JanLilan commited on
Commit
5951387
1 Parent(s): a170a3a

Training in progress, step 500

Browse files
added_tokens.json CHANGED
@@ -1518,7 +1518,6 @@
1518
  "<|da|>": 50285,
1519
  "<|de|>": 50261,
1520
  "<|el|>": 50281,
1521
- "<|endoftext|>": 50257,
1522
  "<|en|>": 50259,
1523
  "<|es|>": 50262,
1524
  "<|et|>": 50307,
 
1518
  "<|da|>": 50285,
1519
  "<|de|>": 50261,
1520
  "<|el|>": 50281,
 
1521
  "<|en|>": 50259,
1522
  "<|es|>": 50262,
1523
  "<|et|>": 50307,
config.json CHANGED
@@ -147,7 +147,7 @@
147
  50362
148
  ],
149
  "torch_dtype": "float32",
150
- "transformers_version": "4.34.0",
151
  "use_cache": false,
152
  "use_weighted_layer_sum": false,
153
  "vocab_size": 51865
 
147
  50362
148
  ],
149
  "torch_dtype": "float32",
150
+ "transformers_version": "4.34.1",
151
  "use_cache": false,
152
  "use_weighted_layer_sum": false,
153
  "vocab_size": 51865
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ccb51281f310d272a27940c19f679d182084d73e2c0af9ada7d47c931109c3f
3
- size 151099049
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f1f9625fa886d9328f0765ba9fbd285e2b42724e53aad9e65f42bcbd215d3d
3
+ size 151099494
special_tokens_map.json CHANGED
@@ -108,8 +108,32 @@
108
  "<|nocaptions|>",
109
  "<|notimestamps|>"
110
  ],
111
- "bos_token": "<|endoftext|>",
112
- "eos_token": "<|endoftext|>",
113
- "pad_token": "<|endoftext|>",
114
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
115
  }
 
108
  "<|nocaptions|>",
109
  "<|notimestamps|>"
110
  ],
111
+ "bos_token": {
112
+ "content": "<|endoftext|>",
113
+ "lstrip": false,
114
+ "normalized": true,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "eos_token": {
119
+ "content": "<|endoftext|>",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "pad_token": {
126
+ "content": "<|endoftext|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false
131
+ },
132
+ "unk_token": {
133
+ "content": "<|endoftext|>",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false
138
+ }
139
  }
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:678265b45759dfbcba115eaee5c17325c2917e3492ac3fb88ed826aed2756b74
3
- size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f29c6e74f0d580a7358523c7477cd77c33abd9690511e6bf8f258477e1b30f
3
+ size 4664