584583,
980
+ "eval_rouge2": 0.39406894473811616,
981
+ "eval_rougeL": 0.46991352957942084,
982
+ "eval_rougeLsum": 0.47053409246489913,
983
+ "eval_runtime": 6.4828,
984
+ "eval_samples_per_second": 9.872,
985
+ "eval_steps_per_second": 2.468,
986
+ "step": 5550
987
+ },
988
+ {
989
+ "epoch": 76.0,
990
+ "eval_loss": 3.511385440826416,
991
+ "eval_rouge1": 0.4958933420717311,
992
+ "eval_rouge2": 0.40271880135871385,
993
+ "eval_rougeL": 0.478388062531942,
994
+ "eval_rougeLsum": 0.4805975001489603,
995
+ "eval_runtime": 6.637,
996
+ "eval_samples_per_second": 9.643,
997
+ "eval_steps_per_second": 2.411,
998
+ "step": 5624
999
+ },
1000
+ {
1001
+ "epoch": 77.0,
1002
+ "eval_loss": 3.559112071990967,
1003
+ "eval_rouge1": 0.4873606646749901,
1004
+ "eval_rouge2": 0.39523537661271524,
1005
+ "eval_rougeL": 0.47059772736900357,
1006
+ "eval_rougeLsum": 0.4725288618416706,
1007
+ "eval_runtime": 6.8715,
1008
+ "eval_samples_per_second": 9.314,
1009
+ "eval_steps_per_second": 2.328,
1010
+ "step": 5698
1011
+ },
1012
+ {
1013
+ "epoch": 78.0,
1014
+ "eval_loss": 3.550933599472046,
1015
+ "eval_rouge1": 0.4866858870154881,
1016
+ "eval_rouge2": 0.3980955081516213,
1017
+ "eval_rougeL": 0.47115788584151075,
1018
+ "eval_rougeLsum": 0.4729082439223625,
1019
+ "eval_runtime": 6.9143,
1020
+ "eval_samples_per_second": 9.256,
1021
+ "eval_steps_per_second": 2.314,
1022
+ "step": 5772
1023
+ },
1024
+ {
1025
+ "epoch": 79.0,
1026
+ "eval_loss": 3.5746328830718994,
1027
+ "eval_rouge1": 0.4938385168719914,
1028
+ "eval_rouge2": 0.40148291472212705,
1029
+ "eval_rougeL": 0.47651891732980245,
1030
+ "eval_rougeLsum": 0.48196531108026874,
1031
+ "eval_runtime": 6.7321,
1032
+ "eval_samples_per_second": 9.507,
1033
+ "eval_steps_per_second": 2.377,
1034
+ "step": 5846
1035
+ },
1036
+ {
1037
+ "epoch": 80.0,
1038
+ "eval_loss": 3.6305410861968994,
1039
+ "eval_rouge1": 0.49906184754409744,
1040
+ "eval_rouge2": 0.4037579727503696,
1041
+ "eval_rougeL": 0.48135298410930016,
1042
+ "eval_rougeLsum": 0.4850652734866746,
1043
+ "eval_runtime": 6.9421,
1044
+ "eval_samples_per_second": 9.219,
1045
+ "eval_steps_per_second": 2.305,
1046
+ "step": 5920
1047
+ },
1048
+ {
1049
+ "epoch": 81.0,
1050
+ "eval_loss": 3.632502794265747,
1051
+ "eval_rouge1": 0.4937222626160631,
1052
+ "eval_rouge2": 0.4001823331099268,
1053
+ "eval_rougeL": 0.4723927700965753,
1054
+ "eval_rougeLsum": 0.4761599401277341,
1055
+ "eval_runtime": 7.1456,
1056
+ "eval_samples_per_second": 8.957,
1057
+ "eval_steps_per_second": 2.239,
1058
+ "step": 5994
1059
+ },
1060
+ {
1061
+ "epoch": 81.08108108108108,
1062
+ "grad_norm": 0.6058977842330933,
1063
+ "learning_rate": 0.00017837837837837839,
1064
+ "loss": 0.0151,
1065
+ "step": 6000
1066
+ },
1067
+ {
1068
+ "epoch": 82.0,
1069
+ "eval_loss": 3.6375513076782227,
1070
+ "eval_rouge1": 0.4961470087554145,
1071
+ "eval_rouge2": 0.40273253186645125,
1072
+ "eval_rougeL": 0.4771099396560761,
1073
+ "eval_rougeLsum": 0.48100694297178787,
1074
+ "eval_runtime": 6.7309,
1075
+ "eval_samples_per_second": 9.508,
1076
+ "eval_steps_per_second": 2.377,
1077
+ "step": 6068
1078
+ },
1079
+ {
1080
+ "epoch": 83.0,
1081
+ "eval_loss": 3.5627195835113525,
1082
+ "eval_rouge1": 0.4995314420849537,
1083
+ "eval_rouge2": 0.40335559902907575,
1084
+ "eval_rougeL": 0.4823993107807216,
1085
+ "eval_rougeLsum": 0.4866764546658857,
1086
+ "eval_runtime": 6.7823,
1087
+ "eval_samples_per_second": 9.436,
1088
+ "eval_steps_per_second": 2.359,
1089
+ "step": 6142
1090
+ },
1091
+ {
1092
+ "epoch": 84.0,
1093
+ "eval_loss": 3.586707592010498,
1094
+ "eval_rouge1": 0.4935070043523979,
1095
+ "eval_rouge2": 0.3942335588271486,
1096
+ "eval_rougeL": 0.474130711435772,
1097
+ "eval_rougeLsum": 0.4775505144021025,
1098
+ "eval_runtime": 6.7985,
1099
+ "eval_samples_per_second": 9.414,
1100
+ "eval_steps_per_second": 2.353,
1101
+ "step": 6216
1102
+ },
1103
+ {
1104
+ "epoch": 85.0,
1105
+ "eval_loss": 3.653571128845215,
1106
+ "eval_rouge1": 0.4881804248663784,
1107
+ "eval_rouge2": 0.391742835732956,
1108
+ "eval_rougeL": 0.46938710096628977,
1109
+ "eval_rougeLsum": 0.47182758126483004,
1110
+ "eval_runtime": 6.8579,
1111
+ "eval_samples_per_second": 9.332,
1112
+ "eval_steps_per_second": 2.333,
1113
+ "step": 6290
1114
+ },
1115
+ {
1116
+ "epoch": 86.0,
1117
+ "eval_loss": 3.643256664276123,
1118
+ "eval_rouge1": 0.48692368300546285,
1119
+ "eval_rouge2": 0.39335563997682566,
1120
+ "eval_rougeL": 0.4712442934765564,
1121
+ "eval_rougeLsum": 0.4741654824375442,
1122
+ "eval_runtime": 6.929,
1123
+ "eval_samples_per_second": 9.237,
1124
+ "eval_steps_per_second": 2.309,
1125
+ "step": 6364
1126
+ },
1127
+ {
1128
+ "epoch": 87.0,
1129
+ "eval_loss": 3.6616086959838867,
1130
+ "eval_rouge1": 0.49749293331782896,
1131
+ "eval_rouge2": 0.40300410454293367,
1132
+ "eval_rougeL": 0.47928673999842175,
1133
+ "eval_rougeLsum": 0.4837732647138796,
1134
+ "eval_runtime": 7.2255,
1135
+ "eval_samples_per_second": 8.857,
1136
+ "eval_steps_per_second": 2.214,
1137
+ "step": 6438
1138
+ },
1139
+ {
1140
+ "epoch": 87.83783783783784,
1141
+ "grad_norm": 0.235611692070961,
1142
+ "learning_rate": 0.00016824324324324325,
1143
+ "loss": 0.0121,
1144
+ "step": 6500
1145
+ },
1146
+ {
1147
+ "epoch": 88.0,
1148
+ "eval_loss": 3.656867504119873,
1149
+ "eval_rouge1": 0.4913983899917831,
1150
+ "eval_rouge2": 0.393535501893543,
1151
+ "eval_rougeL": 0.47100266301623717,
1152
+ "eval_rougeLsum": 0.4738950200928132,
1153
+ "eval_runtime": 6.7134,
1154
+ "eval_samples_per_second": 9.533,
1155
+ "eval_steps_per_second": 2.383,
1156
+ "step": 6512
1157
+ },
1158
+ {
1159
+ "epoch": 89.0,
1160
+ "eval_loss": 3.6369504928588867,
1161
+ "eval_rouge1": 0.5024515479898679,
1162
+ "eval_rouge2": 0.4068328278412592,
1163
+ "eval_rougeL": 0.4830703907699512,
1164
+ "eval_rougeLsum": 0.4860924010479748,
1165
+ "eval_runtime": 6.6955,
1166
+ "eval_samples_per_second": 9.559,
1167
+ "eval_steps_per_second": 2.39,
1168
+ "step": 6586
1169
+ },
1170
+ {
1171
+ "epoch": 90.0,
1172
+ "eval_loss": 3.651461601257324,
1173
+ "eval_rouge1": 0.4927558140102515,
1174
+ "eval_rouge2": 0.399360107524262,
1175
+ "eval_rougeL": 0.4765313230674868,
1176
+ "eval_rougeLsum": 0.4799470579462636,
1177
+ "eval_runtime": 6.9392,
1178
+ "eval_samples_per_second": 9.223,
1179
+ "eval_steps_per_second": 2.306,
1180
+ "step": 6660
1181
+ },
1182
+ {
1183
+ "epoch": 91.0,
1184
+ "eval_loss": 3.669370651245117,
1185
+ "eval_rouge1": 0.49371924215166024,
1186
+ "eval_rouge2": 0.40089928401621466,
1187
+ "eval_rougeL": 0.4757733012282773,
1188
+ "eval_rougeLsum": 0.4763141612251891,
1189
+ "eval_runtime": 6.8486,
1190
+ "eval_samples_per_second": 9.345,
1191
+ "eval_steps_per_second": 2.336,
1192
+ "step": 6734
1193
+ },
1194
+ {
1195
+ "epoch": 92.0,
1196
+ "eval_loss": 3.6855876445770264,
1197
+ "eval_rouge1": 0.49870880560202346,
1198
+ "eval_rouge2": 0.3995434714922107,
1199
+ "eval_rougeL": 0.47709889906045905,
1200
+ "eval_rougeLsum": 0.4800311476126575,
1201
+ "eval_runtime": 6.9861,
1202
+ "eval_samples_per_second": 9.161,
1203
+ "eval_steps_per_second": 2.29,
1204
+ "step": 6808
1205
+ },
1206
+ {
1207
+ "epoch": 93.0,
1208
+ "eval_loss": 3.658203125,
1209
+ "eval_rouge1": 0.49939709188553005,
1210
+ "eval_rouge2": 0.40124350229555694,
1211
+ "eval_rougeL": 0.47982810543295096,
1212
+ "eval_rougeLsum": 0.4811932796134847,
1213
+ "eval_runtime": 7.3285,
1214
+ "eval_samples_per_second": 8.733,
1215
+ "eval_steps_per_second": 2.183,
1216
+ "step": 6882
1217
+ },
1218
+ {
1219
+ "epoch": 94.0,
1220
+ "eval_loss": 3.6597373485565186,
1221
+ "eval_rouge1": 0.5035028200165406,
1222
+ "eval_rouge2": 0.4074152495888604,
1223
+ "eval_rougeL": 0.4832822677146339,
1224
+ "eval_rougeLsum": 0.48675050543330844,
1225
+ "eval_runtime": 7.2037,
1226
+ "eval_samples_per_second": 8.884,
1227
+ "eval_steps_per_second": 2.221,
1228
+ "step": 6956
1229
+ },
1230
+ {
1231
+ "epoch": 94.5945945945946,
1232
+ "grad_norm": 0.005829666741192341,
1233
+ "learning_rate": 0.0001581081081081081,
1234
+ "loss": 0.0113,
1235
+ "step": 7000
1236
+ },
1237
+ {
1238
+ "epoch": 95.0,
1239
+ "eval_loss": 3.6415438652038574,
1240
+ "eval_rouge1": 0.49360456034516226,
1241
+ "eval_rouge2": 0.40015057227140216,
1242
+ "eval_rougeL": 0.474561855190351,
1243
+ "eval_rougeLsum": 0.4762347047490384,
1244
+ "eval_runtime": 6.6515,
1245
+ "eval_samples_per_second": 9.622,
1246
+ "eval_steps_per_second": 2.405,
1247
+ "step": 7030
1248
+ },
1249
+ {
1250
+ "epoch": 96.0,
1251
+ "eval_loss": 3.6551480293273926,
1252
+ "eval_rouge1": 0.49903321106951,
1253
+ "eval_rouge2": 0.39766451768211863,
1254
+ "eval_rougeL": 0.4784771999456732,
1255
+ "eval_rougeLsum": 0.48001611691185453,
1256
+ "eval_runtime": 6.7778,
1257
+ "eval_samples_per_second": 9.443,
1258
+ "eval_steps_per_second": 2.361,
1259
+ "step": 7104
1260
+ },
1261
+ {
1262
+ "epoch": 97.0,
1263
+ "eval_loss": 3.6675968170166016,
1264
+ "eval_rouge1": 0.4932707200152202,
1265
+ "eval_rouge2": 0.39322477909813836,
1266
+ "eval_rougeL": 0.47512203026214206,
1267
+ "eval_rougeLsum": 0.4763580225435634,
1268
+ "eval_runtime": 6.8526,
1269
+ "eval_samples_per_second": 9.339,
1270
+ "eval_steps_per_second": 2.335,
1271
+ "step": 7178
1272
+ },
1273
+ {
1274
+ "epoch": 98.0,
1275
+ "eval_loss": 3.6883370876312256,
1276
+ "eval_rouge1": 0.4875206376053254,
1277
+ "eval_rouge2": 0.3854412341399984,
1278
+ "eval_rougeL": 0.46686705922324473,
1279
+ "eval_rougeLsum": 0.4696615201324402,
1280
+ "eval_runtime": 6.6871,
1281
+ "eval_samples_per_second": 9.571,
1282
+ "eval_steps_per_second": 2.393,
1283
+ "step": 7252
1284
+ },
1285
+ {
1286
+ "epoch": 99.0,
1287
+ "eval_loss": 3.750239849090576,
1288
+ "eval_rouge1": 0.4895475548259989,
1289
+ "eval_rouge2": 0.3931543734202324,
1290
+ "eval_rougeL": 0.4729295951578888,
1291
+ "eval_rougeLsum": 0.4733894371856425,
1292
+ "eval_runtime": 6.8243,
1293
+ "eval_samples_per_second": 9.378,
1294
+ "eval_steps_per_second": 2.345,
1295
+ "step": 7326
1296
+ },
1297
+ {
1298
+ "epoch": 100.0,
1299
+ "eval_loss": 3.710012435913086,
1300
+ "eval_rouge1": 0.4922460168917058,
1301
+ "eval_rouge2": 0.38907716748403615,
1302
+ "eval_rougeL": 0.4703757958634286,
1303
+ "eval_rougeLsum": 0.47469578477355245,
1304
+ "eval_runtime": 7.1953,
1305
+ "eval_samples_per_second": 8.895,
1306
+ "eval_steps_per_second": 2.224,
1307
+ "step": 7400
1308
+ },
1309
+ {
1310
+ "epoch": 101.0,
1311
+ "eval_loss": 3.7263288497924805,
1312
+ "eval_rouge1": 0.4994776956737418,
1313
+ "eval_rouge2": 0.4016675015566174,
1314
+ "eval_rougeL": 0.47921650877286537,
1315
+ "eval_rougeLsum": 0.481978781304056,
1316
+ "eval_runtime": 7.1605,
1317
+ "eval_samples_per_second": 8.938,
1318
+ "eval_steps_per_second": 2.234,
1319
+ "step": 7474
1320
+ },
1321
+ {
1322
+ "epoch": 101.35135135135135,
1323
+ "grad_norm": 1.3754329681396484,
1324
+ "learning_rate": 0.00014797297297297295,
1325
+ "loss": 0.0115,
1326
+ "step": 7500
1327
+ },
1328
+ {
1329
+ "epoch": 102.0,
1330
+ "eval_loss": 3.7390670776367188,
1331
+ "eval_rouge1": 0.4970291645397934,
1332
+ "eval_rouge2": 0.3965329334942411,
1333
+ "eval_rougeL": 0.4785005226666328,
1334
+ "eval_rougeLsum": 0.48034491922833267,
1335
+ "eval_runtime": 6.6275,
1336
+ "eval_samples_per_second": 9.657,
1337
+ "eval_steps_per_second": 2.414,
1338
+ "step": 7548
1339
+ },
1340
+ {
1341
+ "epoch": 103.0,
1342
+ "eval_loss": 3.732781410217285,
1343
+ "eval_rouge1": 0.48700489472062974,
1344
+ "eval_rouge2": 0.39143224992971243,
1345
+ "eval_rougeL": 0.4697739833563407,
1346
+ "eval_rougeLsum": 0.47133796360275837,
1347
+ "eval_runtime": 6.758,
1348
+ "eval_samples_per_second": 9.47,
1349
+ "eval_steps_per_second": 2.368,
1350
+ "step": 7622
1351
+ },
1352
+ {
1353
+ "epoch": 104.0,
1354
+ "eval_loss": 3.7326784133911133,
1355
+ "eval_rouge1": 0.48634126558210156,
1356
+ "eval_rouge2": 0.3914253095431699,
1357
+ "eval_rougeL": 0.4662095381023694,
1358
+ "eval_rougeLsum": 0.46828089571132425,
1359
+ "eval_runtime": 6.9292,
1360
+ "eval_samples_per_second": 9.236,
1361
+ "eval_steps_per_second": 2.309,
1362
+ "step": 7696
1363
+ },
1364
+ {
1365
+ "epoch": 105.0,
1366
+ "eval_loss": 3.72397780418396,
1367
+ "eval_rouge1": 0.49207262377656813,
1368
+ "eval_rouge2": 0.3926530860066015,
1369
+ "eval_rougeL": 0.4716827714689972,
1370
+ "eval_rougeLsum": 0.47383906517378155,
1371
+ "eval_runtime": 6.6924,
1372
+ "eval_samples_per_second": 9.563,
1373
+ "eval_steps_per_second": 2.391,
1374
+ "step": 7770
1375
+ },
1376
+ {
1377
+ "epoch": 106.0,
1378
+ "eval_loss": 3.71506404876709,
1379
+ "eval_rouge1": 0.491413986073613,
1380
+ "eval_rouge2": 0.39806354091405716,
1381
+ "eval_rougeL": 0.47232948697868965,
1382
+ "eval_rougeLsum": 0.47370687635582465,
1383
+ "eval_runtime": 6.8886,
1384
+ "eval_samples_per_second": 9.291,
1385
+ "eval_steps_per_second": 2.323,
1386
+ "step": 7844
1387
+ },
1388
+ {
1389
+ "epoch": 107.0,
1390
+ "eval_loss": 3.7703864574432373,
1391
+ "eval_rouge1": 0.49389730784828345,
1392
+ "eval_rouge2": 0.39541639053141187,
1393
+ "eval_rougeL": 0.4714732208294661,
1394
+ "eval_rougeLsum": 0.47623481194977557,
1395
+ "eval_runtime": 6.9886,
1396
+ "eval_samples_per_second": 9.158,
1397
+ "eval_steps_per_second": 2.289,
1398
+ "step": 7918
1399
+ },
1400
+ {
1401
+ "epoch": 108.0,
1402
+ "eval_loss": 3.731736421585083,
1403
+ "eval_rouge1": 0.49478828073404685,
1404
+ "eval_rouge2": 0.39657333313753584,
1405
+ "eval_rougeL": 0.4749519387034692,
1406
+ "eval_rougeLsum": 0.47610183775428533,
1407
+ "eval_runtime": 7.0844,
1408
+ "eval_samples_per_second": 9.034,
1409
+ "eval_steps_per_second": 2.258,
1410
+ "step": 7992
1411
+ },
1412
+ {
1413
+ "epoch": 108.10810810810811,
1414
+ "grad_norm": 0.15748290717601776,
1415
+ "learning_rate": 0.00013783783783783782,
1416
+ "loss": 0.0097,
1417
+ "step": 8000
1418
+ },
1419
+ {
1420
+ "epoch": 109.0,
1421
+ "eval_loss": 3.7394156455993652,
1422
+ "eval_rouge1": 0.4928722114905978,
1423
+ "eval_rouge2": 0.39617632886171655,
1424
+ "eval_rougeL": 0.4727238492899394,
1425
+ "eval_rougeLsum": 0.4738978259656522,
1426
+ "eval_runtime": 6.7715,
1427
+ "eval_samples_per_second": 9.451,
1428
+ "eval_steps_per_second": 2.363,
1429
+ "step": 8066
1430
+ },
1431
+ {
1432
+ "epoch": 110.0,
1433
+ "eval_loss": 3.782604217529297,
1434
+ "eval_rouge1": 0.48456677608733023,
1435
+ "eval_rouge2": 0.39200786618317157,
1436
+ "eval_rougeL": 0.46735627531908003,
1437
+ "eval_rougeLsum": 0.4678895131769854,
1438
+ "eval_runtime": 6.6784,
1439
+ "eval_samples_per_second": 9.583,
1440
+ "eval_steps_per_second": 2.396,
1441
+ "step": 8140
1442
+ },
1443
+ {
1444
+ "epoch": 111.0,
1445
+ "eval_loss": 3.756638526916504,
1446
+ "eval_rouge1": 0.4845583346799728,
1447
+ "eval_rouge2": 0.39273356781728475,
1448
+ "eval_rougeL": 0.46727953305101155,
1449
+ "eval_rougeLsum": 0.46750848691275326,
1450
+ "eval_runtime": 6.7593,
1451
+ "eval_samples_per_second": 9.468,
1452
+ "eval_steps_per_second": 2.367,
1453
+ "step": 8214
1454
+ },
1455
+ {
1456
+ "epoch": 112.0,
1457
+ "eval_loss": 3.7435970306396484,
1458
+ "eval_rouge1": 0.47934894419153573,
1459
+ "eval_rouge2": 0.38451063069829866,
1460
+ "eval_rougeL": 0.460189645563753,
1461
+ "eval_rougeLsum": 0.46059641183020916,
1462
+ "eval_runtime": 6.7106,
1463
+ "eval_samples_per_second": 9.537,
1464
+ "eval_steps_per_second": 2.384,
1465
+ "step": 8288
1466
+ },
1467
+ {
1468
+ "epoch": 113.0,
1469
+ "eval_loss": 3.7368521690368652,
1470
+ "eval_rouge1": 0.4829508280944451,
1471
+ "eval_rouge2": 0.3823021635565298,
1472
+ "eval_rougeL": 0.4603754136609347,
1473
+ "eval_rougeLsum": 0.46119234388219343,
1474
+ "eval_runtime": 6.9009,
1475
+ "eval_samples_per_second": 9.274,
1476
+ "eval_steps_per_second": 2.319,
1477
+ "step": 8362
1478
+ },
1479
+ {
1480
+ "epoch": 114.0,
1481
+ "eval_loss": 3.753373622894287,
1482
+ "eval_rouge1": 0.48550199682179285,
1483
+ "eval_rouge2": 0.39669425610509723,
1484
+ "eval_rougeL": 0.46928318330826313,
1485
+ "eval_rougeLsum": 0.4700911939934148,
1486
+ "eval_runtime": 6.9224,
1487
+ "eval_samples_per_second": 9.245,
1488
+ "eval_steps_per_second": 2.311,
1489
+ "step": 8436
1490
+ },
1491
+ {
1492
+ "epoch": 114.86486486486487,
1493
+ "grad_norm": 2.249493360519409,
1494
+ "learning_rate": 0.00012770270270270269,
1495
+ "loss": 0.0081,
1496
+ "step": 8500
1497
+ },
1498
+ {
1499
+ "epoch": 115.0,
1500
+ "eval_loss": 3.7596099376678467,
1501
+ "eval_rouge1": 0.4844489870502281,
1502
+ "eval_rouge2": 0.39373641353300476,
1503
+ "eval_rougeL": 0.465943647782728,
1504
+ "eval_rougeLsum": 0.4667838391510246,
1505
+ "eval_runtime": 6.7565,
1506
+ "eval_samples_per_second": 9.472,
1507
+ "eval_steps_per_second": 2.368,
1508
+ "step": 8510
1509
+ },
1510
+ {
1511
+ "epoch": 116.0,
1512
+ "eval_loss": 3.7971744537353516,
1513
+ "eval_rouge1": 0.4839609425846231,
1514
+ "eval_rouge2": 0.39429760970418737,
1515
+ "eval_rougeL": 0.4676976417871506,
1516
+ "eval_rougeLsum": 0.46788383269053146,
1517
+ "eval_runtime": 6.7435,
1518
+ "eval_samples_per_second": 9.491,
1519
+ "eval_steps_per_second": 2.373,
1520
+ "step": 8584
1521
+ },
1522
+ {
1523
+ "epoch": 117.0,
1524
+ "eval_loss": 3.796170711517334,
1525
+ "eval_rouge1": 0.4890036495615311,
1526
+ "eval_rouge2": 0.40029838829858966,
1527
+ "eval_rougeL": 0.4695189944140329,
1528
+ "eval_rougeLsum": 0.47150052045445745,
1529
+ "eval_runtime": 6.8876,
1530
+ "eval_samples_per_second": 9.292,
1531
+ "eval_steps_per_second": 2.323,
1532
+ "step": 8658
1533
+ },
1534
+ {
1535
+ "epoch": 118.0,
1536
+ "eval_loss": 3.7930757999420166,
1537
+ "eval_rouge1": 0.49228898940808674,
1538
+ "eval_rouge2": 0.39827560867374456,
1539
+ "eval_rougeL": 0.4744564034893066,
1540
+ "eval_rougeLsum": 0.4766465053914651,
1541
+ "eval_runtime": 7.2191,
1542
+ "eval_samples_per_second": 8.865,
1543
+ "eval_steps_per_second": 2.216,
1544
+ "step": 8732
1545
+ },
1546
+ {
1547
+ "epoch": 119.0,
1548
+ "eval_loss": 3.8108878135681152,
1549
+ "eval_rouge1": 0.4847730471627255,
1550
+ "eval_rouge2": 0.3942853548976314,
1551
+ "eval_rougeL": 0.46643367219610266,
1552
+ "eval_rougeLsum": 0.46858946699295617,
1553
+ "eval_runtime": 7.3767,
1554
+ "eval_samples_per_second": 8.676,
1555
+ "eval_steps_per_second": 2.169,
1556
+ "step": 8806
1557
+ },
1558
+ {
1559
+ "epoch": 120.0,
1560
+ "eval_loss": 3.8008246421813965,
1561
+ "eval_rouge1": 0.4846634237685579,
1562
+ "eval_rouge2": 0.39052270581455634,
1563
+ "eval_rougeL": 0.46516978082832616,
1564
+ "eval_rougeLsum": 0.4660286941183181,
1565
+ "eval_runtime": 7.1943,
1566
+ "eval_samples_per_second": 8.896,
1567
+ "eval_steps_per_second": 2.224,
1568
+ "step": 8880
1569
+ },
1570
+ {
1571
+ "epoch": 121.0,
1572
+ "eval_loss": 3.837533712387085,
1573
+ "eval_rouge1": 0.480238168191317,
1574
+ "eval_rouge2": 0.3836647960301529,
1575
+ "eval_rougeL": 0.45981846963427486,
1576
+ "eval_rougeLsum": 0.46002047511561506,
1577
+ "eval_runtime": 7.4528,
1578
+ "eval_samples_per_second": 8.587,
1579
+ "eval_steps_per_second": 2.147,
1580
+ "step": 8954
1581
+ },
1582
+ {
1583
+ "epoch": 121.62162162162163,
1584
+ "grad_norm": 0.156394362449646,
1585
+ "learning_rate": 0.00011756756756756755,
1586
+ "loss": 0.0073,
1587
+ "step": 9000
1588
+ },
1589
+ {
1590
+ "epoch": 122.0,
1591
+ "eval_loss": 3.844420909881592,
1592
+ "eval_rouge1": 0.48399770438699874,
1593
+ "eval_rouge2": 0.38640038347896755,
1594
+ "eval_rougeL": 0.46195539603011354,
1595
+ "eval_rougeLsum": 0.46383728530832075,
1596
+ "eval_runtime": 6.5224,
1597
+ "eval_samples_per_second": 9.812,
1598
+ "eval_steps_per_second": 2.453,
1599
+ "step": 9028
1600
+ },
1601
+ {
1602
+ "epoch": 123.0,
1603
+ "eval_loss": 3.8776814937591553,
1604
+ "eval_rouge1": 0.4854005110821537,
1605
+ "eval_rouge2": 0.3917034412373144,
1606
+ "eval_rougeL": 0.4668504149804634,
1607
+ "eval_rougeLsum": 0.4673636008329948,
1608
+ "eval_runtime": 6.6767,
1609
+ "eval_samples_per_second": 9.586,
1610
+ "eval_steps_per_second": 2.396,
1611
+ "step": 9102
1612
+ },
1613
+ {
1614
+ "epoch": 124.0,
1615
+ "eval_loss": 3.865213394165039,
1616
+ "eval_rouge1": 0.48354814096021004,
1617
+ "eval_rouge2": 0.3875565081336061,
1618
+ "eval_rougeL": 0.4644387512744705,
1619
+ "eval_rougeLsum": 0.4657678163591755,
1620
+ "eval_runtime": 6.7223,
1621
+ "eval_samples_per_second": 9.521,
1622
+ "eval_steps_per_second": 2.38,
1623
+ "step": 9176
1624
+ },
1625
+ {
1626
+ "epoch": 125.0,
1627
+ "eval_loss": 3.8568525314331055,
1628
+ "eval_rouge1": 0.49281072095688017,
1629
+ "eval_rouge2": 0.39982303603622116,
1630
+ "eval_rougeL": 0.47299639047330055,
1631
+ "eval_rougeLsum": 0.474738468225831,
1632
+ "eval_runtime": 6.714,
1633
+ "eval_samples_per_second": 9.532,
1634
+ "eval_steps_per_second": 2.383,
1635
+ "step": 9250
1636
+ },
1637
+ {
1638
+ "epoch": 126.0,
1639
+ "eval_loss": 3.874713659286499,
1640
+ "eval_rouge1": 0.48223669204507696,
1641
+ "eval_rouge2": 0.3940917922642585,
1642
+ "eval_rougeL": 0.46483980398639463,
1643
+ "eval_rougeLsum": 0.4654093903936942,
1644
+ "eval_runtime": 6.8849,
1645
+ "eval_samples_per_second": 9.296,
1646
+ "eval_steps_per_second": 2.324,
1647
+ "step": 9324
1648
+ },
1649
+ {
1650
+ "epoch": 127.0,
1651
+ "eval_loss": 3.8582425117492676,
1652
+ "eval_rouge1": 0.48577800020767237,
1653
+ "eval_rouge2": 0.3893328433203812,
1654
+ "eval_rougeL": 0.4642142206721902,
1655
+ "eval_rougeLsum": 0.46762126305920615,
1656
+ "eval_runtime": 7.1741,
1657
+ "eval_samples_per_second": 8.921,
1658
+ "eval_steps_per_second": 2.23,
1659
+ "step": 9398
1660
+ },
1661
+ {
1662
+ "epoch": 128.0,
1663
+ "eval_loss": 3.8560242652893066,
1664
+ "eval_rouge1": 0.48276042100553784,
1665
+ "eval_rouge2": 0.3935526373639349,
1666
+ "eval_rougeL": 0.46394413427722736,
1667
+ "eval_rougeLsum": 0.46693603589333066,
1668
+ "eval_runtime": 7.4705,
1669
+ "eval_samples_per_second": 8.567,
1670
+ "eval_steps_per_second": 2.142,
1671
+ "step": 9472
1672
+ },
1673
+ {
1674
+ "epoch": 128.3783783783784,
1675
+ "grad_norm": 0.5053192377090454,
1676
+ "learning_rate": 0.00010743243243243243,
1677
+ "loss": 0.0052,
1678
+ "step": 9500
1679
+ },
1680
+ {
1681
+ "epoch": 129.0,
1682
+ "eval_loss": 3.8928046226501465,
1683
+ "eval_rouge1": 0.4827880613762454,
1684
+ "eval_rouge2": 0.39063612795118435,
1685
+ "eval_rougeL": 0.46292609876431945,
1686
+ "eval_rougeLsum": 0.4639229804932192,
1687
+ "eval_runtime": 6.7521,
1688
+ "eval_samples_per_second": 9.479,
1689
+ "eval_steps_per_second": 2.37,
1690
+ "step": 9546
1691
+ },
1692
+ {
1693
+ "epoch": 130.0,
1694
+ "eval_loss": 3.8779563903808594,
1695
+ "eval_rouge1": 0.4844923294167751,
1696
+ "eval_rouge2": 0.38633459533219433,
1697
+ "eval_rougeL": 0.46262521762970926,
1698
+ "eval_rougeLsum": 0.4640136282049044,
1699
+ "eval_runtime": 6.7605,
1700
+ "eval_samples_per_second": 9.467,
1701
+ "eval_steps_per_second": 2.367,
1702
+ "step": 9620
1703
+ },
1704
+ {
1705
+ "epoch": 131.0,
1706
+ "eval_loss": 3.866152286529541,
1707
+ "eval_rouge1": 0.4852900095674466,
1708
+ "eval_rouge2": 0.391461632155927,
1709
+ "eval_rougeL": 0.4646976857262868,
1710
+ "eval_rougeLsum": 0.4650219596477825,
1711
+ "eval_runtime": 7.1336,
1712
+ "eval_samples_per_second": 8.972,
1713
+ "eval_steps_per_second": 2.243,
1714
+ "step": 9694
1715
+ },
1716
+ {
1717
+ "epoch": 132.0,
1718
+ "eval_loss": 3.876262664794922,
1719
+ "eval_rouge1": 0.4814059761270737,
1720
+ "eval_rouge2": 0.38660843742603485,
1721
+ "eval_rougeL": 0.4597208266484611,
1722
+ "eval_rougeLsum": 0.46074176653361254,
1723
+ "eval_runtime": 7.2201,
1724
+ "eval_samples_per_second": 8.864,
1725
+ "eval_steps_per_second": 2.216,
1726
+ "step": 9768
1727
+ },
1728
+ {
1729
+ "epoch": 133.0,
1730
+ "eval_loss": 3.8748536109924316,
1731
+ "eval_rouge1": 0.4845049505767603,
1732
+ "eval_rouge2": 0.38630241264644166,
1733
+ "eval_rougeL": 0.46161461756838357,
1734
+ "eval_rougeLsum": 0.4614392713949589,
1735
+ "eval_runtime": 7.3979,
1736
+ "eval_samples_per_second": 8.651,
1737
+ "eval_steps_per_second": 2.163,
1738
+ "step": 9842
1739
+ },
1740
+ {
1741
+ "epoch": 134.0,
1742
+ "eval_loss": 3.903346300125122,
1743
+ "eval_rouge1": 0.48684820794711436,
1744
+ "eval_rouge2": 0.39076743252039103,
1745
+ "eval_rougeL": 0.46325285677108063,
1746
+ "eval_rougeLsum": 0.465521140679641,
1747
+ "eval_runtime": 7.5395,
1748
+ "eval_samples_per_second": 8.489,
1749
+ "eval_steps_per_second": 2.122,
1750
+ "step": 9916
1751
+ },
1752
+ {
1753
+ "epoch": 135.0,
1754
+ "eval_loss": 3.913891315460205,
1755
+ "eval_rouge1": 0.48673702365042004,
1756
+ "eval_rouge2": 0.3912891412344346,
1757
+ "eval_rougeL": 0.46486407293584286,
1758
+ "eval_rougeLsum": 0.46762822555796624,
1759
+ "eval_runtime": 7.2933,
1760
+ "eval_samples_per_second": 8.775,
1761
+ "eval_steps_per_second": 2.194,
1762
+ "step": 9990
1763
+ },
1764
+ {
1765
+ "epoch": 135.13513513513513,
1766
+ "grad_norm": 0.164429172873497,
1767
+ "learning_rate": 9.72972972972973e-05,
1768
+ "loss": 0.0056,
1769
+ "step": 10000
1770
+ },
1771
+ {
1772
+ "epoch": 136.0,
1773
+ "eval_loss": 3.932033061981201,
1774
+ "eval_rouge1": 0.4843296592917674,
1775
+ "eval_rouge2": 0.38711489173362024,
1776
+ "eval_rougeL": 0.4628261592622239,
1777
+ "eval_rougeLsum": 0.46403305263253225,
1778
+ "eval_runtime": 6.7372,
1779
+ "eval_samples_per_second": 9.5,
1780
+ "eval_steps_per_second": 2.375,
1781
+ "step": 10064
1782
+ },
1783
+ {
1784
+ "epoch": 137.0,
1785
+ "eval_loss": 3.9207522869110107,
1786
+ "eval_rouge1": 0.48663560972636954,
1787
+ "eval_rouge2": 0.38917485963208237,
1788
+ "eval_rougeL": 0.4641843636902843,
1789
+ "eval_rougeLsum": 0.4670661984486967,
1790
+ "eval_runtime": 7.0897,
1791
+ "eval_samples_per_second": 9.027,
1792
+ "eval_steps_per_second": 2.257,
1793
+ "step": 10138
1794
+ },
1795
+ {
1796
+ "epoch": 138.0,
1797
+ "eval_loss": 3.923243999481201,
1798
+ "eval_rouge1": 0.4869405313162995,
1799
+ "eval_rouge2": 0.39033225065949406,
1800
+ "eval_rougeL": 0.4660086299963394,
1801
+ "eval_rougeLsum": 0.4694681627569816,
1802
+ "eval_runtime": 7.3705,
1803
+ "eval_samples_per_second": 8.683,
1804
+ "eval_steps_per_second": 2.171,
1805
+ "step": 10212
1806
+ },
1807
+ {
1808
+ "epoch": 139.0,
1809
+ "eval_loss": 3.9049696922302246,
1810
+ "eval_rouge1": 0.4857155018095176,
1811
+ "eval_rouge2": 0.3903974717105526,
1812
+ "eval_rougeL": 0.46598084906502785,
1813
+ "eval_rougeLsum": 0.4687923513004851,
1814
+ "eval_runtime": 7.5586,
1815
+ "eval_samples_per_second": 8.467,
1816
+ "eval_steps_per_second": 2.117,
1817
+ "step": 10286
1818
+ },
1819
+ {
1820
+ "epoch": 140.0,
1821
+ "eval_loss": 3.9089577198028564,
1822
+ "eval_rouge1": 0.49232283072813465,
1823
+ "eval_rouge2": 0.39755334531122133,
1824
+ "eval_rougeL": 0.4720020408046367,
1825
+ "eval_rougeLsum": 0.4733960027621831,
1826
+ "eval_runtime": 7.4052,
1827
+ "eval_samples_per_second": 8.643,
1828
+ "eval_steps_per_second": 2.161,
1829
+ "step": 10360
1830
+ },
1831
+ {
1832
+ "epoch": 141.0,
1833
+ "eval_loss": 3.9259438514709473,
1834
+ "eval_rouge1": 0.48520578506166845,
1835
+ "eval_rouge2": 0.3929926818071112,
1836
+ "eval_rougeL": 0.4657921992214292,
1837
+ "eval_rougeLsum": 0.46805633734997604,
1838
+ "eval_runtime": 7.7086,
1839
+ "eval_samples_per_second": 8.302,
1840
+ "eval_steps_per_second": 2.076,
1841
+ "step": 10434
1842
+ },
1843
+ {
1844
+ "epoch": 141.8918918918919,
1845
+ "grad_norm": 0.04262608289718628,
1846
+ "learning_rate": 8.716216216216215e-05,
1847
+ "loss": 0.0038,
1848
+ "step": 10500
1849
+ },
1850
+ {
1851
+ "epoch": 142.0,
1852
+ "eval_loss": 3.944688558578491,
1853
+ "eval_rouge1": 0.487675604262949,
1854
+ "eval_rouge2": 0.3921027004601982,
1855
+ "eval_rougeL": 0.4679360442338828,
1856
+ "eval_rougeLsum": 0.4707407417491424,
1857
+ "eval_runtime": 6.5398,
1858
+ "eval_samples_per_second": 9.786,
1859
+ "eval_steps_per_second": 2.447,
1860
+ "step": 10508
1861
+ },
1862
+ {
1863
+ "epoch": 143.0,
1864
+ "eval_loss": 3.9202613830566406,
1865
+ "eval_rouge1": 0.4869107696524746,
1866
+ "eval_rouge2": 0.39163777862392646,
1867
+ "eval_rougeL": 0.4667490559738572,
1868
+ "eval_rougeLsum": 0.4693423272541999,
1869
+ "eval_runtime": 6.705,
1870
+ "eval_samples_per_second": 9.545,
1871
+ "eval_steps_per_second": 2.386,
1872
+ "step": 10582
1873
+ },
1874
+ {
1875
+ "epoch": 144.0,
1876
+ "eval_loss": 3.948978900909424,
1877
+ "eval_rouge1": 0.49250533905328897,
1878
+ "eval_rouge2": 0.3959336606525481,
1879
+ "eval_rougeL": 0.47206086537528646,
1880
+ "eval_rougeLsum": 0.473413686648378,
1881
+ "eval_runtime": 6.853,
1882
+ "eval_samples_per_second": 9.339,
1883
+ "eval_steps_per_second": 2.335,
1884
+ "step": 10656
1885
+ },
1886
+ {
1887
+ "epoch": 145.0,
1888
+ "eval_loss": 3.9446568489074707,
1889
+ "eval_rouge1": 0.48810661530935073,
1890
+ "eval_rouge2": 0.3932420193989471,
1891
+ "eval_rougeL": 0.467612141938169,
1892
+ "eval_rougeLsum": 0.4700796872193581,
1893
+ "eval_runtime": 6.8609,
1894
+ "eval_samples_per_second": 9.328,
1895
+ "eval_steps_per_second": 2.332,
1896
+ "step": 10730
1897
+ },
1898
+ {
1899
+ "epoch": 146.0,
1900
+ "eval_loss": 3.9405150413513184,
1901
+ "eval_rouge1": 0.48480711997528214,
1902
+ "eval_rouge2": 0.3933858006917045,
1903
+ "eval_rougeL": 0.46612345176895637,
1904
+ "eval_rougeLsum": 0.46797061838955234,
1905
+ "eval_runtime": 6.7331,
1906
+ "eval_samples_per_second": 9.505,
1907
+ "eval_steps_per_second": 2.376,
1908
+ "step": 10804
1909
+ },
1910
+ {
1911
+ "epoch": 147.0,
1912
+ "eval_loss": 3.9228992462158203,
1913
+ "eval_rouge1": 0.4873307537597772,
1914
+ "eval_rouge2": 0.39731296067287103,
1915
+ "eval_rougeL": 0.47021025970811053,
1916
+ "eval_rougeLsum": 0.4720477730864451,
1917
+ "eval_runtime": 6.9553,
1918
+ "eval_samples_per_second": 9.202,
1919
+ "eval_steps_per_second": 2.3,
1920
+ "step": 10878
1921
+ },
1922
+ {
1923
+ "epoch": 148.0,
1924
+ "eval_loss": 3.927485227584839,
1925
+ "eval_rouge1": 0.4894933069163522,
1926
+ "eval_rouge2": 0.39630502877208873,
1927
+ "eval_rougeL": 0.4706409032694612,
1928
+ "eval_rougeLsum": 0.47251705975502384,
1929
+ "eval_runtime": 6.8852,
1930
+ "eval_samples_per_second": 9.295,
1931
+ "eval_steps_per_second": 2.324,
1932
+ "step": 10952
1933
+ },
1934
+ {
1935
+ "epoch": 148.64864864864865,
1936
+ "grad_norm": 0.06265202164649963,
1937
+ "learning_rate": 7.702702702702701e-05,
1938
+ "loss": 0.0046,
1939
+ "step": 11000
1940
+ },
1941
+ {
1942
+ "epoch": 149.0,
1943
+ "eval_loss": 3.9115383625030518,
1944
+ "eval_rouge1": 0.48236726641895555,
1945
+ "eval_rouge2": 0.39058286433636713,
1946
+ "eval_rougeL": 0.46227491108174484,
1947
+ "eval_rougeLsum": 0.4629699932236985,
1948
+ "eval_runtime": 6.7009,
1949
+ "eval_samples_per_second": 9.551,
1950
+ "eval_steps_per_second": 2.388,
1951
+ "step": 11026
1952
+ },
1953
+ {
1954
+ "epoch": 150.0,
1955
+ "eval_loss": 3.930911064147949,
1956
+ "eval_rouge1": 0.4878527875495306,
1957
+ "eval_rouge2": 0.39283884580724954,
1958
+ "eval_rougeL": 0.4671990073575799,
1959
+ "eval_rougeLsum": 0.47041003584932495,
1960
+ "eval_runtime": 6.6879,
1961
+ "eval_samples_per_second": 9.57,
1962
+ "eval_steps_per_second": 2.392,
1963
+ "step": 11100
1964
+ },
1965
+ {
1966
+ "epoch": 151.0,
1967
+ "eval_loss": 3.9732909202575684,
1968
+ "eval_rouge1": 0.4842635411230555,
1969
+ "eval_rouge2": 0.3934133257871197,
1970
+ "eval_rougeL": 0.46621039602137504,
1971
+ "eval_rougeLsum": 0.46784839735484063,
1972
+ "eval_runtime": 6.7159,
1973
+ "eval_samples_per_second": 9.53,
1974
+ "eval_steps_per_second": 2.382,
1975
+ "step": 11174
1976
+ },
1977
+ {
1978
+ "epoch": 152.0,
1979
+ "eval_loss": 3.952836036682129,
1980
+ "eval_rouge1": 0.48821078362566034,
1981
+ "eval_rouge2": 0.3930914690285585,
1982
+ "eval_rougeL": 0.46691136255327237,
1983
+ "eval_rougeLsum": 0.47018503206271367,
1984
+ "eval_runtime": 6.8389,
1985
+ "eval_samples_per_second": 9.358,
1986
+ "eval_steps_per_second": 2.34,
1987
+ "step": 11248
1988
+ },
1989
+ {
1990
+ "epoch": 153.0,
1991
+ "eval_loss": 3.9353346824645996,
1992
+ "eval_rouge1": 0.49172107393851816,
1993
+ "eval_rouge2": 0.394135306910142,
1994
+ "eval_rougeL": 0.47053235476800326,
1995
+ "eval_rougeLsum": 0.47467536744383443,
1996
+ "eval_runtime": 7.0262,
1997
+ "eval_samples_per_second": 9.109,
1998
+ "eval_steps_per_second": 2.277,
1999
+ "step": 11322
2000
+ },
2001
+ {
2002
+ "epoch": 154.0,
2003
+ "eval_loss": 3.955352783203125,
2004
+ "eval_rouge1": 0.4925059248834573,
2005
+ "eval_rouge2": 0.39699149764016994,
2006
+ "eval_rougeL": 0.4718398234633252,
2007
+ "eval_rougeLsum": 0.47625245196436417,
2008
+ "eval_runtime": 7.3091,
2009
+ "eval_samples_per_second": 8.756,
2010
+ "eval_steps_per_second": 2.189,
2011
+ "step": 11396
2012
+ },
2013
+ {
2014
+ "epoch": 155.0,
2015
+ "eval_loss": 3.9426536560058594,
2016
+ "eval_rouge1": 0.4924969427568193,
2017
+ "eval_rouge2": 0.3960196634992188,
2018
+ "eval_rougeL": 0.47242435472194855,
2019
+ "eval_rougeLsum": 0.47677592847041894,
2020
+ "eval_runtime": 7.5133,
2021
+ "eval_samples_per_second": 8.518,
2022
+ "eval_steps_per_second": 2.13,
2023
+ "step": 11470
2024
+ },
2025
+ {
2026
+ "epoch": 155.40540540540542,
2027
+ "grad_norm": 0.0715257003903389,
2028
+ "learning_rate": 6.689189189189189e-05,
2029
+ "loss": 0.0037,
2030
+ "step": 11500
2031
+ },
2032
+ {
2033
+ "epoch": 156.0,
2034
+ "eval_loss": 3.933366298675537,
2035
+ "eval_rouge1": 0.49233799907987563,
2036
+ "eval_rouge2": 0.3965013420598218,
2037
+ "eval_rougeL": 0.47174545806545665,
2038
+ "eval_rougeLsum": 0.47602740740299954,
2039
+ "eval_runtime": 6.8977,
2040
+ "eval_samples_per_second": 9.278,
2041
+ "eval_steps_per_second": 2.32,
2042
+ "step": 11544
2043
+ },
2044
+ {
2045
+ "epoch": 157.0,
2046
+ "eval_loss": 3.9453284740448,
2047
+ "eval_rouge1": 0.4935660910336177,
2048
+ "eval_rouge2": 0.3957963732927968,
2049
+ "eval_rougeL": 0.47177139453079964,
2050
+ "eval_rougeLsum": 0.4755186608753167,
2051
+ "eval_runtime": 6.7823,
2052
+ "eval_samples_per_second": 9.436,
2053
+ "eval_steps_per_second": 2.359,
2054
+ "step": 11618
2055
+ },
2056
+ {
2057
+ "epoch": 158.0,
2058
+ "eval_loss": 3.9491419792175293,
2059
+ "eval_rouge1": 0.4930742424700606,
2060
+ "eval_rouge2": 0.39526285411169537,
2061
+ "eval_rougeL": 0.4719829435372723,
2062
+ "eval_rougeLsum": 0.4759326109467592,
2063
+ "eval_runtime": 6.8284,
2064
+ "eval_samples_per_second": 9.373,
2065
+ "eval_steps_per_second": 2.343,
2066
+ "step": 11692
2067
+ },
2068
+ {
2069
+ "epoch": 159.0,
2070
+ "eval_loss": 3.953434467315674,
2071
+ "eval_rouge1": 0.49316892275094,
2072
+ "eval_rouge2": 0.3964291062584909,
2073
+ "eval_rougeL": 0.4720610975684992,
2074
+ "eval_rougeLsum": 0.47604465153214315,
2075
+ "eval_runtime": 7.0341,
2076
+ "eval_samples_per_second": 9.099,
2077
+ "eval_steps_per_second": 2.275,
2078
+ "step": 11766
2079
+ },
2080
+ {
2081
+ "epoch": 160.0,
2082
+ "eval_loss": 3.961452007293701,
2083
+ "eval_rouge1": 0.49376119479297864,
2084
+ "eval_rouge2": 0.39647298452806135,
2085
+ "eval_rougeL": 0.47232622651544753,
2086
+ "eval_rougeLsum": 0.476869743899335,
2087
+ "eval_runtime": 7.0864,
2088
+ "eval_samples_per_second": 9.031,
2089
+ "eval_steps_per_second": 2.258,
2090
+ "step": 11840
2091
+ },
2092
+ {
2093
+ "epoch": 161.0,
2094
+ "eval_loss": 3.974522113800049,
2095
+ "eval_rouge1": 0.49152727212946457,
2096
+ "eval_rouge2": 0.3953004424504709,
2097
+ "eval_rougeL": 0.47023604272642827,
2098
+ "eval_rougeLsum": 0.4732774227264972,
2099
+ "eval_runtime": 7.4592,
2100
+ "eval_samples_per_second": 8.58,
2101
+ "eval_steps_per_second": 2.145,
2102
+ "step": 11914
2103
+ },
2104
+ {
2105
+ "epoch": 162.0,
2106
+ "eval_loss": 3.979368209838867,
2107
+ "eval_rouge1": 0.49210496109014745,
2108
+ "eval_rouge2": 0.3957612104808744,
2109
+ "eval_rougeL": 0.47146803881202126,
2110
+ "eval_rougeLsum": 0.4751965635581662,
2111
+ "eval_runtime": 7.5133,
2112
+ "eval_samples_per_second": 8.518,
2113
+ "eval_steps_per_second": 2.13,
2114
+ "step": 11988
2115
+ },
2116
+ {
2117
+ "epoch": 162.16216216216216,
2118
+ "grad_norm": 0.020755620673298836,
2119
+ "learning_rate": 5.6756756756756757e-05,
2120
+ "loss": 0.0033,
2121
+ "step": 12000
2122
+ },
2123
+ {
2124
+ "epoch": 163.0,
2125
+ "eval_loss": 3.9921233654022217,
2126
+ "eval_rouge1": 0.4960050950060007,
2127
+ "eval_rouge2": 0.39999937852342404,
2128
+ "eval_rougeL": 0.4755213708113314,
2129
+ "eval_rougeLsum": 0.4795628358236831,
2130
+ "eval_runtime": 6.9003,
2131
+ "eval_samples_per_second": 9.275,
2132
+ "eval_steps_per_second": 2.319,
2133
+ "step": 12062
2134
+ },
2135
+ {
2136
+ "epoch": 164.0,
2137
+ "eval_loss": 4.0162272453308105,
2138
+ "eval_rouge1": 0.492801394287687,
2139
+ "eval_rouge2": 0.397442056436076,
2140
+ "eval_rougeL": 0.47103266304177527,
2141
+ "eval_rougeLsum": 0.4748829924767563,
2142
+ "eval_runtime": 6.8719,
2143
+ "eval_samples_per_second": 9.313,
2144
+ "eval_steps_per_second": 2.328,
2145
+ "step": 12136
2146
+ },
2147
+ {
2148
+ "epoch": 165.0,
2149
+ "eval_loss": 3.996596097946167,
2150
+ "eval_rouge1": 0.49315466512445916,
2151
+ "eval_rouge2": 0.3985964076994628,
2152
+ "eval_rougeL": 0.4735840963826083,
2153
+ "eval_rougeLsum": 0.47858269202555725,
2154
+ "eval_runtime": 6.9342,
2155
+ "eval_samples_per_second": 9.23,
2156
+ "eval_steps_per_second": 2.307,
2157
+ "step": 12210
2158
+ },
2159
+ {
2160
+ "epoch": 166.0,
2161
+ "eval_loss": 3.995129108428955,
2162
+ "eval_rouge1": 0.4941258909094296,
2163
+ "eval_rouge2": 0.4015187340990569,
2164
+ "eval_rougeL": 0.4758513247728338,
2165
+ "eval_rougeLsum": 0.4789241505191637,
2166
+ "eval_runtime": 7.3809,
2167
+ "eval_samples_per_second": 8.671,
2168
+ "eval_steps_per_second": 2.168,
2169
+ "step": 12284
2170
+ },
2171
+ {
2172
+ "epoch": 167.0,
2173
+ "eval_loss": 4.009509086608887,
2174
+ "eval_rouge1": 0.4946445747494288,
2175
+ "eval_rouge2": 0.40202139316604324,
2176
+ "eval_rougeL": 0.4773328124627762,
2177
+ "eval_rougeLsum": 0.48067203669273695,
2178
+ "eval_runtime": 7.3061,
2179
+ "eval_samples_per_second": 8.76,
2180
+ "eval_steps_per_second": 2.19,
2181
+ "step": 12358
2182
+ },
2183
+ {
2184
+ "epoch": 168.0,
2185
+ "eval_loss": 4.0200018882751465,
2186
+ "eval_rouge1": 0.4927259103544268,
2187
+ "eval_rouge2": 0.40104825000910027,
2188
+ "eval_rougeL": 0.4735139731424237,
2189
+ "eval_rougeLsum": 0.4756183913048333,
2190
+ "eval_runtime": 7.5103,
2191
+ "eval_samples_per_second": 8.522,
2192
+ "eval_steps_per_second": 2.13,
2193
+ "step": 12432
2194
+ },
2195
+ {
2196
+ "epoch": 168.9189189189189,
2197
+ "grad_norm": 1.5782980918884277,
2198
+ "learning_rate": 4.6621621621621615e-05,
2199
+ "loss": 0.0034,
2200
+ "step": 12500
2201
+ },
2202
+ {
2203
+ "epoch": 169.0,
2204
+ "eval_loss": 4.012574195861816,
2205
+ "eval_rouge1": 0.496091078807664,
2206
+ "eval_rouge2": 0.40862976551688035,
2207
+ "eval_rougeL": 0.48006706521844855,
2208
+ "eval_rougeLsum": 0.48333388286468126,
2209
+ "eval_runtime": 6.7294,
2210
+ "eval_samples_per_second": 9.51,
2211
+ "eval_steps_per_second": 2.378,
2212
+ "step": 12506
2213
+ },
2214
+ {
2215
+ "epoch": 170.0,
2216
+ "eval_loss": 3.999107837677002,
2217
+ "eval_rouge1": 0.4945963719889479,
2218
+ "eval_rouge2": 0.40532127010917274,
2219
+ "eval_rougeL": 0.4757107170560549,
2220
+ "eval_rougeLsum": 0.47802150685708367,
2221
+ "eval_runtime": 6.9002,
2222
+ "eval_samples_per_second": 9.275,
2223
+ "eval_steps_per_second": 2.319,
2224
+ "step": 12580
2225
+ },
2226
+ {
2227
+ "epoch": 171.0,
2228
+ "eval_loss": 3.990157127380371,
2229
+ "eval_rouge1": 0.4970906257094063,
2230
+ "eval_rouge2": 0.40441572257587777,
2231
+ "eval_rougeL": 0.4763034913242958,
2232
+ "eval_rougeLsum": 0.48003172600357014,
2233
+ "eval_runtime": 7.1185,
2234
+ "eval_samples_per_second": 8.991,
2235
+ "eval_steps_per_second": 2.248,
2236
+ "step": 12654
2237
+ },
2238
+ {
2239
+ "epoch": 172.0,
2240
+ "eval_loss": 3.9884870052337646,
2241
+ "eval_rouge1": 0.4919713054717275,
2242
+ "eval_rouge2": 0.3978217334671761,
2243
+ "eval_rougeL": 0.4717472188768614,
2244
+ "eval_rougeLsum": 0.4752567984418149,
2245
+ "eval_runtime": 7.2011,
2246
+ "eval_samples_per_second": 8.888,
2247
+ "eval_steps_per_second": 2.222,
2248
+ "step": 12728
2249
+ },
2250
+ {
2251
+ "epoch": 173.0,
2252
+ "eval_loss": 3.995528221130371,
2253
+ "eval_rouge1": 0.4892295390230387,
2254
+ "eval_rouge2": 0.39245630150338084,
2255
+ "eval_rougeL": 0.46800971679320924,
2256
+ "eval_rougeLsum": 0.47172263652645663,
2257
+ "eval_runtime": 7.3505,
2258
+ "eval_samples_per_second": 8.707,
2259
+ "eval_steps_per_second": 2.177,
2260
+ "step": 12802
2261
+ },
2262
+ {
2263
+ "epoch": 174.0,
2264
+ "eval_loss": 3.9886558055877686,
2265
+ "eval_rouge1": 0.49254486459338476,
2266
+ "eval_rouge2": 0.3977283376888407,
2267
+ "eval_rougeL": 0.4719540790713239,
2268
+ "eval_rougeLsum": 0.4761202466533264,
2269
+ "eval_runtime": 7.5746,
2270
+ "eval_samples_per_second": 8.449,
2271
+ "eval_steps_per_second": 2.112,
2272
+ "step": 12876
2273
+ },
2274
+ {
2275
+ "epoch": 175.0,
2276
+ "eval_loss": 3.9935975074768066,
2277
+ "eval_rouge1": 0.49184767087274567,
2278
+ "eval_rouge2": 0.39517761703169657,
2279
+ "eval_rougeL": 0.47011431582517893,
2280
+ "eval_rougeLsum": 0.47482326137378367,
2281
+ "eval_runtime": 7.3613,
2282
+ "eval_samples_per_second": 8.694,
2283
+ "eval_steps_per_second": 2.174,
2284
+ "step": 12950
2285
+ },
2286
+ {
2287
+ "epoch": 175.67567567567568,
2288
+ "grad_norm": 0.21789249777793884,
2289
+ "learning_rate": 3.648648648648649e-05,
2290
+ "loss": 0.0031,
2291
+ "step": 13000
2292
+ },
2293
+ {
2294
+ "epoch": 176.0,
2295
+ "eval_loss": 3.991879463195801,
2296
+ "eval_rouge1": 0.49436064822903425,
2297
+ "eval_rouge2": 0.3983319755827057,
2298
+ "eval_rougeL": 0.47423185319254557,
2299
+ "eval_rougeLsum": 0.47939931586363027,
2300
+ "eval_runtime": 6.0616,
2301
+ "eval_samples_per_second": 10.558,
2302
+ "eval_steps_per_second": 2.64,
2303
+ "step": 13024
2304
+ },
2305
+ {
2306
+ "epoch": 177.0,
2307
+ "eval_loss": 3.9859113693237305,
2308
+ "eval_rouge1": 0.49493023202648,
2309
+ "eval_rouge2": 0.39876076391867105,
2310
+ "eval_rougeL": 0.47502603733194293,
2311
+ "eval_rougeLsum": 0.47979135340843765,
2312
+ "eval_runtime": 6.0337,
2313
+ "eval_samples_per_second": 10.607,
2314
+ "eval_steps_per_second": 2.652,
2315
+ "step": 13098
2316
+ },
2317
+ {
2318
+ "epoch": 178.0,
2319
+ "eval_loss": 3.9933767318725586,
2320
+ "eval_rouge1": 0.49395800948427726,
2321
+ "eval_rouge2": 0.39853734308250965,
2322
+ "eval_rougeL": 0.47430798111549466,
2323
+ "eval_rougeLsum": 0.4783243132851581,
2324
+ "eval_runtime": 6.3858,
2325
+ "eval_samples_per_second": 10.022,
2326
+ "eval_steps_per_second": 2.506,
2327
+ "step": 13172
2328
+ },
2329
+ {
2330
+ "epoch": 179.0,
2331
+ "eval_loss": 3.9931554794311523,
2332
+ "eval_rouge1": 0.49238304957658807,
2333
+ "eval_rouge2": 0.3963583838874407,
2334
+ "eval_rougeL": 0.47174238658414747,
2335
+ "eval_rougeLsum": 0.4753519409810264,
2336
+ "eval_runtime": 6.735,
2337
+ "eval_samples_per_second": 9.503,
2338
+ "eval_steps_per_second": 2.376,
2339
+ "step": 13246
2340
+ },
2341
+ {
2342
+ "epoch": 180.0,
2343
+ "eval_loss": 3.9880971908569336,
2344
+ "eval_rouge1": 0.49080560963978376,
2345
+ "eval_rouge2": 0.3972907788541582,
2346
+ "eval_rougeL": 0.47184356604760724,
2347
+ "eval_rougeLsum": 0.47466334337431604,
2348
+ "eval_runtime": 6.7997,
2349
+ "eval_samples_per_second": 9.412,
2350
+ "eval_steps_per_second": 2.353,
2351
+ "step": 13320
2352
+ },
2353
+ {
2354
+ "epoch": 181.0,
2355
+ "eval_loss": 3.9810729026794434,
2356
+ "eval_rouge1": 0.4901453996617402,
2357
+ "eval_rouge2": 0.39677107201508166,
2358
+ "eval_rougeL": 0.4703169982341144,
2359
+ "eval_rougeLsum": 0.4731671717016933,
2360
+ "eval_runtime": 6.7854,
2361
+ "eval_samples_per_second": 9.432,
2362
+ "eval_steps_per_second": 2.358,
2363
+ "step": 13394
2364
+ },
2365
+ {
2366
+ "epoch": 182.0,
2367
+ "eval_loss": 3.96390438079834,
2368
+ "eval_rouge1": 0.4904213027490153,
2369
+ "eval_rouge2": 0.39702370328662856,
2370
+ "eval_rougeL": 0.4721674656812758,
2371
+ "eval_rougeLsum": 0.47478324364675517,
2372
+ "eval_runtime": 6.8084,
2373
+ "eval_samples_per_second": 9.4,
2374
+ "eval_steps_per_second": 2.35,
2375
+ "step": 13468
2376
+ },
2377
+ {
2378
+ "epoch": 182.43243243243242,
2379
+ "grad_norm": 0.0035254976246505976,
2380
+ "learning_rate": 2.635135135135135e-05,
2381
+ "loss": 0.0028,
2382
+ "step": 13500
2383
+ },
2384
+ {
2385
+ "epoch": 183.0,
2386
+ "eval_loss": 3.9630651473999023,
2387
+ "eval_rouge1": 0.49176793094985966,
2388
+ "eval_rouge2": 0.3982124661120756,
2389
+ "eval_rougeL": 0.4739900352741334,
2390
+ "eval_rougeLsum": 0.4772889228039448,
2391
+ "eval_runtime": 6.7422,
2392
+ "eval_samples_per_second": 9.492,
2393
+ "eval_steps_per_second": 2.373,
2394
+ "step": 13542
2395
+ },
2396
+ {
2397
+ "epoch": 184.0,
2398
+ "eval_loss": 3.9613349437713623,
2399
+ "eval_rouge1": 0.49252377109539347,
2400
+ "eval_rouge2": 0.3991753353796805,
2401
+ "eval_rougeL": 0.4744207046904064,
2402
+ "eval_rougeLsum": 0.47843050814235677,
2403
+ "eval_runtime": 6.7346,
2404
+ "eval_samples_per_second": 9.503,
2405
+ "eval_steps_per_second": 2.376,
2406
+ "step": 13616
2407
+ },
2408
+ {
2409
+ "epoch": 185.0,
2410
+ "eval_loss": 3.966508388519287,
2411
+ "eval_rouge1": 0.49176793094985966,
2412
+ "eval_rouge2": 0.3982124661120756,
2413
+ "eval_rougeL": 0.4739900352741334,
2414
+ "eval_rougeLsum": 0.4772889228039448,
2415
+ "eval_runtime": 6.6765,
2416
+ "eval_samples_per_second": 9.586,
2417
+ "eval_steps_per_second": 2.396,
2418
+ "step": 13690
2419
+ },
2420
+ {
2421
+ "epoch": 186.0,
2422
+ "eval_loss": 3.969733715057373,
2423
+ "eval_rouge1": 0.49176793094985966,
2424
+ "eval_rouge2": 0.3982124661120756,
2425
+ "eval_rougeL": 0.4739900352741334,
2426
+ "eval_rougeLsum": 0.4772889228039448,
2427
+ "eval_runtime": 6.8824,
2428
+ "eval_samples_per_second": 9.299,
2429
+ "eval_steps_per_second": 2.325,
2430
+ "step": 13764
2431
+ },
2432
+ {
2433
+ "epoch": 187.0,
2434
+ "eval_loss": 3.9655680656433105,
2435
+ "eval_rouge1": 0.49176793094985966,
2436
+ "eval_rouge2": 0.3982124661120756,
2437
+ "eval_rougeL": 0.4739900352741334,
2438
+ "eval_rougeLsum": 0.4772889228039448,
2439
+ "eval_runtime": 6.9789,
2440
+ "eval_samples_per_second": 9.171,
2441
+ "eval_steps_per_second": 2.293,
2442
+ "step": 13838
2443
+ },
2444
+ {
2445
+ "epoch": 188.0,
2446
+ "eval_loss": 3.9675371646881104,
2447
+ "eval_rouge1": 0.4914535390216627,
2448
+ "eval_rouge2": 0.3996949212212493,
2449
+ "eval_rougeL": 0.4750270162479517,
2450
+ "eval_rougeLsum": 0.4774780484281064,
2451
+ "eval_runtime": 7.1278,
2452
+ "eval_samples_per_second": 8.979,
2453
+ "eval_steps_per_second": 2.245,
2454
+ "step": 13912
2455
+ },
2456
+ {
2457
+ "epoch": 189.0,
2458
+ "eval_loss": 3.9671735763549805,
2459
+ "eval_rouge1": 0.49101134475679165,
2460
+ "eval_rouge2": 0.3999416033500164,
2461
+ "eval_rougeL": 0.4751983641524803,
2462
+ "eval_rougeLsum": 0.47761184908243365,
2463
+ "eval_runtime": 7.124,
2464
+ "eval_samples_per_second": 8.984,
2465
+ "eval_steps_per_second": 2.246,
2466
+ "step": 13986
2467
+ },
2468
+ {
2469
+ "epoch": 189.1891891891892,
2470
+ "grad_norm": 0.15321534872055054,
2471
+ "learning_rate": 1.6216216216216215e-05,
2472
+ "loss": 0.0024,
2473
+ "step": 14000
2474
+ }
2475
+ ],
2476
+ "logging_steps": 500,
2477
+ "max_steps": 14800,
2478
+ "num_input_tokens_seen": 0,
2479
+ "num_train_epochs": 200,
2480
+ "save_steps": 500,
2481
+ "stateful_callbacks": {
2482
+ "TrainerControl": {
2483
+ "args": {
2484
+ "should_epoch_stop": false,
2485
+ "should_evaluate": false,
2486
+ "should_log": false,
2487
+ "should_save": true,
2488
+ "should_training_stop": false
2489
+ },
2490
+ "attributes": {}
2491
+ }
2492
+ },
2493
+ "total_flos": 152816225550336.0,
2494
+ "train_batch_size": 2,
2495
+ "trial_name": null,
2496
+ "trial_params": null
2497
+ }
results/checkpoint-14000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a42ec5404b2e8ac8f2f4376a8da0b5e09eb82c54628966bc74fc83bbb71250d
3
+ size 5304
results/checkpoint-14500/added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }
results/checkpoint-14500/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.44.2",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
results/checkpoint-14500/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": "4.44.2"
6
+ }
results/checkpoint-14500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99cc045b757ce95deda7291f01c0310dc840620e87d2f29c7f6752c219f956c7
3
+ size 242041896
results/checkpoint-14500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dac400702158251b7947eb10b83992919a96a1388b03c1f03d53409bfc23514
3
+ size 484163514
results/checkpoint-14500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77a61babb53159a3ac639f4e486ccad8d2f882403feb436acbf59bff30249c01
3
+ size 14244
results/checkpoint-14500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b944ddd654686f6dbca4a9abca090d2544ed3921e9e8a971cc4bf974f062ad4a
3
+ size 1064
results/checkpoint-14500/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
+ }
results/checkpoint-14500/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
results/checkpoint-14500/tokenizer_config.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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": true,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "legacy": true,
935
+ "model_max_length": 512,
936
+ "pad_token": "<pad>",
937
+ "sp_model_kwargs": {},
938
+ "tokenizer_class": "T5Tokenizer",
939
+ "unk_token": "<unk>"
940
+ }
results/checkpoint-14500/trainer_state.json ADDED
@@ -0,0 +1,2576 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 195.94594594594594,
5
+ "eval_steps": 500,
6
+ "global_step": 14500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 1.8613592386245728,
14
+ "eval_rouge1": 0.4786345373045099,
15
+ "eval_rouge2": 0.37180882574119667,
16
+ "eval_rougeL": 0.45993348459469097,
17
+ "eval_rougeLsum": 0.46473759136147386,
18
+ "eval_runtime": 6.5152,
19
+ "eval_samples_per_second": 9.823,
20
+ "eval_steps_per_second": 2.456,
21
+ "step": 74
22
+ },
23
+ {
24
+ "epoch": 2.0,
25
+ "eval_loss": 1.9003169536590576,
26
+ "eval_rouge1": 0.48640604321499575,
27
+ "eval_rouge2": 0.37989220372871,
28
+ "eval_rougeL": 0.4679360920147918,
29
+ "eval_rougeLsum": 0.4730461956934725,
30
+ "eval_runtime": 6.8749,
31
+ "eval_samples_per_second": 9.309,
32
+ "eval_steps_per_second": 2.327,
33
+ "step": 148
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 1.8439046144485474,
38
+ "eval_rouge1": 0.4878659052451008,
39
+ "eval_rouge2": 0.37862931599963434,
40
+ "eval_rougeL": 0.4686655551573986,
41
+ "eval_rougeLsum": 0.4745397729079822,
42
+ "eval_runtime": 6.9056,
43
+ "eval_samples_per_second": 9.268,
44
+ "eval_steps_per_second": 2.317,
45
+ "step": 222
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_loss": 1.859361171722412,
50
+ "eval_rouge1": 0.4899970322537004,
51
+ "eval_rouge2": 0.39712825251075856,
52
+ "eval_rougeL": 0.47922614340714226,
53
+ "eval_rougeLsum": 0.4845442547862512,
54
+ "eval_runtime": 6.8081,
55
+ "eval_samples_per_second": 9.401,
56
+ "eval_steps_per_second": 2.35,
57
+ "step": 296
58
+ },
59
+ {
60
+ "epoch": 5.0,
61
+ "eval_loss": 1.9181809425354004,
62
+ "eval_rouge1": 0.5019986152414111,
63
+ "eval_rouge2": 0.39075144771524173,
64
+ "eval_rougeL": 0.48288657869037616,
65
+ "eval_rougeLsum": 0.4897115650226128,
66
+ "eval_runtime": 6.7301,
67
+ "eval_samples_per_second": 9.51,
68
+ "eval_steps_per_second": 2.377,
69
+ "step": 370
70
+ },
71
+ {
72
+ "epoch": 6.0,
73
+ "eval_loss": 1.9439482688903809,
74
+ "eval_rouge1": 0.5017635218691469,
75
+ "eval_rouge2": 0.40394299359796604,
76
+ "eval_rougeL": 0.4856876042232454,
77
+ "eval_rougeLsum": 0.4902182125463155,
78
+ "eval_runtime": 8.3277,
79
+ "eval_samples_per_second": 7.685,
80
+ "eval_steps_per_second": 1.921,
81
+ "step": 444
82
+ },
83
+ {
84
+ "epoch": 6.756756756756757,
85
+ "grad_norm": 3.515812635421753,
86
+ "learning_rate": 0.00028986486486486487,
87
+ "loss": 1.0738,
88
+ "step": 500
89
+ },
90
+ {
91
+ "epoch": 7.0,
92
+ "eval_loss": 1.9816868305206299,
93
+ "eval_rouge1": 0.48981665251409034,
94
+ "eval_rouge2": 0.38940540670364077,
95
+ "eval_rougeL": 0.4756157468523289,
96
+ "eval_rougeLsum": 0.47786350441316916,
97
+ "eval_runtime": 6.7892,
98
+ "eval_samples_per_second": 9.427,
99
+ "eval_steps_per_second": 2.357,
100
+ "step": 518
101
+ },
102
+ {
103
+ "epoch": 8.0,
104
+ "eval_loss": 1.9661787748336792,
105
+ "eval_rouge1": 0.503527283682017,
106
+ "eval_rouge2": 0.3907616822377492,
107
+ "eval_rougeL": 0.48117377461776023,
108
+ "eval_rougeLsum": 0.48596520984967795,
109
+ "eval_runtime": 7.1304,
110
+ "eval_samples_per_second": 8.976,
111
+ "eval_steps_per_second": 2.244,
112
+ "step": 592
113
+ },
114
+ {
115
+ "epoch": 9.0,
116
+ "eval_loss": 2.0364491939544678,
117
+ "eval_rouge1": 0.49655106473304944,
118
+ "eval_rouge2": 0.4026512074564483,
119
+ "eval_rougeL": 0.48182640465396503,
120
+ "eval_rougeLsum": 0.48682277089096093,
121
+ "eval_runtime": 7.2868,
122
+ "eval_samples_per_second": 8.783,
123
+ "eval_steps_per_second": 2.196,
124
+ "step": 666
125
+ },
126
+ {
127
+ "epoch": 10.0,
128
+ "eval_loss": 2.0958075523376465,
129
+ "eval_rouge1": 0.5027632027654159,
130
+ "eval_rouge2": 0.405224140796529,
131
+ "eval_rougeL": 0.487341765630358,
132
+ "eval_rougeLsum": 0.49286491460972326,
133
+ "eval_runtime": 7.5086,
134
+ "eval_samples_per_second": 8.524,
135
+ "eval_steps_per_second": 2.131,
136
+ "step": 740
137
+ },
138
+ {
139
+ "epoch": 11.0,
140
+ "eval_loss": 2.1330082416534424,
141
+ "eval_rouge1": 0.4959996625037898,
142
+ "eval_rouge2": 0.39173324347256133,
143
+ "eval_rougeL": 0.47707298584837665,
144
+ "eval_rougeLsum": 0.4801611854873997,
145
+ "eval_runtime": 7.2859,
146
+ "eval_samples_per_second": 8.784,
147
+ "eval_steps_per_second": 2.196,
148
+ "step": 814
149
+ },
150
+ {
151
+ "epoch": 12.0,
152
+ "eval_loss": 2.1985864639282227,
153
+ "eval_rouge1": 0.49880201305687655,
154
+ "eval_rouge2": 0.39953137212155626,
155
+ "eval_rougeL": 0.47742278166430285,
156
+ "eval_rougeLsum": 0.4805222964063607,
157
+ "eval_runtime": 7.603,
158
+ "eval_samples_per_second": 8.418,
159
+ "eval_steps_per_second": 2.104,
160
+ "step": 888
161
+ },
162
+ {
163
+ "epoch": 13.0,
164
+ "eval_loss": 2.199228525161743,
165
+ "eval_rouge1": 0.49651192761571294,
166
+ "eval_rouge2": 0.3996406381133431,
167
+ "eval_rougeL": 0.48019273990957534,
168
+ "eval_rougeLsum": 0.4830744303463099,
169
+ "eval_runtime": 7.41,
170
+ "eval_samples_per_second": 8.637,
171
+ "eval_steps_per_second": 2.159,
172
+ "step": 962
173
+ },
174
+ {
175
+ "epoch": 13.513513513513514,
176
+ "grad_norm": 1.04505455493927,
177
+ "learning_rate": 0.0002797297297297297,
178
+ "loss": 0.5758,
179
+ "step": 1000
180
+ },
181
+ {
182
+ "epoch": 14.0,
183
+ "eval_loss": 2.2532949447631836,
184
+ "eval_rouge1": 0.4974175527416956,
185
+ "eval_rouge2": 0.3938967736606859,
186
+ "eval_rougeL": 0.47594155912589253,
187
+ "eval_rougeLsum": 0.47750953126404355,
188
+ "eval_runtime": 6.7122,
189
+ "eval_samples_per_second": 9.535,
190
+ "eval_steps_per_second": 2.384,
191
+ "step": 1036
192
+ },
193
+ {
194
+ "epoch": 15.0,
195
+ "eval_loss": 2.288240671157837,
196
+ "eval_rouge1": 0.5002431437874408,
197
+ "eval_rouge2": 0.4044372576278309,
198
+ "eval_rougeL": 0.4840219965379457,
199
+ "eval_rougeLsum": 0.4857965014846245,
200
+ "eval_runtime": 7.012,
201
+ "eval_samples_per_second": 9.127,
202
+ "eval_steps_per_second": 2.282,
203
+ "step": 1110
204
+ },
205
+ {
206
+ "epoch": 16.0,
207
+ "eval_loss": 2.3295252323150635,
208
+ "eval_rouge1": 0.49837277766128096,
209
+ "eval_rouge2": 0.400153779173206,
210
+ "eval_rougeL": 0.4787384592897309,
211
+ "eval_rougeLsum": 0.4811181898511001,
212
+ "eval_runtime": 7.1846,
213
+ "eval_samples_per_second": 8.908,
214
+ "eval_steps_per_second": 2.227,
215
+ "step": 1184
216
+ },
217
+ {
218
+ "epoch": 17.0,
219
+ "eval_loss": 2.4045495986938477,
220
+ "eval_rouge1": 0.4978315032043237,
221
+ "eval_rouge2": 0.40024152683134784,
222
+ "eval_rougeL": 0.4779140878590623,
223
+ "eval_rougeLsum": 0.482043049548367,
224
+ "eval_runtime": 7.0985,
225
+ "eval_samples_per_second": 9.016,
226
+ "eval_steps_per_second": 2.254,
227
+ "step": 1258
228
+ },
229
+ {
230
+ "epoch": 18.0,
231
+ "eval_loss": 2.407705783843994,
232
+ "eval_rouge1": 0.4926722210399497,
233
+ "eval_rouge2": 0.39489818358868434,
234
+ "eval_rougeL": 0.4741921466377443,
235
+ "eval_rougeLsum": 0.4779971741886041,
236
+ "eval_runtime": 7.1727,
237
+ "eval_samples_per_second": 8.923,
238
+ "eval_steps_per_second": 2.231,
239
+ "step": 1332
240
+ },
241
+ {
242
+ "epoch": 19.0,
243
+ "eval_loss": 2.478081703186035,
244
+ "eval_rouge1": 0.4968199981652396,
245
+ "eval_rouge2": 0.3921631193099281,
246
+ "eval_rougeL": 0.47676117839634435,
247
+ "eval_rougeLsum": 0.47994768391715004,
248
+ "eval_runtime": 7.454,
249
+ "eval_samples_per_second": 8.586,
250
+ "eval_steps_per_second": 2.146,
251
+ "step": 1406
252
+ },
253
+ {
254
+ "epoch": 20.0,
255
+ "eval_loss": 2.4524130821228027,
256
+ "eval_rouge1": 0.5080094877873333,
257
+ "eval_rouge2": 0.4032125314338061,
258
+ "eval_rougeL": 0.48666005983666427,
259
+ "eval_rougeLsum": 0.4894073793399426,
260
+ "eval_runtime": 7.2808,
261
+ "eval_samples_per_second": 8.79,
262
+ "eval_steps_per_second": 2.198,
263
+ "step": 1480
264
+ },
265
+ {
266
+ "epoch": 20.27027027027027,
267
+ "grad_norm": 1.7321689128875732,
268
+ "learning_rate": 0.0002695945945945946,
269
+ "loss": 0.3167,
270
+ "step": 1500
271
+ },
272
+ {
273
+ "epoch": 21.0,
274
+ "eval_loss": 2.534647226333618,
275
+ "eval_rouge1": 0.5022719998675416,
276
+ "eval_rouge2": 0.3965945705867416,
277
+ "eval_rougeL": 0.47982490810386763,
278
+ "eval_rougeLsum": 0.48480167185914425,
279
+ "eval_runtime": 6.8184,
280
+ "eval_samples_per_second": 9.386,
281
+ "eval_steps_per_second": 2.347,
282
+ "step": 1554
283
+ },
284
+ {
285
+ "epoch": 22.0,
286
+ "eval_loss": 2.5828959941864014,
287
+ "eval_rouge1": 0.4976653665113625,
288
+ "eval_rouge2": 0.40224136020443735,
289
+ "eval_rougeL": 0.4811444805687263,
290
+ "eval_rougeLsum": 0.48383489837790894,
291
+ "eval_runtime": 6.7252,
292
+ "eval_samples_per_second": 9.516,
293
+ "eval_steps_per_second": 2.379,
294
+ "step": 1628
295
+ },
296
+ {
297
+ "epoch": 23.0,
298
+ "eval_loss": 2.5470526218414307,
299
+ "eval_rouge1": 0.4874729550501261,
300
+ "eval_rouge2": 0.3987554141783959,
301
+ "eval_rougeL": 0.47201372208979153,
302
+ "eval_rougeLsum": 0.47412842500299435,
303
+ "eval_runtime": 7.0639,
304
+ "eval_samples_per_second": 9.06,
305
+ "eval_steps_per_second": 2.265,
306
+ "step": 1702
307
+ },
308
+ {
309
+ "epoch": 24.0,
310
+ "eval_loss": 2.630704402923584,
311
+ "eval_rouge1": 0.4896711232817296,
312
+ "eval_rouge2": 0.3955887747393345,
313
+ "eval_rougeL": 0.47391307139859873,
314
+ "eval_rougeLsum": 0.4770794334968449,
315
+ "eval_runtime": 7.3201,
316
+ "eval_samples_per_second": 8.743,
317
+ "eval_steps_per_second": 2.186,
318
+ "step": 1776
319
+ },
320
+ {
321
+ "epoch": 25.0,
322
+ "eval_loss": 2.643130302429199,
323
+ "eval_rouge1": 0.4990756076647881,
324
+ "eval_rouge2": 0.40258726349946017,
325
+ "eval_rougeL": 0.4819547441943952,
326
+ "eval_rougeLsum": 0.4882772750587064,
327
+ "eval_runtime": 7.3246,
328
+ "eval_samples_per_second": 8.738,
329
+ "eval_steps_per_second": 2.184,
330
+ "step": 1850
331
+ },
332
+ {
333
+ "epoch": 26.0,
334
+ "eval_loss": 2.6722755432128906,
335
+ "eval_rouge1": 0.49478698590012704,
336
+ "eval_rouge2": 0.4068068282048684,
337
+ "eval_rougeL": 0.47973303108617305,
338
+ "eval_rougeLsum": 0.4829897810492303,
339
+ "eval_runtime": 7.3062,
340
+ "eval_samples_per_second": 8.76,
341
+ "eval_steps_per_second": 2.19,
342
+ "step": 1924
343
+ },
344
+ {
345
+ "epoch": 27.0,
346
+ "eval_loss": 2.730930805206299,
347
+ "eval_rouge1": 0.48566293927001947,
348
+ "eval_rouge2": 0.3851552374981059,
349
+ "eval_rougeL": 0.4705474000074168,
350
+ "eval_rougeLsum": 0.4722918346693246,
351
+ "eval_runtime": 7.4221,
352
+ "eval_samples_per_second": 8.623,
353
+ "eval_steps_per_second": 2.156,
354
+ "step": 1998
355
+ },
356
+ {
357
+ "epoch": 27.027027027027028,
358
+ "grad_norm": 1.6483324766159058,
359
+ "learning_rate": 0.00025945945945945944,
360
+ "loss": 0.1748,
361
+ "step": 2000
362
+ },
363
+ {
364
+ "epoch": 28.0,
365
+ "eval_loss": 2.7344658374786377,
366
+ "eval_rouge1": 0.49051030653062777,
367
+ "eval_rouge2": 0.3941201110385898,
368
+ "eval_rougeL": 0.4719692856196016,
369
+ "eval_rougeLsum": 0.47611754141135576,
370
+ "eval_runtime": 6.5296,
371
+ "eval_samples_per_second": 9.802,
372
+ "eval_steps_per_second": 2.45,
373
+ "step": 2072
374
+ },
375
+ {
376
+ "epoch": 29.0,
377
+ "eval_loss": 2.7428927421569824,
378
+ "eval_rouge1": 0.4925127943579154,
379
+ "eval_rouge2": 0.3907254802029442,
380
+ "eval_rougeL": 0.4737655715932324,
381
+ "eval_rougeLsum": 0.4773362259172194,
382
+ "eval_runtime": 6.8059,
383
+ "eval_samples_per_second": 9.404,
384
+ "eval_steps_per_second": 2.351,
385
+ "step": 2146
386
+ },
387
+ {
388
+ "epoch": 30.0,
389
+ "eval_loss": 2.796144962310791,
390
+ "eval_rouge1": 0.49155918498382867,
391
+ "eval_rouge2": 0.3999581981140521,
392
+ "eval_rougeL": 0.47417603819102405,
393
+ "eval_rougeLsum": 0.47954892078188294,
394
+ "eval_runtime": 6.775,
395
+ "eval_samples_per_second": 9.447,
396
+ "eval_steps_per_second": 2.362,
397
+ "step": 2220
398
+ },
399
+ {
400
+ "epoch": 31.0,
401
+ "eval_loss": 2.8113179206848145,
402
+ "eval_rouge1": 0.49033614321676355,
403
+ "eval_rouge2": 0.39673932600475936,
404
+ "eval_rougeL": 0.4736746112835428,
405
+ "eval_rougeLsum": 0.4766478013171821,
406
+ "eval_runtime": 6.8964,
407
+ "eval_samples_per_second": 9.28,
408
+ "eval_steps_per_second": 2.32,
409
+ "step": 2294
410
+ },
411
+ {
412
+ "epoch": 32.0,
413
+ "eval_loss": 2.8311588764190674,
414
+ "eval_rouge1": 0.4959842681554596,
415
+ "eval_rouge2": 0.3987159642616428,
416
+ "eval_rougeL": 0.4773867458483667,
417
+ "eval_rougeLsum": 0.48240925171506055,
418
+ "eval_runtime": 6.7543,
419
+ "eval_samples_per_second": 9.475,
420
+ "eval_steps_per_second": 2.369,
421
+ "step": 2368
422
+ },
423
+ {
424
+ "epoch": 33.0,
425
+ "eval_loss": 2.8345541954040527,
426
+ "eval_rouge1": 0.4982105069215113,
427
+ "eval_rouge2": 0.4019606298133721,
428
+ "eval_rougeL": 0.4810665966926186,
429
+ "eval_rougeLsum": 0.48452636993191933,
430
+ "eval_runtime": 6.8235,
431
+ "eval_samples_per_second": 9.379,
432
+ "eval_steps_per_second": 2.345,
433
+ "step": 2442
434
+ },
435
+ {
436
+ "epoch": 33.78378378378378,
437
+ "grad_norm": 1.6361833810806274,
438
+ "learning_rate": 0.0002493243243243243,
439
+ "loss": 0.1085,
440
+ "step": 2500
441
+ },
442
+ {
443
+ "epoch": 34.0,
444
+ "eval_loss": 2.840573787689209,
445
+ "eval_rouge1": 0.4906154416517885,
446
+ "eval_rouge2": 0.3925361294228983,
447
+ "eval_rougeL": 0.47012187809673456,
448
+ "eval_rougeLsum": 0.47358672446502714,
449
+ "eval_runtime": 6.7897,
450
+ "eval_samples_per_second": 9.426,
451
+ "eval_steps_per_second": 2.357,
452
+ "step": 2516
453
+ },
454
+ {
455
+ "epoch": 35.0,
456
+ "eval_loss": 2.930208206176758,
457
+ "eval_rouge1": 0.493665848008467,
458
+ "eval_rouge2": 0.4013160803818016,
459
+ "eval_rougeL": 0.4777617853768054,
460
+ "eval_rougeLsum": 0.48104196224253826,
461
+ "eval_runtime": 6.9547,
462
+ "eval_samples_per_second": 9.202,
463
+ "eval_steps_per_second": 2.301,
464
+ "step": 2590
465
+ },
466
+ {
467
+ "epoch": 36.0,
468
+ "eval_loss": 2.956294059753418,
469
+ "eval_rouge1": 0.49463858809967287,
470
+ "eval_rouge2": 0.40143704462358853,
471
+ "eval_rougeL": 0.4794876543551684,
472
+ "eval_rougeLsum": 0.4829190918461401,
473
+ "eval_runtime": 6.8652,
474
+ "eval_samples_per_second": 9.322,
475
+ "eval_steps_per_second": 2.331,
476
+ "step": 2664
477
+ },
478
+ {
479
+ "epoch": 37.0,
480
+ "eval_loss": 2.969008207321167,
481
+ "eval_rouge1": 0.4954794072003128,
482
+ "eval_rouge2": 0.397320916674356,
483
+ "eval_rougeL": 0.4772272253428127,
484
+ "eval_rougeLsum": 0.48208663351137193,
485
+ "eval_runtime": 6.7157,
486
+ "eval_samples_per_second": 9.53,
487
+ "eval_steps_per_second": 2.382,
488
+ "step": 2738
489
+ },
490
+ {
491
+ "epoch": 38.0,
492
+ "eval_loss": 3.0091614723205566,
493
+ "eval_rouge1": 0.49714553273507894,
494
+ "eval_rouge2": 0.4043158418135101,
495
+ "eval_rougeL": 0.4795949127773593,
496
+ "eval_rougeLsum": 0.4831791208710218,
497
+ "eval_runtime": 7.1733,
498
+ "eval_samples_per_second": 8.922,
499
+ "eval_steps_per_second": 2.23,
500
+ "step": 2812
501
+ },
502
+ {
503
+ "epoch": 39.0,
504
+ "eval_loss": 3.0400657653808594,
505
+ "eval_rouge1": 0.4930990290551204,
506
+ "eval_rouge2": 0.4008358832580894,
507
+ "eval_rougeL": 0.4738879674085547,
508
+ "eval_rougeLsum": 0.4786937389741459,
509
+ "eval_runtime": 7.4692,
510
+ "eval_samples_per_second": 8.569,
511
+ "eval_steps_per_second": 2.142,
512
+ "step": 2886
513
+ },
514
+ {
515
+ "epoch": 40.0,
516
+ "eval_loss": 3.1281185150146484,
517
+ "eval_rouge1": 0.5005688791622078,
518
+ "eval_rouge2": 0.4084174900042821,
519
+ "eval_rougeL": 0.48499705961551304,
520
+ "eval_rougeLsum": 0.4874735515428569,
521
+ "eval_runtime": 7.5007,
522
+ "eval_samples_per_second": 8.533,
523
+ "eval_steps_per_second": 2.133,
524
+ "step": 2960
525
+ },
526
+ {
527
+ "epoch": 40.54054054054054,
528
+ "grad_norm": 0.9557915329933167,
529
+ "learning_rate": 0.00023918918918918917,
530
+ "loss": 0.0705,
531
+ "step": 3000
532
+ },
533
+ {
534
+ "epoch": 41.0,
535
+ "eval_loss": 3.0529465675354004,
536
+ "eval_rouge1": 0.4897934761187476,
537
+ "eval_rouge2": 0.39635503197156763,
538
+ "eval_rougeL": 0.47185062979906517,
539
+ "eval_rougeLsum": 0.4759267454340096,
540
+ "eval_runtime": 6.6953,
541
+ "eval_samples_per_second": 9.559,
542
+ "eval_steps_per_second": 2.39,
543
+ "step": 3034
544
+ },
545
+ {
546
+ "epoch": 42.0,
547
+ "eval_loss": 3.11130690574646,
548
+ "eval_rouge1": 0.4946583089357438,
549
+ "eval_rouge2": 0.3978038705482625,
550
+ "eval_rougeL": 0.47574088550447186,
551
+ "eval_rougeLsum": 0.4806888255731349,
552
+ "eval_runtime": 6.8505,
553
+ "eval_samples_per_second": 9.342,
554
+ "eval_steps_per_second": 2.336,
555
+ "step": 3108
556
+ },
557
+ {
558
+ "epoch": 43.0,
559
+ "eval_loss": 3.0772416591644287,
560
+ "eval_rouge1": 0.5030802762047029,
561
+ "eval_rouge2": 0.410314672620852,
562
+ "eval_rougeL": 0.4833954355578848,
563
+ "eval_rougeLsum": 0.4875555968866432,
564
+ "eval_runtime": 6.8413,
565
+ "eval_samples_per_second": 9.355,
566
+ "eval_steps_per_second": 2.339,
567
+ "step": 3182
568
+ },
569
+ {
570
+ "epoch": 44.0,
571
+ "eval_loss": 3.0869698524475098,
572
+ "eval_rouge1": 0.48529765931122515,
573
+ "eval_rouge2": 0.393553693154484,
574
+ "eval_rougeL": 0.4677500598095278,
575
+ "eval_rougeLsum": 0.47176121532464105,
576
+ "eval_runtime": 7.0952,
577
+ "eval_samples_per_second": 9.02,
578
+ "eval_steps_per_second": 2.255,
579
+ "step": 3256
580
+ },
581
+ {
582
+ "epoch": 45.0,
583
+ "eval_loss": 3.1311964988708496,
584
+ "eval_rouge1": 0.49150604031170264,
585
+ "eval_rouge2": 0.39344648211082733,
586
+ "eval_rougeL": 0.47140730666348807,
587
+ "eval_rougeLsum": 0.4749720765409351,
588
+ "eval_runtime": 7.0711,
589
+ "eval_samples_per_second": 9.051,
590
+ "eval_steps_per_second": 2.263,
591
+ "step": 3330
592
+ },
593
+ {
594
+ "epoch": 46.0,
595
+ "eval_loss": 3.1351137161254883,
596
+ "eval_rouge1": 0.48756191602264853,
597
+ "eval_rouge2": 0.3913618206121121,
598
+ "eval_rougeL": 0.46594848749570755,
599
+ "eval_rougeLsum": 0.4708637065525476,
600
+ "eval_runtime": 7.4988,
601
+ "eval_samples_per_second": 8.535,
602
+ "eval_steps_per_second": 2.134,
603
+ "step": 3404
604
+ },
605
+ {
606
+ "epoch": 47.0,
607
+ "eval_loss": 3.1709024906158447,
608
+ "eval_rouge1": 0.4922573774776159,
609
+ "eval_rouge2": 0.3951502957382841,
610
+ "eval_rougeL": 0.47162786210886765,
611
+ "eval_rougeLsum": 0.47819599079754893,
612
+ "eval_runtime": 7.6141,
613
+ "eval_samples_per_second": 8.406,
614
+ "eval_steps_per_second": 2.101,
615
+ "step": 3478
616
+ },
617
+ {
618
+ "epoch": 47.2972972972973,
619
+ "grad_norm": 0.05126029625535011,
620
+ "learning_rate": 0.00022905405405405403,
621
+ "loss": 0.048,
622
+ "step": 3500
623
+ },
624
+ {
625
+ "epoch": 48.0,
626
+ "eval_loss": 3.2214059829711914,
627
+ "eval_rouge1": 0.4890967944398124,
628
+ "eval_rouge2": 0.3899734025187871,
629
+ "eval_rougeL": 0.47142210483202807,
630
+ "eval_rougeLsum": 0.4747196341231704,
631
+ "eval_runtime": 6.8558,
632
+ "eval_samples_per_second": 9.335,
633
+ "eval_steps_per_second": 2.334,
634
+ "step": 3552
635
+ },
636
+ {
637
+ "epoch": 49.0,
638
+ "eval_loss": 3.212207317352295,
639
+ "eval_rouge1": 0.49216557406572503,
640
+ "eval_rouge2": 0.39842262033619624,
641
+ "eval_rougeL": 0.47319779876406254,
642
+ "eval_rougeLsum": 0.47788473282281796,
643
+ "eval_runtime": 7.1919,
644
+ "eval_samples_per_second": 8.899,
645
+ "eval_steps_per_second": 2.225,
646
+ "step": 3626
647
+ },
648
+ {
649
+ "epoch": 50.0,
650
+ "eval_loss": 3.2497425079345703,
651
+ "eval_rouge1": 0.48706134754757757,
652
+ "eval_rouge2": 0.38575444861667946,
653
+ "eval_rougeL": 0.46735785969190247,
654
+ "eval_rougeLsum": 0.4728504130518682,
655
+ "eval_runtime": 7.0702,
656
+ "eval_samples_per_second": 9.052,
657
+ "eval_steps_per_second": 2.263,
658
+ "step": 3700
659
+ },
660
+ {
661
+ "epoch": 51.0,
662
+ "eval_loss": 3.2969608306884766,
663
+ "eval_rouge1": 0.4932365455711594,
664
+ "eval_rouge2": 0.4000747029784189,
665
+ "eval_rougeL": 0.4738167823332297,
666
+ "eval_rougeLsum": 0.4772360828349106,
667
+ "eval_runtime": 6.965,
668
+ "eval_samples_per_second": 9.189,
669
+ "eval_steps_per_second": 2.297,
670
+ "step": 3774
671
+ },
672
+ {
673
+ "epoch": 52.0,
674
+ "eval_loss": 3.2699038982391357,
675
+ "eval_rouge1": 0.48578637168024275,
676
+ "eval_rouge2": 0.3899767424324475,
677
+ "eval_rougeL": 0.4655432811779165,
678
+ "eval_rougeLsum": 0.46990217980095994,
679
+ "eval_runtime": 7.1115,
680
+ "eval_samples_per_second": 8.999,
681
+ "eval_steps_per_second": 2.25,
682
+ "step": 3848
683
+ },
684
+ {
685
+ "epoch": 53.0,
686
+ "eval_loss": 3.27628755569458,
687
+ "eval_rouge1": 0.4933670872384299,
688
+ "eval_rouge2": 0.39634620451150876,
689
+ "eval_rougeL": 0.4732893971674522,
690
+ "eval_rougeLsum": 0.47671103112248703,
691
+ "eval_runtime": 7.4331,
692
+ "eval_samples_per_second": 8.61,
693
+ "eval_steps_per_second": 2.153,
694
+ "step": 3922
695
+ },
696
+ {
697
+ "epoch": 54.0,
698
+ "eval_loss": 3.3377037048339844,
699
+ "eval_rouge1": 0.49163229783499957,
700
+ "eval_rouge2": 0.39568035885308184,
701
+ "eval_rougeL": 0.4728118235854102,
702
+ "eval_rougeLsum": 0.47626488443738957,
703
+ "eval_runtime": 7.5795,
704
+ "eval_samples_per_second": 8.444,
705
+ "eval_steps_per_second": 2.111,
706
+ "step": 3996
707
+ },
708
+ {
709
+ "epoch": 54.054054054054056,
710
+ "grad_norm": 1.0509763956069946,
711
+ "learning_rate": 0.0002189189189189189,
712
+ "loss": 0.038,
713
+ "step": 4000
714
+ },
715
+ {
716
+ "epoch": 55.0,
717
+ "eval_loss": 3.3113150596618652,
718
+ "eval_rouge1": 0.48945272795521544,
719
+ "eval_rouge2": 0.3963221515559594,
720
+ "eval_rougeL": 0.4721919860446503,
721
+ "eval_rougeLsum": 0.47357799717311305,
722
+ "eval_runtime": 6.678,
723
+ "eval_samples_per_second": 9.584,
724
+ "eval_steps_per_second": 2.396,
725
+ "step": 4070
726
+ },
727
+ {
728
+ "epoch": 56.0,
729
+ "eval_loss": 3.3390731811523438,
730
+ "eval_rouge1": 0.48992251021991795,
731
+ "eval_rouge2": 0.39489410083425924,
732
+ "eval_rougeL": 0.47052371258574177,
733
+ "eval_rougeLsum": 0.4743893718036267,
734
+ "eval_runtime": 6.7362,
735
+ "eval_samples_per_second": 9.501,
736
+ "eval_steps_per_second": 2.375,
737
+ "step": 4144
738
+ },
739
+ {
740
+ "epoch": 57.0,
741
+ "eval_loss": 3.3541388511657715,
742
+ "eval_rouge1": 0.485591464354193,
743
+ "eval_rouge2": 0.3922683949911642,
744
+ "eval_rougeL": 0.467559759968952,
745
+ "eval_rougeLsum": 0.47055134836018797,
746
+ "eval_runtime": 6.7783,
747
+ "eval_samples_per_second": 9.442,
748
+ "eval_steps_per_second": 2.36,
749
+ "step": 4218
750
+ },
751
+ {
752
+ "epoch": 58.0,
753
+ "eval_loss": 3.3830862045288086,
754
+ "eval_rouge1": 0.48567933561799026,
755
+ "eval_rouge2": 0.3913114600982295,
756
+ "eval_rougeL": 0.4717197222629562,
757
+ "eval_rougeLsum": 0.4759054008130139,
758
+ "eval_runtime": 6.7362,
759
+ "eval_samples_per_second": 9.501,
760
+ "eval_steps_per_second": 2.375,
761
+ "step": 4292
762
+ },
763
+ {
764
+ "epoch": 59.0,
765
+ "eval_loss": 3.362180233001709,
766
+ "eval_rouge1": 0.4871759825945764,
767
+ "eval_rouge2": 0.39201146093813594,
768
+ "eval_rougeL": 0.46798817172512763,
769
+ "eval_rougeLsum": 0.4722525087292696,
770
+ "eval_runtime": 6.8255,
771
+ "eval_samples_per_second": 9.377,
772
+ "eval_steps_per_second": 2.344,
773
+ "step": 4366
774
+ },
775
+ {
776
+ "epoch": 60.0,
777
+ "eval_loss": 3.365551233291626,
778
+ "eval_rouge1": 0.491209709363416,
779
+ "eval_rouge2": 0.3941051958571793,
780
+ "eval_rougeL": 0.4710680943298621,
781
+ "eval_rougeLsum": 0.47543333130232784,
782
+ "eval_runtime": 7.1366,
783
+ "eval_samples_per_second": 8.968,
784
+ "eval_steps_per_second": 2.242,
785
+ "step": 4440
786
+ },
787
+ {
788
+ "epoch": 60.810810810810814,
789
+ "grad_norm": 0.5249083042144775,
790
+ "learning_rate": 0.00020878378378378376,
791
+ "loss": 0.0262,
792
+ "step": 4500
793
+ },
794
+ {
795
+ "epoch": 61.0,
796
+ "eval_loss": 3.3976566791534424,
797
+ "eval_rouge1": 0.4927070473298987,
798
+ "eval_rouge2": 0.39541083512710884,
799
+ "eval_rougeL": 0.4719375953633722,
800
+ "eval_rougeLsum": 0.4739645816900254,
801
+ "eval_runtime": 5.9466,
802
+ "eval_samples_per_second": 10.762,
803
+ "eval_steps_per_second": 2.691,
804
+ "step": 4514
805
+ },
806
+ {
807
+ "epoch": 62.0,
808
+ "eval_loss": 3.415280342102051,
809
+ "eval_rouge1": 0.4931049778367517,
810
+ "eval_rouge2": 0.3954821826304163,
811
+ "eval_rougeL": 0.4730007788710514,
812
+ "eval_rougeLsum": 0.4765290778808515,
813
+ "eval_runtime": 5.9912,
814
+ "eval_samples_per_second": 10.682,
815
+ "eval_steps_per_second": 2.671,
816
+ "step": 4588
817
+ },
818
+ {
819
+ "epoch": 63.0,
820
+ "eval_loss": 3.4405603408813477,
821
+ "eval_rouge1": 0.48902472517948936,
822
+ "eval_rouge2": 0.3912770214119093,
823
+ "eval_rougeL": 0.4678029162844149,
824
+ "eval_rougeLsum": 0.4717999074200574,
825
+ "eval_runtime": 6.0508,
826
+ "eval_samples_per_second": 10.577,
827
+ "eval_steps_per_second": 2.644,
828
+ "step": 4662
829
+ },
830
+ {
831
+ "epoch": 64.0,
832
+ "eval_loss": 3.4136810302734375,
833
+ "eval_rouge1": 0.4863383911556584,
834
+ "eval_rouge2": 0.3918101023135222,
835
+ "eval_rougeL": 0.4691773006948949,
836
+ "eval_rougeLsum": 0.4701254305876148,
837
+ "eval_runtime": 5.9957,
838
+ "eval_samples_per_second": 10.674,
839
+ "eval_steps_per_second": 2.669,
840
+ "step": 4736
841
+ },
842
+ {
843
+ "epoch": 65.0,
844
+ "eval_loss": 3.408576488494873,
845
+ "eval_rouge1": 0.48284179574608654,
846
+ "eval_rouge2": 0.3858487599642365,
847
+ "eval_rougeL": 0.4641900110562617,
848
+ "eval_rougeLsum": 0.4663033361080079,
849
+ "eval_runtime": 5.9307,
850
+ "eval_samples_per_second": 10.791,
851
+ "eval_steps_per_second": 2.698,
852
+ "step": 4810
853
+ },
854
+ {
855
+ "epoch": 66.0,
856
+ "eval_loss": 3.451409339904785,
857
+ "eval_rouge1": 0.4856531269102483,
858
+ "eval_rouge2": 0.3856457649232374,
859
+ "eval_rougeL": 0.4649051696307025,
860
+ "eval_rougeLsum": 0.46875160328429377,
861
+ "eval_runtime": 6.2318,
862
+ "eval_samples_per_second": 10.27,
863
+ "eval_steps_per_second": 2.567,
864
+ "step": 4884
865
+ },
866
+ {
867
+ "epoch": 67.0,
868
+ "eval_loss": 3.484530210494995,
869
+ "eval_rouge1": 0.48758647184312953,
870
+ "eval_rouge2": 0.3840632511768816,
871
+ "eval_rougeL": 0.4672550598356402,
872
+ "eval_rougeLsum": 0.47087847986805387,
873
+ "eval_runtime": 6.5818,
874
+ "eval_samples_per_second": 9.724,
875
+ "eval_steps_per_second": 2.431,
876
+ "step": 4958
877
+ },
878
+ {
879
+ "epoch": 67.56756756756756,
880
+ "grad_norm": 0.10448549687862396,
881
+ "learning_rate": 0.00019864864864864863,
882
+ "loss": 0.0234,
883
+ "step": 5000
884
+ },
885
+ {
886
+ "epoch": 68.0,
887
+ "eval_loss": 3.4810497760772705,
888
+ "eval_rouge1": 0.49381108636054727,
889
+ "eval_rouge2": 0.39657607052252347,
890
+ "eval_rougeL": 0.47743909398976075,
891
+ "eval_rougeLsum": 0.4800737432511466,
892
+ "eval_runtime": 5.9672,
893
+ "eval_samples_per_second": 10.725,
894
+ "eval_steps_per_second": 2.681,
895
+ "step": 5032
896
+ },
897
+ {
898
+ "epoch": 69.0,
899
+ "eval_loss": 3.4901700019836426,
900
+ "eval_rouge1": 0.4898415437441482,
901
+ "eval_rouge2": 0.3882823621363838,
902
+ "eval_rougeL": 0.47261608178486914,
903
+ "eval_rougeLsum": 0.4741921184693466,
904
+ "eval_runtime": 5.9512,
905
+ "eval_samples_per_second": 10.754,
906
+ "eval_steps_per_second": 2.689,
907
+ "step": 5106
908
+ },
909
+ {
910
+ "epoch": 70.0,
911
+ "eval_loss": 3.5320417881011963,
912
+ "eval_rouge1": 0.4947141614912596,
913
+ "eval_rouge2": 0.39465368442175086,
914
+ "eval_rougeL": 0.4734668819817565,
915
+ "eval_rougeLsum": 0.4760338682248753,
916
+ "eval_runtime": 6.1859,
917
+ "eval_samples_per_second": 10.346,
918
+ "eval_steps_per_second": 2.587,
919
+ "step": 5180
920
+ },
921
+ {
922
+ "epoch": 71.0,
923
+ "eval_loss": 3.5137100219726562,
924
+ "eval_rouge1": 0.49608835837704873,
925
+ "eval_rouge2": 0.39887453020105085,
926
+ "eval_rougeL": 0.47537134411252835,
927
+ "eval_rougeLsum": 0.4782933040241389,
928
+ "eval_runtime": 6.5425,
929
+ "eval_samples_per_second": 9.782,
930
+ "eval_steps_per_second": 2.446,
931
+ "step": 5254
932
+ },
933
+ {
934
+ "epoch": 72.0,
935
+ "eval_loss": 3.54203462600708,
936
+ "eval_rouge1": 0.4938721262652266,
937
+ "eval_rouge2": 0.3991345798512075,
938
+ "eval_rougeL": 0.473889236162382,
939
+ "eval_rougeLsum": 0.4769789156636634,
940
+ "eval_runtime": 6.6452,
941
+ "eval_samples_per_second": 9.631,
942
+ "eval_steps_per_second": 2.408,
943
+ "step": 5328
944
+ },
945
+ {
946
+ "epoch": 73.0,
947
+ "eval_loss": 3.5607151985168457,
948
+ "eval_rouge1": 0.49582537040349045,
949
+ "eval_rouge2": 0.3988131906852439,
950
+ "eval_rougeL": 0.4742133994505331,
951
+ "eval_rougeLsum": 0.4766127354706121,
952
+ "eval_runtime": 6.7249,
953
+ "eval_samples_per_second": 9.517,
954
+ "eval_steps_per_second": 2.379,
955
+ "step": 5402
956
+ },
957
+ {
958
+ "epoch": 74.0,
959
+ "eval_loss": 3.5173583030700684,
960
+ "eval_rouge1": 0.49408949503121624,
961
+ "eval_rouge2": 0.3987998981499851,
962
+ "eval_rougeL": 0.4744563588816155,
963
+ "eval_rougeLsum": 0.477003901682462,
964
+ "eval_runtime": 6.815,
965
+ "eval_samples_per_second": 9.391,
966
+ "eval_steps_per_second": 2.348,
967
+ "step": 5476
968
+ },
969
+ {
970
+ "epoch": 74.32432432432432,
971
+ "grad_norm": 1.538454294204712,
972
+ "learning_rate": 0.0001885135135135135,
973
+ "loss": 0.0206,
974
+ "step": 5500
975
+ },
976
+ {
977
+ "epoch": 75.0,
978
+ "eval_loss": 3.510671615600586,
979
+ "eval_rouge1": 0.48857041939584583,
980
+ "eval_rouge2": 0.39406894473811616,
981
+ "eval_rougeL": 0.46991352957942084,
982
+ "eval_rougeLsum": 0.47053409246489913,
983
+ "eval_runtime": 6.4828,
984
+ "eval_samples_per_second": 9.872,
985
+ "eval_steps_per_second": 2.468,
986
+ "step": 5550
987
+ },
988
+ {
989
+ "epoch": 76.0,
990
+ "eval_loss": 3.511385440826416,
991
+ "eval_rouge1": 0.4958933420717311,
992
+ "eval_rouge2": 0.40271880135871385,
993
+ "eval_rougeL": 0.478388062531942,
994
+ "eval_rougeLsum": 0.4805975001489603,
995
+ "eval_runtime": 6.637,
996
+ "eval_samples_per_second": 9.643,
997
+ "eval_steps_per_second": 2.411,
998
+ "step": 5624
999
+ },
1000
+ {
1001
+ "epoch": 77.0,
1002
+ "eval_loss": 3.559112071990967,
1003
+ "eval_rouge1": 0.4873606646749901,
1004
+ "eval_rouge2": 0.39523537661271524,
1005
+ "eval_rougeL": 0.47059772736900357,
1006
+ "eval_rougeLsum": 0.4725288618416706,
1007
+ "eval_runtime": 6.8715,
1008
+ "eval_samples_per_second": 9.314,
1009
+ "eval_steps_per_second": 2.328,
1010
+ "step": 5698
1011
+ },
1012
+ {
1013
+ "epoch": 78.0,
1014
+ "eval_loss": 3.550933599472046,
1015
+ "eval_rouge1": 0.4866858870154881,
1016
+ "eval_rouge2": 0.3980955081516213,
1017
+ "eval_rougeL": 0.47115788584151075,
1018
+ "eval_rougeLsum": 0.4729082439223625,
1019
+ "eval_runtime": 6.9143,
1020
+ "eval_samples_per_second": 9.256,
1021
+ "eval_steps_per_second": 2.314,
1022
+ "step": 5772
1023
+ },
1024
+ {
1025
+ "epoch": 79.0,
1026
+ "eval_loss": 3.5746328830718994,
1027
+ "eval_rouge1": 0.4938385168719914,
1028
+ "eval_rouge2": 0.40148291472212705,
1029
+ "eval_rougeL": 0.47651891732980245,
1030
+ "eval_rougeLsum": 0.48196531108026874,
1031
+ "eval_runtime": 6.7321,
1032
+ "eval_samples_per_second": 9.507,
1033
+ "eval_steps_per_second": 2.377,
1034
+ "step": 5846
1035
+ },
1036
+ {
1037
+ "epoch": 80.0,
1038
+ "eval_loss": 3.6305410861968994,
1039
+ "eval_rouge1": 0.49906184754409744,
1040
+ "eval_rouge2": 0.4037579727503696,
1041
+ "eval_rougeL": 0.48135298410930016,
1042
+ "eval_rougeLsum": 0.4850652734866746,
1043
+ "eval_runtime": 6.9421,
1044
+ "eval_samples_per_second": 9.219,
1045
+ "eval_steps_per_second": 2.305,
1046
+ "step": 5920
1047
+ },
1048
+ {
1049
+ "epoch": 81.0,
1050
+ "eval_loss": 3.632502794265747,
1051
+ "eval_rouge1": 0.4937222626160631,
1052
+ "eval_rouge2": 0.4001823331099268,
1053
+ "eval_rougeL": 0.4723927700965753,
1054
+ "eval_rougeLsum": 0.4761599401277341,
1055
+ "eval_runtime": 7.1456,
1056
+ "eval_samples_per_second": 8.957,
1057
+ "eval_steps_per_second": 2.239,
1058
+ "step": 5994
1059
+ },
1060
+ {
1061
+ "epoch": 81.08108108108108,
1062
+ "grad_norm": 0.6058977842330933,
1063
+ "learning_rate": 0.00017837837837837839,
1064
+ "loss": 0.0151,
1065
+ "step": 6000
1066
+ },
1067
+ {
1068
+ "epoch": 82.0,
1069
+ "eval_loss": 3.6375513076782227,
1070
+ "eval_rouge1": 0.4961470087554145,
1071
+ "eval_rouge2": 0.40273253186645125,
1072
+ "eval_rougeL": 0.4771099396560761,
1073
+ "eval_rougeLsum": 0.48100694297178787,
1074
+ "eval_runtime": 6.7309,
1075
+ "eval_samples_per_second": 9.508,
1076
+ "eval_steps_per_second": 2.377,
1077
+ "step": 6068
1078
+ },
1079
+ {
1080
+ "epoch": 83.0,
1081
+ "eval_loss": 3.5627195835113525,
1082
+ "eval_rouge1": 0.4995314420849537,
1083
+ "eval_rouge2": 0.40335559902907575,
1084
+ "eval_rougeL": 0.4823993107807216,
1085
+ "eval_rougeLsum": 0.4866764546658857,
1086
+ "eval_runtime": 6.7823,
1087
+ "eval_samples_per_second": 9.436,
1088
+ "eval_steps_per_second": 2.359,
1089
+ "step": 6142
1090
+ },
1091
+ {
1092
+ "epoch": 84.0,
1093
+ "eval_loss": 3.586707592010498,
1094
+ "eval_rouge1": 0.4935070043523979,
1095
+ "eval_rouge2": 0.3942335588271486,
1096
+ "eval_rougeL": 0.474130711435772,
1097
+ "eval_rougeLsum": 0.4775505144021025,
1098
+ "eval_runtime": 6.7985,
1099
+ "eval_samples_per_second": 9.414,
1100
+ "eval_steps_per_second": 2.353,
1101
+ "step": 6216
1102
+ },
1103
+ {
1104
+ "epoch": 85.0,
1105
+ "eval_loss": 3.653571128845215,
1106
+ "eval_rouge1": 0.4881804248663784,
1107
+ "eval_rouge2": 0.391742835732956,
1108
+ "eval_rougeL": 0.46938710096628977,
1109
+ "eval_rougeLsum": 0.47182758126483004,
1110
+ "eval_runtime": 6.8579,
1111
+ "eval_samples_per_second": 9.332,
1112
+ "eval_steps_per_second": 2.333,
1113
+ "step": 6290
1114
+ },
1115
+ {
1116
+ "epoch": 86.0,
1117
+ "eval_loss": 3.643256664276123,
1118
+ "eval_rouge1": 0.48692368300546285,
1119
+ "eval_rouge2": 0.39335563997682566,
1120
+ "eval_rougeL": 0.4712442934765564,
1121
+ "eval_rougeLsum": 0.4741654824375442,
1122
+ "eval_runtime": 6.929,
1123
+ "eval_samples_per_second": 9.237,
1124
+ "eval_steps_per_second": 2.309,
1125
+ "step": 6364
1126
+ },
1127
+ {
1128
+ "epoch": 87.0,
1129
+ "eval_loss": 3.6616086959838867,
1130
+ "eval_rouge1": 0.49749293331782896,
1131
+ "eval_rouge2": 0.40300410454293367,
1132
+ "eval_rougeL": 0.47928673999842175,
1133
+ "eval_rougeLsum": 0.4837732647138796,
1134
+ "eval_runtime": 7.2255,
1135
+ "eval_samples_per_second": 8.857,
1136
+ "eval_steps_per_second": 2.214,
1137
+ "step": 6438
1138
+ },
1139
+ {
1140
+ "epoch": 87.83783783783784,
1141
+ "grad_norm": 0.235611692070961,
1142
+ "learning_rate": 0.00016824324324324325,
1143
+ "loss": 0.0121,
1144
+ "step": 6500
1145
+ },
1146
+ {
1147
+ "epoch": 88.0,
1148
+ "eval_loss": 3.656867504119873,
1149
+ "eval_rouge1": 0.4913983899917831,
1150
+ "eval_rouge2": 0.393535501893543,
1151
+ "eval_rougeL": 0.47100266301623717,
1152
+ "eval_rougeLsum": 0.4738950200928132,
1153
+ "eval_runtime": 6.7134,
1154
+ "eval_samples_per_second": 9.533,
1155
+ "eval_steps_per_second": 2.383,
1156
+ "step": 6512
1157
+ },
1158
+ {
1159
+ "epoch": 89.0,
1160
+ "eval_loss": 3.6369504928588867,
1161
+ "eval_rouge1": 0.5024515479898679,
1162
+ "eval_rouge2": 0.4068328278412592,
1163
+ "eval_rougeL": 0.4830703907699512,
1164
+ "eval_rougeLsum": 0.4860924010479748,
1165
+ "eval_runtime": 6.6955,
1166
+ "eval_samples_per_second": 9.559,
1167
+ "eval_steps_per_second": 2.39,
1168
+ "step": 6586
1169
+ },
1170
+ {
1171
+ "epoch": 90.0,
1172
+ "eval_loss": 3.651461601257324,
1173
+ "eval_rouge1": 0.4927558140102515,
1174
+ "eval_rouge2": 0.399360107524262,
1175
+ "eval_rougeL": 0.4765313230674868,
1176
+ "eval_rougeLsum": 0.4799470579462636,
1177
+ "eval_runtime": 6.9392,
1178
+ "eval_samples_per_second": 9.223,
1179
+ "eval_steps_per_second": 2.306,
1180
+ "step": 6660
1181
+ },
1182
+ {
1183
+ "epoch": 91.0,
1184
+ "eval_loss": 3.669370651245117,
1185
+ "eval_rouge1": 0.49371924215166024,
1186
+ "eval_rouge2": 0.40089928401621466,
1187
+ "eval_rougeL": 0.4757733012282773,
1188
+ "eval_rougeLsum": 0.4763141612251891,
1189
+ "eval_runtime": 6.8486,
1190
+ "eval_samples_per_second": 9.345,
1191
+ "eval_steps_per_second": 2.336,
1192
+ "step": 6734
1193
+ },
1194
+ {
1195
+ "epoch": 92.0,
1196
+ "eval_loss": 3.6855876445770264,
1197
+ "eval_rouge1": 0.49870880560202346,
1198
+ "eval_rouge2": 0.3995434714922107,
1199
+ "eval_rougeL": 0.47709889906045905,
1200
+ "eval_rougeLsum": 0.4800311476126575,
1201
+ "eval_runtime": 6.9861,
1202
+ "eval_samples_per_second": 9.161,
1203
+ "eval_steps_per_second": 2.29,
1204
+ "step": 6808
1205
+ },
1206
+ {
1207
+ "epoch": 93.0,
1208
+ "eval_loss": 3.658203125,
1209
+ "eval_rouge1": 0.49939709188553005,
1210
+ "eval_rouge2": 0.40124350229555694,
1211
+ "eval_rougeL": 0.47982810543295096,
1212
+ "eval_rougeLsum": 0.4811932796134847,
1213
+ "eval_runtime": 7.3285,
1214
+ "eval_samples_per_second": 8.733,
1215
+ "eval_steps_per_second": 2.183,
1216
+ "step": 6882
1217
+ },
1218
+ {
1219
+ "epoch": 94.0,
1220
+ "eval_loss": 3.6597373485565186,
1221
+ "eval_rouge1": 0.5035028200165406,
1222
+ "eval_rouge2": 0.4074152495888604,
1223
+ "eval_rougeL": 0.4832822677146339,
1224
+ "eval_rougeLsum": 0.48675050543330844,
1225
+ "eval_runtime": 7.2037,
1226
+ "eval_samples_per_second": 8.884,
1227
+ "eval_steps_per_second": 2.221,
1228
+ "step": 6956
1229
+ },
1230
+ {
1231
+ "epoch": 94.5945945945946,
1232
+ "grad_norm": 0.005829666741192341,
1233
+ "learning_rate": 0.0001581081081081081,
1234
+ "loss": 0.0113,
1235
+ "step": 7000
1236
+ },
1237
+ {
1238
+ "epoch": 95.0,
1239
+ "eval_loss": 3.6415438652038574,
1240
+ "eval_rouge1": 0.49360456034516226,
1241
+ "eval_rouge2": 0.40015057227140216,
1242
+ "eval_rougeL": 0.474561855190351,
1243
+ "eval_rougeLsum": 0.4762347047490384,
1244
+ "eval_runtime": 6.6515,
1245
+ "eval_samples_per_second": 9.622,
1246
+ "eval_steps_per_second": 2.405,
1247
+ "step": 7030
1248
+ },
1249
+ {
1250
+ "epoch": 96.0,
1251
+ "eval_loss": 3.6551480293273926,
1252
+ "eval_rouge1": 0.49903321106951,
1253
+ "eval_rouge2": 0.39766451768211863,
1254
+ "eval_rougeL": 0.4784771999456732,
1255
+ "eval_rougeLsum": 0.48001611691185453,
1256
+ "eval_runtime": 6.7778,
1257
+ "eval_samples_per_second": 9.443,
1258
+ "eval_steps_per_second": 2.361,
1259
+ "step": 7104
1260
+ },
1261
+ {
1262
+ "epoch": 97.0,
1263
+ "eval_loss": 3.6675968170166016,
1264
+ "eval_rouge1": 0.4932707200152202,
1265
+ "eval_rouge2": 0.39322477909813836,
1266
+ "eval_rougeL": 0.47512203026214206,
1267
+ "eval_rougeLsum": 0.4763580225435634,
1268
+ "eval_runtime": 6.8526,
1269
+ "eval_samples_per_second": 9.339,
1270
+ "eval_steps_per_second": 2.335,
1271
+ "step": 7178
1272
+ },
1273
+ {
1274
+ "epoch": 98.0,
1275
+ "eval_loss": 3.6883370876312256,
1276
+ "eval_rouge1": 0.4875206376053254,
1277
+ "eval_rouge2": 0.3854412341399984,
1278
+ "eval_rougeL": 0.46686705922324473,
1279
+ "eval_rougeLsum": 0.4696615201324402,
1280
+ "eval_runtime": 6.6871,
1281
+ "eval_samples_per_second": 9.571,
1282
+ "eval_steps_per_second": 2.393,
1283
+ "step": 7252
1284
+ },
1285
+ {
1286
+ "epoch": 99.0,
1287
+ "eval_loss": 3.750239849090576,
1288
+ "eval_rouge1": 0.4895475548259989,
1289
+ "eval_rouge2": 0.3931543734202324,
1290
+ "eval_rougeL": 0.4729295951578888,
1291
+ "eval_rougeLsum": 0.4733894371856425,
1292
+ "eval_runtime": 6.8243,
1293
+ "eval_samples_per_second": 9.378,
1294
+ "eval_steps_per_second": 2.345,
1295
+ "step": 7326
1296
+ },
1297
+ {
1298
+ "epoch": 100.0,
1299
+ "eval_loss": 3.710012435913086,
1300
+ "eval_rouge1": 0.4922460168917058,
1301
+ "eval_rouge2": 0.38907716748403615,
1302
+ "eval_rougeL": 0.4703757958634286,
1303
+ "eval_rougeLsum": 0.47469578477355245,
1304
+ "eval_runtime": 7.1953,
1305
+ "eval_samples_per_second": 8.895,
1306
+ "eval_steps_per_second": 2.224,
1307
+ "step": 7400
1308
+ },
1309
+ {
1310
+ "epoch": 101.0,
1311
+ "eval_loss": 3.7263288497924805,
1312
+ "eval_rouge1": 0.4994776956737418,
1313
+ "eval_rouge2": 0.4016675015566174,
1314
+ "eval_rougeL": 0.47921650877286537,
1315
+ "eval_rougeLsum": 0.481978781304056,
1316
+ "eval_runtime": 7.1605,
1317
+ "eval_samples_per_second": 8.938,
1318
+ "eval_steps_per_second": 2.234,
1319
+ "step": 7474
1320
+ },
1321
+ {
1322
+ "epoch": 101.35135135135135,
1323
+ "grad_norm": 1.3754329681396484,
1324
+ "learning_rate": 0.00014797297297297295,
1325
+ "loss": 0.0115,
1326
+ "step": 7500
1327
+ },
1328
+ {
1329
+ "epoch": 102.0,
1330
+ "eval_loss": 3.7390670776367188,
1331
+ "eval_rouge1": 0.4970291645397934,
1332
+ "eval_rouge2": 0.3965329334942411,
1333
+ "eval_rougeL": 0.4785005226666328,
1334
+ "eval_rougeLsum": 0.48034491922833267,
1335
+ "eval_runtime": 6.6275,
1336
+ "eval_samples_per_second": 9.657,
1337
+ "eval_steps_per_second": 2.414,
1338
+ "step": 7548
1339
+ },
1340
+ {
1341
+ "epoch": 103.0,
1342
+ "eval_loss": 3.732781410217285,
1343
+ "eval_rouge1": 0.48700489472062974,
1344
+ "eval_rouge2": 0.39143224992971243,
1345
+ "eval_rougeL": 0.4697739833563407,
1346
+ "eval_rougeLsum": 0.47133796360275837,
1347
+ "eval_runtime": 6.758,
1348
+ "eval_samples_per_second": 9.47,
1349
+ "eval_steps_per_second": 2.368,
1350
+ "step": 7622
1351
+ },
1352
+ {
1353
+ "epoch": 104.0,
1354
+ "eval_loss": 3.7326784133911133,
1355
+ "eval_rouge1": 0.48634126558210156,
1356
+ "eval_rouge2": 0.3914253095431699,
1357
+ "eval_rougeL": 0.4662095381023694,
1358
+ "eval_rougeLsum": 0.46828089571132425,
1359
+ "eval_runtime": 6.9292,
1360
+ "eval_samples_per_second": 9.236,
1361
+ "eval_steps_per_second": 2.309,
1362
+ "step": 7696
1363
+ },
1364
+ {
1365
+ "epoch": 105.0,
1366
+ "eval_loss": 3.72397780418396,
1367
+ "eval_rouge1": 0.49207262377656813,
1368
+ "eval_rouge2": 0.3926530860066015,
1369
+ "eval_rougeL": 0.4716827714689972,
1370
+ "eval_rougeLsum": 0.47383906517378155,
1371
+ "eval_runtime": 6.6924,
1372
+ "eval_samples_per_second": 9.563,
1373
+ "eval_steps_per_second": 2.391,
1374
+ "step": 7770
1375
+ },
1376
+ {
1377
+ "epoch": 106.0,
1378
+ "eval_loss": 3.71506404876709,
1379
+ "eval_rouge1": 0.491413986073613,
1380
+ "eval_rouge2": 0.39806354091405716,
1381
+ "eval_rougeL": 0.47232948697868965,
1382
+ "eval_rougeLsum": 0.47370687635582465,
1383
+ "eval_runtime": 6.8886,
1384
+ "eval_samples_per_second": 9.291,
1385
+ "eval_steps_per_second": 2.323,
1386
+ "step": 7844
1387
+ },
1388
+ {
1389
+ "epoch": 107.0,
1390
+ "eval_loss": 3.7703864574432373,
1391
+ "eval_rouge1": 0.49389730784828345,
1392
+ "eval_rouge2": 0.39541639053141187,
1393
+ "eval_rougeL": 0.4714732208294661,
1394
+ "eval_rougeLsum": 0.47623481194977557,
1395
+ "eval_runtime": 6.9886,
1396
+ "eval_samples_per_second": 9.158,
1397
+ "eval_steps_per_second": 2.289,
1398
+ "step": 7918
1399
+ },
1400
+ {
1401
+ "epoch": 108.0,
1402
+ "eval_loss": 3.731736421585083,
1403
+ "eval_rouge1": 0.49478828073404685,
1404
+ "eval_rouge2": 0.39657333313753584,
1405
+ "eval_rougeL": 0.4749519387034692,
1406
+ "eval_rougeLsum": 0.47610183775428533,
1407
+ "eval_runtime": 7.0844,
1408
+ "eval_samples_per_second": 9.034,
1409
+ "eval_steps_per_second": 2.258,
1410
+ "step": 7992
1411
+ },
1412
+ {
1413
+ "epoch": 108.10810810810811,
1414
+ "grad_norm": 0.15748290717601776,
1415
+ "learning_rate": 0.00013783783783783782,
1416
+ "loss": 0.0097,
1417
+ "step": 8000
1418
+ },
1419
+ {
1420
+ "epoch": 109.0,
1421
+ "eval_loss": 3.7394156455993652,
1422
+ "eval_rouge1": 0.4928722114905978,
1423
+ "eval_rouge2": 0.39617632886171655,
1424
+ "eval_rougeL": 0.4727238492899394,
1425
+ "eval_rougeLsum": 0.4738978259656522,
1426
+ "eval_runtime": 6.7715,
1427
+ "eval_samples_per_second": 9.451,
1428
+ "eval_steps_per_second": 2.363,
1429
+ "step": 8066
1430
+ },
1431
+ {
1432
+ "epoch": 110.0,
1433
+ "eval_loss": 3.782604217529297,
1434
+ "eval_rouge1": 0.48456677608733023,
1435
+ "eval_rouge2": 0.39200786618317157,
1436
+ "eval_rougeL": 0.46735627531908003,
1437
+ "eval_rougeLsum": 0.4678895131769854,
1438
+ "eval_runtime": 6.6784,
1439
+ "eval_samples_per_second": 9.583,
1440
+ "eval_steps_per_second": 2.396,
1441
+ "step": 8140
1442
+ },
1443
+ {
1444
+ "epoch": 111.0,
1445
+ "eval_loss": 3.756638526916504,
1446
+ "eval_rouge1": 0.4845583346799728,
1447
+ "eval_rouge2": 0.39273356781728475,
1448
+ "eval_rougeL": 0.46727953305101155,
1449
+ "eval_rougeLsum": 0.46750848691275326,
1450
+ "eval_runtime": 6.7593,
1451
+ "eval_samples_per_second": 9.468,
1452
+ "eval_steps_per_second": 2.367,
1453
+ "step": 8214
1454
+ },
1455
+ {
1456
+ "epoch": 112.0,
1457
+ "eval_loss": 3.7435970306396484,
1458
+ "eval_rouge1": 0.47934894419153573,
1459
+ "eval_rouge2": 0.38451063069829866,
1460
+ "eval_rougeL": 0.460189645563753,
1461
+ "eval_rougeLsum": 0.46059641183020916,
1462
+ "eval_runtime": 6.7106,
1463
+ "eval_samples_per_second": 9.537,
1464
+ "eval_steps_per_second": 2.384,
1465
+ "step": 8288
1466
+ },
1467
+ {
1468
+ "epoch": 113.0,
1469
+ "eval_loss": 3.7368521690368652,
1470
+ "eval_rouge1": 0.4829508280944451,
1471
+ "eval_rouge2": 0.3823021635565298,
1472
+ "eval_rougeL": 0.4603754136609347,
1473
+ "eval_rougeLsum": 0.46119234388219343,
1474
+ "eval_runtime": 6.9009,
1475
+ "eval_samples_per_second": 9.274,
1476
+ "eval_steps_per_second": 2.319,
1477
+ "step": 8362
1478
+ },
1479
+ {
1480
+ "epoch": 114.0,
1481
+ "eval_loss": 3.753373622894287,
1482
+ "eval_rouge1": 0.48550199682179285,
1483
+ "eval_rouge2": 0.39669425610509723,
1484
+ "eval_rougeL": 0.46928318330826313,
1485
+ "eval_rougeLsum": 0.4700911939934148,
1486
+ "eval_runtime": 6.9224,
1487
+ "eval_samples_per_second": 9.245,
1488
+ "eval_steps_per_second": 2.311,
1489
+ "step": 8436
1490
+ },
1491
+ {
1492
+ "epoch": 114.86486486486487,
1493
+ "grad_norm": 2.249493360519409,
1494
+ "learning_rate": 0.00012770270270270269,
1495
+ "loss": 0.0081,
1496
+ "step": 8500
1497
+ },
1498
+ {
1499
+ "epoch": 115.0,
1500
+ "eval_loss": 3.7596099376678467,
1501
+ "eval_rouge1": 0.4844489870502281,
1502
+ "eval_rouge2": 0.39373641353300476,
1503
+ "eval_rougeL": 0.465943647782728,
1504
+ "eval_rougeLsum": 0.4667838391510246,
1505
+ "eval_runtime": 6.7565,
1506
+ "eval_samples_per_second": 9.472,
1507
+ "eval_steps_per_second": 2.368,
1508
+ "step": 8510
1509
+ },
1510
+ {
1511
+ "epoch": 116.0,
1512
+ "eval_loss": 3.7971744537353516,
1513
+ "eval_rouge1": 0.4839609425846231,
1514
+ "eval_rouge2": 0.39429760970418737,
1515
+ "eval_rougeL": 0.4676976417871506,
1516
+ "eval_rougeLsum": 0.46788383269053146,
1517
+ "eval_runtime": 6.7435,
1518
+ "eval_samples_per_second": 9.491,
1519
+ "eval_steps_per_second": 2.373,
1520
+ "step": 8584
1521
+ },
1522
+ {
1523
+ "epoch": 117.0,
1524
+ "eval_loss": 3.796170711517334,
1525
+ "eval_rouge1": 0.4890036495615311,
1526
+ "eval_rouge2": 0.40029838829858966,
1527
+ "eval_rougeL": 0.4695189944140329,
1528
+ "eval_rougeLsum": 0.47150052045445745,
1529
+ "eval_runtime": 6.8876,
1530
+ "eval_samples_per_second": 9.292,
1531
+ "eval_steps_per_second": 2.323,
1532
+ "step": 8658
1533
+ },
1534
+ {
1535
+ "epoch": 118.0,
1536
+ "eval_loss": 3.7930757999420166,
1537
+ "eval_rouge1": 0.49228898940808674,
1538
+ "eval_rouge2": 0.39827560867374456,
1539
+ "eval_rougeL": 0.4744564034893066,
1540
+ "eval_rougeLsum": 0.4766465053914651,
1541
+ "eval_runtime": 7.2191,
1542
+ "eval_samples_per_second": 8.865,
1543
+ "eval_steps_per_second": 2.216,
1544
+ "step": 8732
1545
+ },
1546
+ {
1547
+ "epoch": 119.0,
1548
+ "eval_loss": 3.8108878135681152,
1549
+ "eval_rouge1": 0.4847730471627255,
1550
+ "eval_rouge2": 0.3942853548976314,
1551
+ "eval_rougeL": 0.46643367219610266,
1552
+ "eval_rougeLsum": 0.46858946699295617,
1553
+ "eval_runtime": 7.3767,
1554
+ "eval_samples_per_second": 8.676,
1555
+ "eval_steps_per_second": 2.169,
1556
+ "step": 8806
1557
+ },
1558
+ {
1559
+ "epoch": 120.0,
1560
+ "eval_loss": 3.8008246421813965,
1561
+ "eval_rouge1": 0.4846634237685579,
1562
+ "eval_rouge2": 0.39052270581455634,
1563
+ "eval_rougeL": 0.46516978082832616,
1564
+ "eval_rougeLsum": 0.4660286941183181,
1565
+ "eval_runtime": 7.1943,
1566
+ "eval_samples_per_second": 8.896,
1567
+ "eval_steps_per_second": 2.224,
1568
+ "step": 8880
1569
+ },
1570
+ {
1571
+ "epoch": 121.0,
1572
+ "eval_loss": 3.837533712387085,
1573
+ "eval_rouge1": 0.480238168191317,
1574
+ "eval_rouge2": 0.3836647960301529,
1575
+ "eval_rougeL": 0.45981846963427486,
1576
+ "eval_rougeLsum": 0.46002047511561506,
1577
+ "eval_runtime": 7.4528,
1578
+ "eval_samples_per_second": 8.587,
1579
+ "eval_steps_per_second": 2.147,
1580
+ "step": 8954
1581
+ },
1582
+ {
1583
+ "epoch": 121.62162162162163,
1584
+ "grad_norm": 0.156394362449646,
1585
+ "learning_rate": 0.00011756756756756755,
1586
+ "loss": 0.0073,
1587
+ "step": 9000
1588
+ },
1589
+ {
1590
+ "epoch": 122.0,
1591
+ "eval_loss": 3.844420909881592,
1592
+ "eval_rouge1": 0.48399770438699874,
1593
+ "eval_rouge2": 0.38640038347896755,
1594
+ "eval_rougeL": 0.46195539603011354,
1595
+ "eval_rougeLsum": 0.46383728530832075,
1596
+ "eval_runtime": 6.5224,
1597
+ "eval_samples_per_second": 9.812,
1598
+ "eval_steps_per_second": 2.453,
1599
+ "step": 9028
1600
+ },
1601
+ {
1602
+ "epoch": 123.0,
1603
+ "eval_loss": 3.8776814937591553,
1604
+ "eval_rouge1": 0.4854005110821537,
1605
+ "eval_rouge2": 0.3917034412373144,
1606
+ "eval_rougeL": 0.4668504149804634,
1607
+ "eval_rougeLsum": 0.4673636008329948,
1608
+ "eval_runtime": 6.6767,
1609
+ "eval_samples_per_second": 9.586,
1610
+ "eval_steps_per_second": 2.396,
1611
+ "step": 9102
1612
+ },
1613
+ {
1614
+ "epoch": 124.0,
1615
+ "eval_loss": 3.865213394165039,
1616
+ "eval_rouge1": 0.48354814096021004,
1617
+ "eval_rouge2": 0.3875565081336061,
1618
+ "eval_rougeL": 0.4644387512744705,
1619
+ "eval_rougeLsum": 0.4657678163591755,
1620
+ "eval_runtime": 6.7223,
1621
+ "eval_samples_per_second": 9.521,
1622
+ "eval_steps_per_second": 2.38,
1623
+ "step": 9176
1624
+ },
1625
+ {
1626
+ "epoch": 125.0,
1627
+ "eval_loss": 3.8568525314331055,
1628
+ "eval_rouge1": 0.49281072095688017,
1629
+ "eval_rouge2": 0.39982303603622116,
1630
+ "eval_rougeL": 0.47299639047330055,
1631
+ "eval_rougeLsum": 0.474738468225831,
1632
+ "eval_runtime": 6.714,
1633
+ "eval_samples_per_second": 9.532,
1634
+ "eval_steps_per_second": 2.383,
1635
+ "step": 9250
1636
+ },
1637
+ {
1638
+ "epoch": 126.0,
1639
+ "eval_loss": 3.874713659286499,
1640
+ "eval_rouge1": 0.48223669204507696,
1641
+ "eval_rouge2": 0.3940917922642585,
1642
+ "eval_rougeL": 0.46483980398639463,
1643
+ "eval_rougeLsum": 0.4654093903936942,
1644
+ "eval_runtime": 6.8849,
1645
+ "eval_samples_per_second": 9.296,
1646
+ "eval_steps_per_second": 2.324,
1647
+ "step": 9324
1648
+ },
1649
+ {
1650
+ "epoch": 127.0,
1651
+ "eval_loss": 3.8582425117492676,
1652
+ "eval_rouge1": 0.48577800020767237,
1653
+ "eval_rouge2": 0.3893328433203812,
1654
+ "eval_rougeL": 0.4642142206721902,
1655
+ "eval_rougeLsum": 0.46762126305920615,
1656
+ "eval_runtime": 7.1741,
1657
+ "eval_samples_per_second": 8.921,
1658
+ "eval_steps_per_second": 2.23,
1659
+ "step": 9398
1660
+ },
1661
+ {
1662
+ "epoch": 128.0,
1663
+ "eval_loss": 3.8560242652893066,
1664
+ "eval_rouge1": 0.48276042100553784,
1665
+ "eval_rouge2": 0.3935526373639349,
1666
+ "eval_rougeL": 0.46394413427722736,
1667
+ "eval_rougeLsum": 0.46693603589333066,
1668
+ "eval_runtime": 7.4705,
1669
+ "eval_samples_per_second": 8.567,
1670
+ "eval_steps_per_second": 2.142,
1671
+ "step": 9472
1672
+ },
1673
+ {
1674
+ "epoch": 128.3783783783784,
1675
+ "grad_norm": 0.5053192377090454,
1676
+ "learning_rate": 0.00010743243243243243,
1677
+ "loss": 0.0052,
1678
+ "step": 9500
1679
+ },
1680
+ {
1681
+ "epoch": 129.0,
1682
+ "eval_loss": 3.8928046226501465,
1683
+ "eval_rouge1": 0.4827880613762454,
1684
+ "eval_rouge2": 0.39063612795118435,
1685
+ "eval_rougeL": 0.46292609876431945,
1686
+ "eval_rougeLsum": 0.4639229804932192,
1687
+ "eval_runtime": 6.7521,
1688
+ "eval_samples_per_second": 9.479,
1689
+ "eval_steps_per_second": 2.37,
1690
+ "step": 9546
1691
+ },
1692
+ {
1693
+ "epoch": 130.0,
1694
+ "eval_loss": 3.8779563903808594,
1695
+ "eval_rouge1": 0.4844923294167751,
1696
+ "eval_rouge2": 0.38633459533219433,
1697
+ "eval_rougeL": 0.46262521762970926,
1698
+ "eval_rougeLsum": 0.4640136282049044,
1699
+ "eval_runtime": 6.7605,
1700
+ "eval_samples_per_second": 9.467,
1701
+ "eval_steps_per_second": 2.367,
1702
+ "step": 9620
1703
+ },
1704
+ {
1705
+ "epoch": 131.0,
1706
+ "eval_loss": 3.866152286529541,
1707
+ "eval_rouge1": 0.4852900095674466,
1708
+ "eval_rouge2": 0.391461632155927,
1709
+ "eval_rougeL": 0.4646976857262868,
1710
+ "eval_rougeLsum": 0.4650219596477825,
1711
+ "eval_runtime": 7.1336,
1712
+ "eval_samples_per_second": 8.972,
1713
+ "eval_steps_per_second": 2.243,
1714
+ "step": 9694
1715
+ },
1716
+ {
1717
+ "epoch": 132.0,
1718
+ "eval_loss": 3.876262664794922,
1719
+ "eval_rouge1": 0.4814059761270737,
1720
+ "eval_rouge2": 0.38660843742603485,
1721
+ "eval_rougeL": 0.4597208266484611,
1722
+ "eval_rougeLsum": 0.46074176653361254,
1723
+ "eval_runtime": 7.2201,
1724
+ "eval_samples_per_second": 8.864,
1725
+ "eval_steps_per_second": 2.216,
1726
+ "step": 9768
1727
+ },
1728
+ {
1729
+ "epoch": 133.0,
1730
+ "eval_loss": 3.8748536109924316,
1731
+ "eval_rouge1": 0.4845049505767603,
1732
+ "eval_rouge2": 0.38630241264644166,
1733
+ "eval_rougeL": 0.46161461756838357,
1734
+ "eval_rougeLsum": 0.4614392713949589,
1735
+ "eval_runtime": 7.3979,
1736
+ "eval_samples_per_second": 8.651,
1737
+ "eval_steps_per_second": 2.163,
1738
+ "step": 9842
1739
+ },
1740
+ {
1741
+ "epoch": 134.0,
1742
+ "eval_loss": 3.903346300125122,
1743
+ "eval_rouge1": 0.48684820794711436,
1744
+ "eval_rouge2": 0.39076743252039103,
1745
+ "eval_rougeL": 0.46325285677108063,
1746
+ "eval_rougeLsum": 0.465521140679641,
1747
+ "eval_runtime": 7.5395,
1748
+ "eval_samples_per_second": 8.489,
1749
+ "eval_steps_per_second": 2.122,
1750
+ "step": 9916
1751
+ },
1752
+ {
1753
+ "epoch": 135.0,
1754
+ "eval_loss": 3.913891315460205,
1755
+ "eval_rouge1": 0.48673702365042004,
1756
+ "eval_rouge2": 0.3912891412344346,
1757
+ "eval_rougeL": 0.46486407293584286,
1758
+ "eval_rougeLsum": 0.46762822555796624,
1759
+ "eval_runtime": 7.2933,
1760
+ "eval_samples_per_second": 8.775,
1761
+ "eval_steps_per_second": 2.194,
1762
+ "step": 9990
1763
+ },
1764
+ {
1765
+ "epoch": 135.13513513513513,
1766
+ "grad_norm": 0.164429172873497,
1767
+ "learning_rate": 9.72972972972973e-05,
1768
+ "loss": 0.0056,
1769
+ "step": 10000
1770
+ },
1771
+ {
1772
+ "epoch": 136.0,
1773
+ "eval_loss": 3.932033061981201,
1774
+ "eval_rouge1": 0.4843296592917674,
1775
+ "eval_rouge2": 0.38711489173362024,
1776
+ "eval_rougeL": 0.4628261592622239,
1777
+ "eval_rougeLsum": 0.46403305263253225,
1778
+ "eval_runtime": 6.7372,
1779
+ "eval_samples_per_second": 9.5,
1780
+ "eval_steps_per_second": 2.375,
1781
+ "step": 10064
1782
+ },
1783
+ {
1784
+ "epoch": 137.0,
1785
+ "eval_loss": 3.9207522869110107,
1786
+ "eval_rouge1": 0.48663560972636954,
1787
+ "eval_rouge2": 0.38917485963208237,
1788
+ "eval_rougeL": 0.4641843636902843,
1789
+ "eval_rougeLsum": 0.4670661984486967,
1790
+ "eval_runtime": 7.0897,
1791
+ "eval_samples_per_second": 9.027,
1792
+ "eval_steps_per_second": 2.257,
1793
+ "step": 10138
1794
+ },
1795
+ {
1796
+ "epoch": 138.0,
1797
+ "eval_loss": 3.923243999481201,
1798
+ "eval_rouge1": 0.4869405313162995,
1799
+ "eval_rouge2": 0.39033225065949406,
1800
+ "eval_rougeL": 0.4660086299963394,
1801
+ "eval_rougeLsum": 0.4694681627569816,
1802
+ "eval_runtime": 7.3705,
1803
+ "eval_samples_per_second": 8.683,
1804
+ "eval_steps_per_second": 2.171,
1805
+ "step": 10212
1806
+ },
1807
+ {
1808
+ "epoch": 139.0,
1809
+ "eval_loss": 3.9049696922302246,
1810
+ "eval_rouge1": 0.4857155018095176,
1811
+ "eval_rouge2": 0.3903974717105526,
1812
+ "eval_rougeL": 0.46598084906502785,
1813
+ "eval_rougeLsum": 0.4687923513004851,
1814
+ "eval_runtime": 7.5586,
1815
+ "eval_samples_per_second": 8.467,
1816
+ "eval_steps_per_second": 2.117,
1817
+ "step": 10286
1818
+ },
1819
+ {
1820
+ "epoch": 140.0,
1821
+ "eval_loss": 3.9089577198028564,
1822
+ "eval_rouge1": 0.49232283072813465,
1823
+ "eval_rouge2": 0.39755334531122133,
1824
+ "eval_rougeL": 0.4720020408046367,
1825
+ "eval_rougeLsum": 0.4733960027621831,
1826
+ "eval_runtime": 7.4052,
1827
+ "eval_samples_per_second": 8.643,
1828
+ "eval_steps_per_second": 2.161,
1829
+ "step": 10360
1830
+ },
1831
+ {
1832
+ "epoch": 141.0,
1833
+ "eval_loss": 3.9259438514709473,
1834
+ "eval_rouge1": 0.48520578506166845,
1835
+ "eval_rouge2": 0.3929926818071112,
1836
+ "eval_rougeL": 0.4657921992214292,
1837
+ "eval_rougeLsum": 0.46805633734997604,
1838
+ "eval_runtime": 7.7086,
1839
+ "eval_samples_per_second": 8.302,
1840
+ "eval_steps_per_second": 2.076,
1841
+ "step": 10434
1842
+ },
1843
+ {
1844
+ "epoch": 141.8918918918919,
1845
+ "grad_norm": 0.04262608289718628,
1846
+ "learning_rate": 8.716216216216215e-05,
1847
+ "loss": 0.0038,
1848
+ "step": 10500
1849
+ },
1850
+ {
1851
+ "epoch": 142.0,
1852
+ "eval_loss": 3.944688558578491,
1853
+ "eval_rouge1": 0.487675604262949,
1854
+ "eval_rouge2": 0.3921027004601982,
1855
+ "eval_rougeL": 0.4679360442338828,
1856
+ "eval_rougeLsum": 0.4707407417491424,
1857
+ "eval_runtime": 6.5398,
1858
+ "eval_samples_per_second": 9.786,
1859
+ "eval_steps_per_second": 2.447,
1860
+ "step": 10508
1861
+ },
1862
+ {
1863
+ "epoch": 143.0,
1864
+ "eval_loss": 3.9202613830566406,
1865
+ "eval_rouge1": 0.4869107696524746,
1866
+ "eval_rouge2": 0.39163777862392646,
1867
+ "eval_rougeL": 0.4667490559738572,
1868
+ "eval_rougeLsum": 0.4693423272541999,
1869
+ "eval_runtime": 6.705,
1870
+ "eval_samples_per_second": 9.545,
1871
+ "eval_steps_per_second": 2.386,
1872
+ "step": 10582
1873
+ },
1874
+ {
1875
+ "epoch": 144.0,
1876
+ "eval_loss": 3.948978900909424,
1877
+ "eval_rouge1": 0.49250533905328897,
1878
+ "eval_rouge2": 0.3959336606525481,
1879
+ "eval_rougeL": 0.47206086537528646,
1880
+ "eval_rougeLsum": 0.473413686648378,
1881
+ "eval_runtime": 6.853,
1882
+ "eval_samples_per_second": 9.339,
1883
+ "eval_steps_per_second": 2.335,
1884
+ "step": 10656
1885
+ },
1886
+ {
1887
+ "epoch": 145.0,
1888
+ "eval_loss": 3.9446568489074707,
1889
+ "eval_rouge1": 0.48810661530935073,
1890
+ "eval_rouge2": 0.3932420193989471,
1891
+ "eval_rougeL": 0.467612141938169,
1892
+ "eval_rougeLsum": 0.4700796872193581,
1893
+ "eval_runtime": 6.8609,
1894
+ "eval_samples_per_second": 9.328,
1895
+ "eval_steps_per_second": 2.332,
1896
+ "step": 10730
1897
+ },
1898
+ {
1899
+ "epoch": 146.0,
1900
+ "eval_loss": 3.9405150413513184,
1901
+ "eval_rouge1": 0.48480711997528214,
1902
+ "eval_rouge2": 0.3933858006917045,
1903
+ "eval_rougeL": 0.46612345176895637,
1904
+ "eval_rougeLsum": 0.46797061838955234,
1905
+ "eval_runtime": 6.7331,
1906
+ "eval_samples_per_second": 9.505,
1907
+ "eval_steps_per_second": 2.376,
1908
+ "step": 10804
1909
+ },
1910
+ {
1911
+ "epoch": 147.0,
1912
+ "eval_loss": 3.9228992462158203,
1913
+ "eval_rouge1": 0.4873307537597772,
1914
+ "eval_rouge2": 0.39731296067287103,
1915
+ "eval_rougeL": 0.47021025970811053,
1916
+ "eval_rougeLsum": 0.4720477730864451,
1917
+ "eval_runtime": 6.9553,
1918
+ "eval_samples_per_second": 9.202,
1919
+ "eval_steps_per_second": 2.3,
1920
+ "step": 10878
1921
+ },
1922
+ {
1923
+ "epoch": 148.0,
1924
+ "eval_loss": 3.927485227584839,
1925
+ "eval_rouge1": 0.4894933069163522,
1926
+ "eval_rouge2": 0.39630502877208873,
1927
+ "eval_rougeL": 0.4706409032694612,
1928
+ "eval_rougeLsum": 0.47251705975502384,
1929
+ "eval_runtime": 6.8852,
1930
+ "eval_samples_per_second": 9.295,
1931
+ "eval_steps_per_second": 2.324,
1932
+ "step": 10952
1933
+ },
1934
+ {
1935
+ "epoch": 148.64864864864865,
1936
+ "grad_norm": 0.06265202164649963,
1937
+ "learning_rate": 7.702702702702701e-05,
1938
+ "loss": 0.0046,
1939
+ "step": 11000
1940
+ },
1941
+ {
1942
+ "epoch": 149.0,
1943
+ "eval_loss": 3.9115383625030518,
1944
+ "eval_rouge1": 0.48236726641895555,
1945
+ "eval_rouge2": 0.39058286433636713,
1946
+ "eval_rougeL": 0.46227491108174484,
1947
+ "eval_rougeLsum": 0.4629699932236985,
1948
+ "eval_runtime": 6.7009,
1949
+ "eval_samples_per_second": 9.551,
1950
+ "eval_steps_per_second": 2.388,
1951
+ "step": 11026
1952
+ },
1953
+ {
1954
+ "epoch": 150.0,
1955
+ "eval_loss": 3.930911064147949,
1956
+ "eval_rouge1": 0.4878527875495306,
1957
+ "eval_rouge2": 0.39283884580724954,
1958
+ "eval_rougeL": 0.4671990073575799,
1959
+ "eval_rougeLsum": 0.47041003584932495,
1960
+ "eval_runtime": 6.6879,
1961
+ "eval_samples_per_second": 9.57,
1962
+ "eval_steps_per_second": 2.392,
1963
+ "step": 11100
1964
+ },
1965
+ {
1966
+ "epoch": 151.0,
1967
+ "eval_loss": 3.9732909202575684,
1968
+ "eval_rouge1": 0.4842635411230555,
1969
+ "eval_rouge2": 0.3934133257871197,
1970
+ "eval_rougeL": 0.46621039602137504,
1971
+ "eval_rougeLsum": 0.46784839735484063,
1972
+ "eval_runtime": 6.7159,
1973
+ "eval_samples_per_second": 9.53,
1974
+ "eval_steps_per_second": 2.382,
1975
+ "step": 11174
1976
+ },
1977
+ {
1978
+ "epoch": 152.0,
1979
+ "eval_loss": 3.952836036682129,
1980
+ "eval_rouge1": 0.48821078362566034,
1981
+ "eval_rouge2": 0.3930914690285585,
1982
+ "eval_rougeL": 0.46691136255327237,
1983
+ "eval_rougeLsum": 0.47018503206271367,
1984
+ "eval_runtime": 6.8389,
1985
+ "eval_samples_per_second": 9.358,
1986
+ "eval_steps_per_second": 2.34,
1987
+ "step": 11248
1988
+ },
1989
+ {
1990
+ "epoch": 153.0,
1991
+ "eval_loss": 3.9353346824645996,
1992
+ "eval_rouge1": 0.49172107393851816,
1993
+ "eval_rouge2": 0.394135306910142,
1994
+ "eval_rougeL": 0.47053235476800326,
1995
+ "eval_rougeLsum": 0.47467536744383443,
1996
+ "eval_runtime": 7.0262,
1997
+ "eval_samples_per_second": 9.109,
1998
+ "eval_steps_per_second": 2.277,
1999
+ "step": 11322
2000
+ },
2001
+ {
2002
+ "epoch": 154.0,
2003
+ "eval_loss": 3.955352783203125,
2004
+ "eval_rouge1": 0.4925059248834573,
2005
+ "eval_rouge2": 0.39699149764016994,
2006
+ "eval_rougeL": 0.4718398234633252,
2007
+ "eval_rougeLsum": 0.47625245196436417,
2008
+ "eval_runtime": 7.3091,
2009
+ "eval_samples_per_second": 8.756,
2010
+ "eval_steps_per_second": 2.189,
2011
+ "step": 11396
2012
+ },
2013
+ {
2014
+ "epoch": 155.0,
2015
+ "eval_loss": 3.9426536560058594,
2016
+ "eval_rouge1": 0.4924969427568193,
2017
+ "eval_rouge2": 0.3960196634992188,
2018
+ "eval_rougeL": 0.47242435472194855,
2019
+ "eval_rougeLsum": 0.47677592847041894,
2020
+ "eval_runtime": 7.5133,
2021
+ "eval_samples_per_second": 8.518,
2022
+ "eval_steps_per_second": 2.13,
2023
+ "step": 11470
2024
+ },
2025
+ {
2026
+ "epoch": 155.40540540540542,
2027
+ "grad_norm": 0.0715257003903389,
2028
+ "learning_rate": 6.689189189189189e-05,
2029
+ "loss": 0.0037,
2030
+ "step": 11500
2031
+ },
2032
+ {
2033
+ "epoch": 156.0,
2034
+ "eval_loss": 3.933366298675537,
2035
+ "eval_rouge1": 0.49233799907987563,
2036
+ "eval_rouge2": 0.3965013420598218,
2037
+ "eval_rougeL": 0.47174545806545665,
2038
+ "eval_rougeLsum": 0.47602740740299954,
2039
+ "eval_runtime": 6.8977,
2040
+ "eval_samples_per_second": 9.278,
2041
+ "eval_steps_per_second": 2.32,
2042
+ "step": 11544
2043
+ },
2044
+ {
2045
+ "epoch": 157.0,
2046
+ "eval_loss": 3.9453284740448,
2047
+ "eval_rouge1": 0.4935660910336177,
2048
+ "eval_rouge2": 0.3957963732927968,
2049
+ "eval_rougeL": 0.47177139453079964,
2050
+ "eval_rougeLsum": 0.4755186608753167,
2051
+ "eval_runtime": 6.7823,
2052
+ "eval_samples_per_second": 9.436,
2053
+ "eval_steps_per_second": 2.359,
2054
+ "step": 11618
2055
+ },
2056
+ {
2057
+ "epoch": 158.0,
2058
+ "eval_loss": 3.9491419792175293,
2059
+ "eval_rouge1": 0.4930742424700606,
2060
+ "eval_rouge2": 0.39526285411169537,
2061
+ "eval_rougeL": 0.4719829435372723,
2062
+ "eval_rougeLsum": 0.4759326109467592,
2063
+ "eval_runtime": 6.8284,
2064
+ "eval_samples_per_second": 9.373,
2065
+ "eval_steps_per_second": 2.343,
2066
+ "step": 11692
2067
+ },
2068
+ {
2069
+ "epoch": 159.0,
2070
+ "eval_loss": 3.953434467315674,
2071
+ "eval_rouge1": 0.49316892275094,
2072
+ "eval_rouge2": 0.3964291062584909,
2073
+ "eval_rougeL": 0.4720610975684992,
2074
+ "eval_rougeLsum": 0.47604465153214315,
2075
+ "eval_runtime": 7.0341,
2076
+ "eval_samples_per_second": 9.099,
2077
+ "eval_steps_per_second": 2.275,
2078
+ "step": 11766
2079
+ },
2080
+ {
2081
+ "epoch": 160.0,
2082
+ "eval_loss": 3.961452007293701,
2083
+ "eval_rouge1": 0.49376119479297864,
2084
+ "eval_rouge2": 0.39647298452806135,
2085
+ "eval_rougeL": 0.47232622651544753,
2086
+ "eval_rougeLsum": 0.476869743899335,
2087
+ "eval_runtime": 7.0864,
2088
+ "eval_samples_per_second": 9.031,
2089
+ "eval_steps_per_second": 2.258,
2090
+ "step": 11840
2091
+ },
2092
+ {
2093
+ "epoch": 161.0,
2094
+ "eval_loss": 3.974522113800049,
2095
+ "eval_rouge1": 0.49152727212946457,
2096
+ "eval_rouge2": 0.3953004424504709,
2097
+ "eval_rougeL": 0.47023604272642827,
2098
+ "eval_rougeLsum": 0.4732774227264972,
2099
+ "eval_runtime": 7.4592,
2100
+ "eval_samples_per_second": 8.58,
2101
+ "eval_steps_per_second": 2.145,
2102
+ "step": 11914
2103
+ },
2104
+ {
2105
+ "epoch": 162.0,
2106
+ "eval_loss": 3.979368209838867,
2107
+ "eval_rouge1": 0.49210496109014745,
2108
+ "eval_rouge2": 0.3957612104808744,
2109
+ "eval_rougeL": 0.47146803881202126,
2110
+ "eval_rougeLsum": 0.4751965635581662,
2111
+ "eval_runtime": 7.5133,
2112
+ "eval_samples_per_second": 8.518,
2113
+ "eval_steps_per_second": 2.13,
2114
+ "step": 11988
2115
+ },
2116
+ {
2117
+ "epoch": 162.16216216216216,
2118
+ "grad_norm": 0.020755620673298836,
2119
+ "learning_rate": 5.6756756756756757e-05,
2120
+ "loss": 0.0033,
2121
+ "step": 12000
2122
+ },
2123
+ {
2124
+ "epoch": 163.0,
2125
+ "eval_loss": 3.9921233654022217,
2126
+ "eval_rouge1": 0.4960050950060007,
2127
+ "eval_rouge2": 0.39999937852342404,
2128
+ "eval_rougeL": 0.4755213708113314,
2129
+ "eval_rougeLsum": 0.4795628358236831,
2130
+ "eval_runtime": 6.9003,
2131
+ "eval_samples_per_second": 9.275,
2132
+ "eval_steps_per_second": 2.319,
2133
+ "step": 12062
2134
+ },
2135
+ {
2136
+ "epoch": 164.0,
2137
+ "eval_loss": 4.0162272453308105,
2138
+ "eval_rouge1": 0.492801394287687,
2139
+ "eval_rouge2": 0.397442056436076,
2140
+ "eval_rougeL": 0.47103266304177527,
2141
+ "eval_rougeLsum": 0.4748829924767563,
2142
+ "eval_runtime": 6.8719,
2143
+ "eval_samples_per_second": 9.313,
2144
+ "eval_steps_per_second": 2.328,
2145
+ "step": 12136
2146
+ },
2147
+ {
2148
+ "epoch": 165.0,
2149
+ "eval_loss": 3.996596097946167,
2150
+ "eval_rouge1": 0.49315466512445916,
2151
+ "eval_rouge2": 0.3985964076994628,
2152
+ "eval_rougeL": 0.4735840963826083,
2153
+ "eval_rougeLsum": 0.47858269202555725,
2154
+ "eval_runtime": 6.9342,
2155
+ "eval_samples_per_second": 9.23,
2156
+ "eval_steps_per_second": 2.307,
2157
+ "step": 12210
2158
+ },
2159
+ {
2160
+ "epoch": 166.0,
2161
+ "eval_loss": 3.995129108428955,
2162
+ "eval_rouge1": 0.4941258909094296,
2163
+ "eval_rouge2": 0.4015187340990569,
2164
+ "eval_rougeL": 0.4758513247728338,
2165
+ "eval_rougeLsum": 0.4789241505191637,
2166
+ "eval_runtime": 7.3809,
2167
+ "eval_samples_per_second": 8.671,
2168
+ "eval_steps_per_second": 2.168,
2169
+ "step": 12284
2170
+ },
2171
+ {
2172
+ "epoch": 167.0,
2173
+ "eval_loss": 4.009509086608887,
2174
+ "eval_rouge1": 0.4946445747494288,
2175
+ "eval_rouge2": 0.40202139316604324,
2176
+ "eval_rougeL": 0.4773328124627762,
2177
+ "eval_rougeLsum": 0.48067203669273695,
2178
+ "eval_runtime": 7.3061,
2179
+ "eval_samples_per_second": 8.76,
2180
+ "eval_steps_per_second": 2.19,
2181
+ "step": 12358
2182
+ },
2183
+ {
2184
+ "epoch": 168.0,
2185
+ "eval_loss": 4.0200018882751465,
2186
+ "eval_rouge1": 0.4927259103544268,
2187
+ "eval_rouge2": 0.40104825000910027,
2188
+ "eval_rougeL": 0.4735139731424237,
2189
+ "eval_rougeLsum": 0.4756183913048333,
2190
+ "eval_runtime": 7.5103,
2191
+ "eval_samples_per_second": 8.522,
2192
+ "eval_steps_per_second": 2.13,
2193
+ "step": 12432
2194
+ },
2195
+ {
2196
+ "epoch": 168.9189189189189,
2197
+ "grad_norm": 1.5782980918884277,
2198
+ "learning_rate": 4.6621621621621615e-05,
2199
+ "loss": 0.0034,
2200
+ "step": 12500
2201
+ },
2202
+ {
2203
+ "epoch": 169.0,
2204
+ "eval_loss": 4.012574195861816,
2205
+ "eval_rouge1": 0.496091078807664,
2206
+ "eval_rouge2": 0.40862976551688035,
2207
+ "eval_rougeL": 0.48006706521844855,
2208
+ "eval_rougeLsum": 0.48333388286468126,
2209
+ "eval_runtime": 6.7294,
2210
+ "eval_samples_per_second": 9.51,
2211
+ "eval_steps_per_second": 2.378,
2212
+ "step": 12506
2213
+ },
2214
+ {
2215
+ "epoch": 170.0,
2216
+ "eval_loss": 3.999107837677002,
2217
+ "eval_rouge1": 0.4945963719889479,
2218
+ "eval_rouge2": 0.40532127010917274,
2219
+ "eval_rougeL": 0.4757107170560549,
2220
+ "eval_rougeLsum": 0.47802150685708367,
2221
+ "eval_runtime": 6.9002,
2222
+ "eval_samples_per_second": 9.275,
2223
+ "eval_steps_per_second": 2.319,
2224
+ "step": 12580
2225
+ },
2226
+ {
2227
+ "epoch": 171.0,
2228
+ "eval_loss": 3.990157127380371,
2229
+ "eval_rouge1": 0.4970906257094063,
2230
+ "eval_rouge2": 0.40441572257587777,
2231
+ "eval_rougeL": 0.4763034913242958,
2232
+ "eval_rougeLsum": 0.48003172600357014,
2233
+ "eval_runtime": 7.1185,
2234
+ "eval_samples_per_second": 8.991,
2235
+ "eval_steps_per_second": 2.248,
2236
+ "step": 12654
2237
+ },
2238
+ {
2239
+ "epoch": 172.0,
2240
+ "eval_loss": 3.9884870052337646,
2241
+ "eval_rouge1": 0.4919713054717275,
2242
+ "eval_rouge2": 0.3978217334671761,
2243
+ "eval_rougeL": 0.4717472188768614,
2244
+ "eval_rougeLsum": 0.4752567984418149,
2245
+ "eval_runtime": 7.2011,
2246
+ "eval_samples_per_second": 8.888,
2247
+ "eval_steps_per_second": 2.222,
2248
+ "step": 12728
2249
+ },
2250
+ {
2251
+ "epoch": 173.0,
2252
+ "eval_loss": 3.995528221130371,
2253
+ "eval_rouge1": 0.4892295390230387,
2254
+ "eval_rouge2": 0.39245630150338084,
2255
+ "eval_rougeL": 0.46800971679320924,
2256
+ "eval_rougeLsum": 0.47172263652645663,
2257
+ "eval_runtime": 7.3505,
2258
+ "eval_samples_per_second": 8.707,
2259
+ "eval_steps_per_second": 2.177,
2260
+ "step": 12802
2261
+ },
2262
+ {
2263
+ "epoch": 174.0,
2264
+ "eval_loss": 3.9886558055877686,
2265
+ "eval_rouge1": 0.49254486459338476,
2266
+ "eval_rouge2": 0.3977283376888407,
2267
+ "eval_rougeL": 0.4719540790713239,
2268
+ "eval_rougeLsum": 0.4761202466533264,
2269
+ "eval_runtime": 7.5746,
2270
+ "eval_samples_per_second": 8.449,
2271
+ "eval_steps_per_second": 2.112,
2272
+ "step": 12876
2273
+ },
2274
+ {
2275
+ "epoch": 175.0,
2276
+ "eval_loss": 3.9935975074768066,
2277
+ "eval_rouge1": 0.49184767087274567,
2278
+ "eval_rouge2": 0.39517761703169657,
2279
+ "eval_rougeL": 0.47011431582517893,
2280
+ "eval_rougeLsum": 0.47482326137378367,
2281
+ "eval_runtime": 7.3613,
2282
+ "eval_samples_per_second": 8.694,
2283
+ "eval_steps_per_second": 2.174,
2284
+ "step": 12950
2285
+ },
2286
+ {
2287
+ "epoch": 175.67567567567568,
2288
+ "grad_norm": 0.21789249777793884,
2289
+ "learning_rate": 3.648648648648649e-05,
2290
+ "loss": 0.0031,
2291
+ "step": 13000
2292
+ },
2293
+ {
2294
+ "epoch": 176.0,
2295
+ "eval_loss": 3.991879463195801,
2296
+ "eval_rouge1": 0.49436064822903425,
2297
+ "eval_rouge2": 0.3983319755827057,
2298
+ "eval_rougeL": 0.47423185319254557,
2299
+ "eval_rougeLsum": 0.47939931586363027,
2300
+ "eval_runtime": 6.0616,
2301
+ "eval_samples_per_second": 10.558,
2302
+ "eval_steps_per_second": 2.64,
2303
+ "step": 13024
2304
+ },
2305
+ {
2306
+ "epoch": 177.0,
2307
+ "eval_loss": 3.9859113693237305,
2308
+ "eval_rouge1": 0.49493023202648,
2309
+ "eval_rouge2": 0.39876076391867105,
2310
+ "eval_rougeL": 0.47502603733194293,
2311
+ "eval_rougeLsum": 0.47979135340843765,
2312
+ "eval_runtime": 6.0337,
2313
+ "eval_samples_per_second": 10.607,
2314
+ "eval_steps_per_second": 2.652,
2315
+ "step": 13098
2316
+ },
2317
+ {
2318
+ "epoch": 178.0,
2319
+ "eval_loss": 3.9933767318725586,
2320
+ "eval_rouge1": 0.49395800948427726,
2321
+ "eval_rouge2": 0.39853734308250965,
2322
+ "eval_rougeL": 0.47430798111549466,
2323
+ "eval_rougeLsum": 0.4783243132851581,
2324
+ "eval_runtime": 6.3858,
2325
+ "eval_samples_per_second": 10.022,
2326
+ "eval_steps_per_second": 2.506,
2327
+ "step": 13172
2328
+ },
2329
+ {
2330
+ "epoch": 179.0,
2331
+ "eval_loss": 3.9931554794311523,
2332
+ "eval_rouge1": 0.49238304957658807,
2333
+ "eval_rouge2": 0.3963583838874407,
2334
+ "eval_rougeL": 0.47174238658414747,
2335
+ "eval_rougeLsum": 0.4753519409810264,
2336
+ "eval_runtime": 6.735,
2337
+ "eval_samples_per_second": 9.503,
2338
+ "eval_steps_per_second": 2.376,
2339
+ "step": 13246
2340
+ },
2341
+ {
2342
+ "epoch": 180.0,
2343
+ "eval_loss": 3.9880971908569336,
2344
+ "eval_rouge1": 0.49080560963978376,
2345
+ "eval_rouge2": 0.3972907788541582,
2346
+ "eval_rougeL": 0.47184356604760724,
2347
+ "eval_rougeLsum": 0.47466334337431604,
2348
+ "eval_runtime": 6.7997,
2349
+ "eval_samples_per_second": 9.412,
2350
+ "eval_steps_per_second": 2.353,
2351
+ "step": 13320
2352
+ },
2353
+ {
2354
+ "epoch": 181.0,
2355
+ "eval_loss": 3.9810729026794434,
2356
+ "eval_rouge1": 0.4901453996617402,
2357
+ "eval_rouge2": 0.39677107201508166,
2358
+ "eval_rougeL": 0.4703169982341144,
2359
+ "eval_rougeLsum": 0.4731671717016933,
2360
+ "eval_runtime": 6.7854,
2361
+ "eval_samples_per_second": 9.432,
2362
+ "eval_steps_per_second": 2.358,
2363
+ "step": 13394
2364
+ },
2365
+ {
2366
+ "epoch": 182.0,
2367
+ "eval_loss": 3.96390438079834,
2368
+ "eval_rouge1": 0.4904213027490153,
2369
+ "eval_rouge2": 0.39702370328662856,
2370
+ "eval_rougeL": 0.4721674656812758,
2371
+ "eval_rougeLsum": 0.47478324364675517,
2372
+ "eval_runtime": 6.8084,
2373
+ "eval_samples_per_second": 9.4,
2374
+ "eval_steps_per_second": 2.35,
2375
+ "step": 13468
2376
+ },
2377
+ {
2378
+ "epoch": 182.43243243243242,
2379
+ "grad_norm": 0.0035254976246505976,
2380
+ "learning_rate": 2.635135135135135e-05,
2381
+ "loss": 0.0028,
2382
+ "step": 13500
2383
+ },
2384
+ {
2385
+ "epoch": 183.0,
2386
+ "eval_loss": 3.9630651473999023,
2387
+ "eval_rouge1": 0.49176793094985966,
2388
+ "eval_rouge2": 0.3982124661120756,
2389
+ "eval_rougeL": 0.4739900352741334,
2390
+ "eval_rougeLsum": 0.4772889228039448,
2391
+ "eval_runtime": 6.7422,
2392
+ "eval_samples_per_second": 9.492,
2393
+ "eval_steps_per_second": 2.373,
2394
+ "step": 13542
2395
+ },
2396
+ {
2397
+ "epoch": 184.0,
2398
+ "eval_loss": 3.9613349437713623,
2399
+ "eval_rouge1": 0.49252377109539347,
2400
+ "eval_rouge2": 0.3991753353796805,
2401
+ "eval_rougeL": 0.4744207046904064,
2402
+ "eval_rougeLsum": 0.47843050814235677,
2403
+ "eval_runtime": 6.7346,
2404
+ "eval_samples_per_second": 9.503,
2405
+ "eval_steps_per_second": 2.376,
2406
+ "step": 13616
2407
+ },
2408
+ {
2409
+ "epoch": 185.0,
2410
+ "eval_loss": 3.966508388519287,
2411
+ "eval_rouge1": 0.49176793094985966,
2412
+ "eval_rouge2": 0.3982124661120756,
2413
+ "eval_rougeL": 0.4739900352741334,
2414
+ "eval_rougeLsum": 0.4772889228039448,
2415
+ "eval_runtime": 6.6765,
2416
+ "eval_samples_per_second": 9.586,
2417
+ "eval_steps_per_second": 2.396,
2418
+ "step": 13690
2419
+ },
2420
+ {
2421
+ "epoch": 186.0,
2422
+ "eval_loss": 3.969733715057373,
2423
+ "eval_rouge1": 0.49176793094985966,
2424
+ "eval_rouge2": 0.3982124661120756,
2425
+ "eval_rougeL": 0.4739900352741334,
2426
+ "eval_rougeLsum": 0.4772889228039448,
2427
+ "eval_runtime": 6.8824,
2428
+ "eval_samples_per_second": 9.299,
2429
+ "eval_steps_per_second": 2.325,
2430
+ "step": 13764
2431
+ },
2432
+ {
2433
+ "epoch": 187.0,
2434
+ "eval_loss": 3.9655680656433105,
2435
+ "eval_rouge1": 0.49176793094985966,
2436
+ "eval_rouge2": 0.3982124661120756,
2437
+ "eval_rougeL": 0.4739900352741334,
2438
+ "eval_rougeLsum": 0.4772889228039448,
2439
+ "eval_runtime": 6.9789,
2440
+ "eval_samples_per_second": 9.171,
2441
+ "eval_steps_per_second": 2.293,
2442
+ "step": 13838
2443
+ },
2444
+ {
2445
+ "epoch": 188.0,
2446
+ "eval_loss": 3.9675371646881104,
2447
+ "eval_rouge1": 0.4914535390216627,
2448
+ "eval_rouge2": 0.3996949212212493,
2449
+ "eval_rougeL": 0.4750270162479517,
2450
+ "eval_rougeLsum": 0.4774780484281064,
2451
+ "eval_runtime": 7.1278,
2452
+ "eval_samples_per_second": 8.979,
2453
+ "eval_steps_per_second": 2.245,
2454
+ "step": 13912
2455
+ },
2456
+ {
2457
+ "epoch": 189.0,
2458
+ "eval_loss": 3.9671735763549805,
2459
+ "eval_rouge1": 0.49101134475679165,
2460
+ "eval_rouge2": 0.3999416033500164,
2461
+ "eval_rougeL": 0.4751983641524803,
2462
+ "eval_rougeLsum": 0.47761184908243365,
2463
+ "eval_runtime": 7.124,
2464
+ "eval_samples_per_second": 8.984,
2465
+ "eval_steps_per_second": 2.246,
2466
+ "step": 13986
2467
+ },
2468
+ {
2469
+ "epoch": 189.1891891891892,
2470
+ "grad_norm": 0.15321534872055054,
2471
+ "learning_rate": 1.6216216216216215e-05,
2472
+ "loss": 0.0024,
2473
+ "step": 14000
2474
+ },
2475
+ {
2476
+ "epoch": 190.0,
2477
+ "eval_loss": 3.972198247909546,
2478
+ "eval_rouge1": 0.4905979152260983,
2479
+ "eval_rouge2": 0.39955164941074106,
2480
+ "eval_rougeL": 0.47344604392249445,
2481
+ "eval_rougeLsum": 0.4759329738829975,
2482
+ "eval_runtime": 6.8599,
2483
+ "eval_samples_per_second": 9.33,
2484
+ "eval_steps_per_second": 2.332,
2485
+ "step": 14060
2486
+ },
2487
+ {
2488
+ "epoch": 191.0,
2489
+ "eval_loss": 3.975025177001953,
2490
+ "eval_rouge1": 0.48977979873226074,
2491
+ "eval_rouge2": 0.39813641187525384,
2492
+ "eval_rougeL": 0.47230893585406847,
2493
+ "eval_rougeLsum": 0.4744688749010165,
2494
+ "eval_runtime": 6.6509,
2495
+ "eval_samples_per_second": 9.623,
2496
+ "eval_steps_per_second": 2.406,
2497
+ "step": 14134
2498
+ },
2499
+ {
2500
+ "epoch": 192.0,
2501
+ "eval_loss": 3.9795103073120117,
2502
+ "eval_rouge1": 0.49039895176345305,
2503
+ "eval_rouge2": 0.39799884117083045,
2504
+ "eval_rougeL": 0.4728926726233008,
2505
+ "eval_rougeLsum": 0.47550506244557705,
2506
+ "eval_runtime": 6.8712,
2507
+ "eval_samples_per_second": 9.314,
2508
+ "eval_steps_per_second": 2.329,
2509
+ "step": 14208
2510
+ },
2511
+ {
2512
+ "epoch": 193.0,
2513
+ "eval_loss": 3.986283779144287,
2514
+ "eval_rouge1": 0.49102244746843426,
2515
+ "eval_rouge2": 0.39766661670510695,
2516
+ "eval_rougeL": 0.4725552556797792,
2517
+ "eval_rougeLsum": 0.47528011781656265,
2518
+ "eval_runtime": 6.931,
2519
+ "eval_samples_per_second": 9.234,
2520
+ "eval_steps_per_second": 2.308,
2521
+ "step": 14282
2522
+ },
2523
+ {
2524
+ "epoch": 194.0,
2525
+ "eval_loss": 3.9892172813415527,
2526
+ "eval_rouge1": 0.49118213868467275,
2527
+ "eval_rouge2": 0.3980678792543486,
2528
+ "eval_rougeL": 0.47411330411282765,
2529
+ "eval_rougeLsum": 0.4774810833024574,
2530
+ "eval_runtime": 7.2851,
2531
+ "eval_samples_per_second": 8.785,
2532
+ "eval_steps_per_second": 2.196,
2533
+ "step": 14356
2534
+ },
2535
+ {
2536
+ "epoch": 195.0,
2537
+ "eval_loss": 3.9919543266296387,
2538
+ "eval_rouge1": 0.49206363424277105,
2539
+ "eval_rouge2": 0.39957530399636887,
2540
+ "eval_rougeL": 0.4753350412755837,
2541
+ "eval_rougeLsum": 0.47857260255176703,
2542
+ "eval_runtime": 7.1661,
2543
+ "eval_samples_per_second": 8.931,
2544
+ "eval_steps_per_second": 2.233,
2545
+ "step": 14430
2546
+ },
2547
+ {
2548
+ "epoch": 195.94594594594594,
2549
+ "grad_norm": 0.06605270504951477,
2550
+ "learning_rate": 6.081081081081081e-06,
2551
+ "loss": 0.0019,
2552
+ "step": 14500
2553
+ }
2554
+ ],
2555
+ "logging_steps": 500,
2556
+ "max_steps": 14800,
2557
+ "num_input_tokens_seen": 0,
2558
+ "num_train_epochs": 200,
2559
+ "save_steps": 500,
2560
+ "stateful_callbacks": {
2561
+ "TrainerControl": {
2562
+ "args": {
2563
+ "should_epoch_stop": false,
2564
+ "should_evaluate": false,
2565
+ "should_log": false,
2566
+ "should_save": true,
2567
+ "should_training_stop": false
2568
+ },
2569
+ "attributes": {}
2570
+ }
2571
+ },
2572
+ "total_flos": 158281179463680.0,
2573
+ "train_batch_size": 2,
2574
+ "trial_name": null,
2575
+ "trial_params": null
2576
+ }
results/checkpoint-14500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a42ec5404b2e8ac8f2f4376a8da0b5e09eb82c54628966bc74fc83bbb71250d
3
+ size 5304
results/checkpoint-14800/added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }
results/checkpoint-14800/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.44.2",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
results/checkpoint-14800/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": "4.44.2"
6
+ }
results/checkpoint-14800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bf73349534de30721a42d24bc66a629bc646b09da7937aadfdc9221e54ba52
3
+ size 242041896
results/checkpoint-14800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d99c7c4f9a4d1f2555dc0a2e695489fd001b457fb643d62d087b8f8e5e191d2
3
+ size 484163514
results/checkpoint-14800/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd460366f4ae7a120eede9207a4f327f7a4c2520c1bbe47a356a5a43d4d8cce
3
+ size 14244
results/checkpoint-14800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72dadb051af1cc61fa18d4ab2f7cc76ad8ed8335c4682999017968c1da8feb26
3
+ size 1064
results/checkpoint-14800/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
+ }
results/checkpoint-14800/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
results/checkpoint-14800/tokenizer_config.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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": true,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "legacy": true,
935
+ "model_max_length": 512,
936
+ "pad_token": "<pad>",
937
+ "sp_model_kwargs": {},
938
+ "tokenizer_class": "T5Tokenizer",
939
+ "unk_token": "<unk>"
940
+ }