kavyamanohar commited on
Commit
bc749f7
1 Parent(s): 01da5eb

Training in progress, step 500

Browse files
added_tokens.json CHANGED
@@ -1518,6 +1518,7 @@
1518
  "<|da|>": 50285,
1519
  "<|de|>": 50261,
1520
  "<|el|>": 50281,
 
1521
  "<|en|>": 50259,
1522
  "<|es|>": 50262,
1523
  "<|et|>": 50307,
 
1518
  "<|da|>": 50285,
1519
  "<|de|>": 50261,
1520
  "<|el|>": 50281,
1521
+ "<|endoftext|>": 50257,
1522
  "<|en|>": 50259,
1523
  "<|es|>": 50262,
1524
  "<|et|>": 50307,
config.json CHANGED
@@ -145,7 +145,7 @@
145
  50362
146
  ],
147
  "torch_dtype": "float32",
148
- "transformers_version": "4.33.3",
149
  "use_cache": false,
150
  "use_weighted_layer_sum": false,
151
  "vocab_size": 51865
 
145
  50362
146
  ],
147
  "torch_dtype": "float32",
148
+ "transformers_version": "4.34.0",
149
  "use_cache": false,
150
  "use_weighted_layer_sum": false,
151
  "vocab_size": 51865
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17c9574ff2b03a12db1679e0bed9c65ff6068b34d6f77e369cd76cabf043a515
3
  size 967102729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88b4e6fd56edb66d3dfaf523c28f1be79f265c44a482898d1294ebb1e2a00a7f
3
  size 967102729
special_tokens_map.json CHANGED
@@ -108,26 +108,8 @@
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": "<|endoftext|>",
126
- "unk_token": {
127
- "content": "<|endoftext|>",
128
- "lstrip": false,
129
- "normalized": true,
130
- "rstrip": false,
131
- "single_word": false
132
- }
133
  }
 
108
  "<|nocaptions|>",
109
  "<|notimestamps|>"
110
  ],
111
+ "bos_token": "<|endoftext|>",
112
+ "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
113
  "pad_token": "<|endoftext|>",
114
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
115
  }
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 sha256:5782ee54d539c5289781d19db5a7f7dfca3e1530443925ae17cf14a09017e997
3
- size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2da9ce6885f48bf337baa57854ee53029e43040a05c36cc91ecc2b88d1bcba8
3
+ size 4283