pranay-j commited on
Commit
ea1d89a
·
1 Parent(s): 5153b52

Training in progress, step 300

Browse files
fine-tune-whisper-streaming.ipynb CHANGED
@@ -876,8 +876,8 @@
876
  "\n",
877
  " <div>\n",
878
  " \n",
879
- " <progress value='151' max='300' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
880
- " [151/300 45:50 < 45:50, 0.05 it/s, Epoch 21.01/9223372036854775807]\n",
881
  " </div>\n",
882
  " <table border=\"1\" class=\"dataframe\">\n",
883
  " <thead>\n",
@@ -885,9 +885,22 @@
885
  " <th>Step</th>\n",
886
  " <th>Training Loss</th>\n",
887
  " <th>Validation Loss</th>\n",
 
888
  " </tr>\n",
889
  " </thead>\n",
890
  " <tbody>\n",
 
 
 
 
 
 
 
 
 
 
 
 
891
  " </tbody>\n",
892
  "</table><p>"
893
  ],
@@ -3185,7 +3198,2491 @@
3185
  " \"transformers_version\": \"4.26.0.dev0\",\n",
3186
  " \"use_cache\": false\n",
3187
  "}\n",
3188
- "\n"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3189
  ]
3190
  }
3191
  ],
 
876
  "\n",
877
  " <div>\n",
878
  " \n",
879
+ " <progress value='301' max='300' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
880
+ " [300/300 1:52:52, Epoch 42.02/9223372036854775807]\n",
881
  " </div>\n",
882
  " <table border=\"1\" class=\"dataframe\">\n",
883
  " <thead>\n",
 
885
  " <th>Step</th>\n",
886
  " <th>Training Loss</th>\n",
887
  " <th>Validation Loss</th>\n",
888
+ " <th>Wer</th>\n",
889
  " </tr>\n",
890
  " </thead>\n",
891
  " <tbody>\n",
892
+ " <tr>\n",
893
+ " <td>150</td>\n",
894
+ " <td>0.001200</td>\n",
895
+ " <td>0.521087</td>\n",
896
+ " <td>17.284492</td>\n",
897
+ " </tr>\n",
898
+ " <tr>\n",
899
+ " <td>300</td>\n",
900
+ " <td>0.000600</td>\n",
901
+ " <td>0.553003</td>\n",
902
+ " <td>17.076113</td>\n",
903
+ " </tr>\n",
904
  " </tbody>\n",
905
  "</table><p>"
906
  ],
 
3198
  " \"transformers_version\": \"4.26.0.dev0\",\n",
3199
  " \"use_cache\": false\n",
3200
  "}\n",
3201
+ "\n",
3202
+ "Generate config GenerationConfig {\n",
3203
+ " \"begin_suppress_tokens\": [\n",
3204
+ " 220,\n",
3205
+ " 50257\n",
3206
+ " ],\n",
3207
+ " \"bos_token_id\": 50257,\n",
3208
+ " \"decoder_start_token_id\": 50258,\n",
3209
+ " \"eos_token_id\": 50257,\n",
3210
+ " \"max_length\": 448,\n",
3211
+ " \"pad_token_id\": 50257,\n",
3212
+ " \"suppress_tokens\": [],\n",
3213
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3214
+ " \"use_cache\": false\n",
3215
+ "}\n",
3216
+ "\n",
3217
+ "Generate config GenerationConfig {\n",
3218
+ " \"begin_suppress_tokens\": [\n",
3219
+ " 220,\n",
3220
+ " 50257\n",
3221
+ " ],\n",
3222
+ " \"bos_token_id\": 50257,\n",
3223
+ " \"decoder_start_token_id\": 50258,\n",
3224
+ " \"eos_token_id\": 50257,\n",
3225
+ " \"max_length\": 448,\n",
3226
+ " \"pad_token_id\": 50257,\n",
3227
+ " \"suppress_tokens\": [],\n",
3228
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3229
+ " \"use_cache\": false\n",
3230
+ "}\n",
3231
+ "\n",
3232
+ "Generate config GenerationConfig {\n",
3233
+ " \"begin_suppress_tokens\": [\n",
3234
+ " 220,\n",
3235
+ " 50257\n",
3236
+ " ],\n",
3237
+ " \"bos_token_id\": 50257,\n",
3238
+ " \"decoder_start_token_id\": 50258,\n",
3239
+ " \"eos_token_id\": 50257,\n",
3240
+ " \"max_length\": 448,\n",
3241
+ " \"pad_token_id\": 50257,\n",
3242
+ " \"suppress_tokens\": [],\n",
3243
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3244
+ " \"use_cache\": false\n",
3245
+ "}\n",
3246
+ "\n",
3247
+ "Generate config GenerationConfig {\n",
3248
+ " \"begin_suppress_tokens\": [\n",
3249
+ " 220,\n",
3250
+ " 50257\n",
3251
+ " ],\n",
3252
+ " \"bos_token_id\": 50257,\n",
3253
+ " \"decoder_start_token_id\": 50258,\n",
3254
+ " \"eos_token_id\": 50257,\n",
3255
+ " \"max_length\": 448,\n",
3256
+ " \"pad_token_id\": 50257,\n",
3257
+ " \"suppress_tokens\": [],\n",
3258
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3259
+ " \"use_cache\": false\n",
3260
+ "}\n",
3261
+ "\n",
3262
+ "Generate config GenerationConfig {\n",
3263
+ " \"begin_suppress_tokens\": [\n",
3264
+ " 220,\n",
3265
+ " 50257\n",
3266
+ " ],\n",
3267
+ " \"bos_token_id\": 50257,\n",
3268
+ " \"decoder_start_token_id\": 50258,\n",
3269
+ " \"eos_token_id\": 50257,\n",
3270
+ " \"max_length\": 448,\n",
3271
+ " \"pad_token_id\": 50257,\n",
3272
+ " \"suppress_tokens\": [],\n",
3273
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3274
+ " \"use_cache\": false\n",
3275
+ "}\n",
3276
+ "\n",
3277
+ "Generate config GenerationConfig {\n",
3278
+ " \"begin_suppress_tokens\": [\n",
3279
+ " 220,\n",
3280
+ " 50257\n",
3281
+ " ],\n",
3282
+ " \"bos_token_id\": 50257,\n",
3283
+ " \"decoder_start_token_id\": 50258,\n",
3284
+ " \"eos_token_id\": 50257,\n",
3285
+ " \"max_length\": 448,\n",
3286
+ " \"pad_token_id\": 50257,\n",
3287
+ " \"suppress_tokens\": [],\n",
3288
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3289
+ " \"use_cache\": false\n",
3290
+ "}\n",
3291
+ "\n",
3292
+ "Saving model checkpoint to ./checkpoint-150\n",
3293
+ "Configuration saved in ./checkpoint-150/config.json\n",
3294
+ "Model weights saved in ./checkpoint-150/pytorch_model.bin\n",
3295
+ "Feature extractor saved in ./checkpoint-150/preprocessor_config.json\n",
3296
+ "tokenizer config file saved in ./checkpoint-150/tokenizer_config.json\n",
3297
+ "Special tokens file saved in ./checkpoint-150/special_tokens_map.json\n",
3298
+ "added tokens file saved in ./checkpoint-150/added_tokens.json\n",
3299
+ "Feature extractor saved in ./preprocessor_config.json\n",
3300
+ "tokenizer config file saved in ./tokenizer_config.json\n",
3301
+ "Special tokens file saved in ./special_tokens_map.json\n",
3302
+ "added tokens file saved in ./added_tokens.json\n",
3303
+ "Reading metadata...: 2525it [00:00, 5299.13it/s]\n",
3304
+ "Reading metadata...: 248it [00:00, 674.70it/s]\n",
3305
+ "Reading metadata...: 2525it [00:00, 18192.65it/s]\n",
3306
+ "Reading metadata...: 248it [00:00, 2914.68it/s]\n",
3307
+ "Reading metadata...: 2525it [00:00, 18553.34it/s]\n",
3308
+ "Reading metadata...: 248it [00:00, 3145.02it/s]\n",
3309
+ "Reading metadata...: 2525it [00:00, 18650.41it/s]\n",
3310
+ "Reading metadata...: 248it [00:00, 3177.52it/s]\n",
3311
+ "Reading metadata...: 2525it [00:00, 18610.82it/s]\n",
3312
+ "Reading metadata...: 248it [00:00, 3219.77it/s]\n",
3313
+ "Reading metadata...: 2525it [00:00, 18229.36it/s]\n",
3314
+ "Reading metadata...: 248it [00:00, 3035.93it/s]\n",
3315
+ "Reading metadata...: 2525it [00:00, 18677.84it/s]\n",
3316
+ "Reading metadata...: 248it [00:00, 3148.13it/s]\n",
3317
+ "Reading metadata...: 2525it [00:00, 18547.30it/s]\n",
3318
+ "Reading metadata...: 248it [00:00, 2511.22it/s]\n",
3319
+ "Reading metadata...: 2525it [00:00, 18500.90it/s]\n",
3320
+ "Reading metadata...: 248it [00:00, 3115.06it/s]\n",
3321
+ "Reading metadata...: 2525it [00:00, 18777.36it/s]\n",
3322
+ "Reading metadata...: 248it [00:00, 3136.69it/s]\n",
3323
+ "Reading metadata...: 2525it [00:00, 19017.50it/s]\n",
3324
+ "Reading metadata...: 248it [00:00, 3192.30it/s]\n",
3325
+ "Reading metadata...: 2525it [00:00, 18471.66it/s]\n",
3326
+ "Reading metadata...: 248it [00:00, 3133.50it/s]\n",
3327
+ "Reading metadata...: 2525it [00:00, 18826.63it/s]\n",
3328
+ "Reading metadata...: 248it [00:00, 3148.82it/s]\n",
3329
+ "Reading metadata...: 2525it [00:00, 18456.57it/s]\n",
3330
+ "Reading metadata...: 248it [00:00, 3145.37it/s]\n",
3331
+ "Reading metadata...: 2525it [00:00, 18577.55it/s]\n",
3332
+ "Reading metadata...: 248it [00:00, 3212.87it/s]\n",
3333
+ "Reading metadata...: 2525it [00:00, 18556.85it/s]\n",
3334
+ "Reading metadata...: 248it [00:00, 3144.32it/s]\n",
3335
+ "Reading metadata...: 2525it [00:00, 18747.38it/s]\n",
3336
+ "Reading metadata...: 248it [00:00, 3111.55it/s]\n",
3337
+ "Reading metadata...: 2525it [00:00, 18911.24it/s]\n",
3338
+ "Reading metadata...: 248it [00:00, 3137.81it/s]\n",
3339
+ "Reading metadata...: 2525it [00:00, 18753.85it/s]\n",
3340
+ "Reading metadata...: 248it [00:00, 3171.22it/s]\n",
3341
+ "Reading metadata...: 2525it [00:00, 13683.85it/s]\n",
3342
+ "Reading metadata...: 248it [00:00, 3214.06it/s]\n",
3343
+ "Reading metadata...: 2525it [00:00, 18924.08it/s]\n",
3344
+ "Reading metadata...: 248it [00:00, 3215.36it/s]\n",
3345
+ "***** Running Evaluation *****\n",
3346
+ " Num examples: Unknown\n",
3347
+ " Batch size = 8\n",
3348
+ "Reading metadata...: 1237it [00:00, 10723.62it/s]\n",
3349
+ "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
3350
+ "Generate config GenerationConfig {\n",
3351
+ " \"begin_suppress_tokens\": [\n",
3352
+ " 220,\n",
3353
+ " 50257\n",
3354
+ " ],\n",
3355
+ " \"bos_token_id\": 50257,\n",
3356
+ " \"decoder_start_token_id\": 50258,\n",
3357
+ " \"eos_token_id\": 50257,\n",
3358
+ " \"max_length\": 448,\n",
3359
+ " \"pad_token_id\": 50257,\n",
3360
+ " \"suppress_tokens\": [],\n",
3361
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3362
+ " \"use_cache\": false\n",
3363
+ "}\n",
3364
+ "\n",
3365
+ "Generate config GenerationConfig {\n",
3366
+ " \"begin_suppress_tokens\": [\n",
3367
+ " 220,\n",
3368
+ " 50257\n",
3369
+ " ],\n",
3370
+ " \"bos_token_id\": 50257,\n",
3371
+ " \"decoder_start_token_id\": 50258,\n",
3372
+ " \"eos_token_id\": 50257,\n",
3373
+ " \"max_length\": 448,\n",
3374
+ " \"pad_token_id\": 50257,\n",
3375
+ " \"suppress_tokens\": [],\n",
3376
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3377
+ " \"use_cache\": false\n",
3378
+ "}\n",
3379
+ "\n",
3380
+ "Generate config GenerationConfig {\n",
3381
+ " \"begin_suppress_tokens\": [\n",
3382
+ " 220,\n",
3383
+ " 50257\n",
3384
+ " ],\n",
3385
+ " \"bos_token_id\": 50257,\n",
3386
+ " \"decoder_start_token_id\": 50258,\n",
3387
+ " \"eos_token_id\": 50257,\n",
3388
+ " \"max_length\": 448,\n",
3389
+ " \"pad_token_id\": 50257,\n",
3390
+ " \"suppress_tokens\": [],\n",
3391
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3392
+ " \"use_cache\": false\n",
3393
+ "}\n",
3394
+ "\n",
3395
+ "Generate config GenerationConfig {\n",
3396
+ " \"begin_suppress_tokens\": [\n",
3397
+ " 220,\n",
3398
+ " 50257\n",
3399
+ " ],\n",
3400
+ " \"bos_token_id\": 50257,\n",
3401
+ " \"decoder_start_token_id\": 50258,\n",
3402
+ " \"eos_token_id\": 50257,\n",
3403
+ " \"max_length\": 448,\n",
3404
+ " \"pad_token_id\": 50257,\n",
3405
+ " \"suppress_tokens\": [],\n",
3406
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3407
+ " \"use_cache\": false\n",
3408
+ "}\n",
3409
+ "\n",
3410
+ "Generate config GenerationConfig {\n",
3411
+ " \"begin_suppress_tokens\": [\n",
3412
+ " 220,\n",
3413
+ " 50257\n",
3414
+ " ],\n",
3415
+ " \"bos_token_id\": 50257,\n",
3416
+ " \"decoder_start_token_id\": 50258,\n",
3417
+ " \"eos_token_id\": 50257,\n",
3418
+ " \"max_length\": 448,\n",
3419
+ " \"pad_token_id\": 50257,\n",
3420
+ " \"suppress_tokens\": [],\n",
3421
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3422
+ " \"use_cache\": false\n",
3423
+ "}\n",
3424
+ "\n",
3425
+ "Generate config GenerationConfig {\n",
3426
+ " \"begin_suppress_tokens\": [\n",
3427
+ " 220,\n",
3428
+ " 50257\n",
3429
+ " ],\n",
3430
+ " \"bos_token_id\": 50257,\n",
3431
+ " \"decoder_start_token_id\": 50258,\n",
3432
+ " \"eos_token_id\": 50257,\n",
3433
+ " \"max_length\": 448,\n",
3434
+ " \"pad_token_id\": 50257,\n",
3435
+ " \"suppress_tokens\": [],\n",
3436
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3437
+ " \"use_cache\": false\n",
3438
+ "}\n",
3439
+ "\n",
3440
+ "Generate config GenerationConfig {\n",
3441
+ " \"begin_suppress_tokens\": [\n",
3442
+ " 220,\n",
3443
+ " 50257\n",
3444
+ " ],\n",
3445
+ " \"bos_token_id\": 50257,\n",
3446
+ " \"decoder_start_token_id\": 50258,\n",
3447
+ " \"eos_token_id\": 50257,\n",
3448
+ " \"max_length\": 448,\n",
3449
+ " \"pad_token_id\": 50257,\n",
3450
+ " \"suppress_tokens\": [],\n",
3451
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3452
+ " \"use_cache\": false\n",
3453
+ "}\n",
3454
+ "\n",
3455
+ "Generate config GenerationConfig {\n",
3456
+ " \"begin_suppress_tokens\": [\n",
3457
+ " 220,\n",
3458
+ " 50257\n",
3459
+ " ],\n",
3460
+ " \"bos_token_id\": 50257,\n",
3461
+ " \"decoder_start_token_id\": 50258,\n",
3462
+ " \"eos_token_id\": 50257,\n",
3463
+ " \"max_length\": 448,\n",
3464
+ " \"pad_token_id\": 50257,\n",
3465
+ " \"suppress_tokens\": [],\n",
3466
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3467
+ " \"use_cache\": false\n",
3468
+ "}\n",
3469
+ "\n",
3470
+ "Generate config GenerationConfig {\n",
3471
+ " \"begin_suppress_tokens\": [\n",
3472
+ " 220,\n",
3473
+ " 50257\n",
3474
+ " ],\n",
3475
+ " \"bos_token_id\": 50257,\n",
3476
+ " \"decoder_start_token_id\": 50258,\n",
3477
+ " \"eos_token_id\": 50257,\n",
3478
+ " \"max_length\": 448,\n",
3479
+ " \"pad_token_id\": 50257,\n",
3480
+ " \"suppress_tokens\": [],\n",
3481
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3482
+ " \"use_cache\": false\n",
3483
+ "}\n",
3484
+ "\n",
3485
+ "Generate config GenerationConfig {\n",
3486
+ " \"begin_suppress_tokens\": [\n",
3487
+ " 220,\n",
3488
+ " 50257\n",
3489
+ " ],\n",
3490
+ " \"bos_token_id\": 50257,\n",
3491
+ " \"decoder_start_token_id\": 50258,\n",
3492
+ " \"eos_token_id\": 50257,\n",
3493
+ " \"max_length\": 448,\n",
3494
+ " \"pad_token_id\": 50257,\n",
3495
+ " \"suppress_tokens\": [],\n",
3496
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3497
+ " \"use_cache\": false\n",
3498
+ "}\n",
3499
+ "\n",
3500
+ "Generate config GenerationConfig {\n",
3501
+ " \"begin_suppress_tokens\": [\n",
3502
+ " 220,\n",
3503
+ " 50257\n",
3504
+ " ],\n",
3505
+ " \"bos_token_id\": 50257,\n",
3506
+ " \"decoder_start_token_id\": 50258,\n",
3507
+ " \"eos_token_id\": 50257,\n",
3508
+ " \"max_length\": 448,\n",
3509
+ " \"pad_token_id\": 50257,\n",
3510
+ " \"suppress_tokens\": [],\n",
3511
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3512
+ " \"use_cache\": false\n",
3513
+ "}\n",
3514
+ "\n",
3515
+ "Generate config GenerationConfig {\n",
3516
+ " \"begin_suppress_tokens\": [\n",
3517
+ " 220,\n",
3518
+ " 50257\n",
3519
+ " ],\n",
3520
+ " \"bos_token_id\": 50257,\n",
3521
+ " \"decoder_start_token_id\": 50258,\n",
3522
+ " \"eos_token_id\": 50257,\n",
3523
+ " \"max_length\": 448,\n",
3524
+ " \"pad_token_id\": 50257,\n",
3525
+ " \"suppress_tokens\": [],\n",
3526
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3527
+ " \"use_cache\": false\n",
3528
+ "}\n",
3529
+ "\n",
3530
+ "Generate config GenerationConfig {\n",
3531
+ " \"begin_suppress_tokens\": [\n",
3532
+ " 220,\n",
3533
+ " 50257\n",
3534
+ " ],\n",
3535
+ " \"bos_token_id\": 50257,\n",
3536
+ " \"decoder_start_token_id\": 50258,\n",
3537
+ " \"eos_token_id\": 50257,\n",
3538
+ " \"max_length\": 448,\n",
3539
+ " \"pad_token_id\": 50257,\n",
3540
+ " \"suppress_tokens\": [],\n",
3541
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3542
+ " \"use_cache\": false\n",
3543
+ "}\n",
3544
+ "\n",
3545
+ "Generate config GenerationConfig {\n",
3546
+ " \"begin_suppress_tokens\": [\n",
3547
+ " 220,\n",
3548
+ " 50257\n",
3549
+ " ],\n",
3550
+ " \"bos_token_id\": 50257,\n",
3551
+ " \"decoder_start_token_id\": 50258,\n",
3552
+ " \"eos_token_id\": 50257,\n",
3553
+ " \"max_length\": 448,\n",
3554
+ " \"pad_token_id\": 50257,\n",
3555
+ " \"suppress_tokens\": [],\n",
3556
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3557
+ " \"use_cache\": false\n",
3558
+ "}\n",
3559
+ "\n",
3560
+ "Generate config GenerationConfig {\n",
3561
+ " \"begin_suppress_tokens\": [\n",
3562
+ " 220,\n",
3563
+ " 50257\n",
3564
+ " ],\n",
3565
+ " \"bos_token_id\": 50257,\n",
3566
+ " \"decoder_start_token_id\": 50258,\n",
3567
+ " \"eos_token_id\": 50257,\n",
3568
+ " \"max_length\": 448,\n",
3569
+ " \"pad_token_id\": 50257,\n",
3570
+ " \"suppress_tokens\": [],\n",
3571
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3572
+ " \"use_cache\": false\n",
3573
+ "}\n",
3574
+ "\n",
3575
+ "Generate config GenerationConfig {\n",
3576
+ " \"begin_suppress_tokens\": [\n",
3577
+ " 220,\n",
3578
+ " 50257\n",
3579
+ " ],\n",
3580
+ " \"bos_token_id\": 50257,\n",
3581
+ " \"decoder_start_token_id\": 50258,\n",
3582
+ " \"eos_token_id\": 50257,\n",
3583
+ " \"max_length\": 448,\n",
3584
+ " \"pad_token_id\": 50257,\n",
3585
+ " \"suppress_tokens\": [],\n",
3586
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3587
+ " \"use_cache\": false\n",
3588
+ "}\n",
3589
+ "\n",
3590
+ "Generate config GenerationConfig {\n",
3591
+ " \"begin_suppress_tokens\": [\n",
3592
+ " 220,\n",
3593
+ " 50257\n",
3594
+ " ],\n",
3595
+ " \"bos_token_id\": 50257,\n",
3596
+ " \"decoder_start_token_id\": 50258,\n",
3597
+ " \"eos_token_id\": 50257,\n",
3598
+ " \"max_length\": 448,\n",
3599
+ " \"pad_token_id\": 50257,\n",
3600
+ " \"suppress_tokens\": [],\n",
3601
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3602
+ " \"use_cache\": false\n",
3603
+ "}\n",
3604
+ "\n",
3605
+ "Generate config GenerationConfig {\n",
3606
+ " \"begin_suppress_tokens\": [\n",
3607
+ " 220,\n",
3608
+ " 50257\n",
3609
+ " ],\n",
3610
+ " \"bos_token_id\": 50257,\n",
3611
+ " \"decoder_start_token_id\": 50258,\n",
3612
+ " \"eos_token_id\": 50257,\n",
3613
+ " \"max_length\": 448,\n",
3614
+ " \"pad_token_id\": 50257,\n",
3615
+ " \"suppress_tokens\": [],\n",
3616
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3617
+ " \"use_cache\": false\n",
3618
+ "}\n",
3619
+ "\n",
3620
+ "Generate config GenerationConfig {\n",
3621
+ " \"begin_suppress_tokens\": [\n",
3622
+ " 220,\n",
3623
+ " 50257\n",
3624
+ " ],\n",
3625
+ " \"bos_token_id\": 50257,\n",
3626
+ " \"decoder_start_token_id\": 50258,\n",
3627
+ " \"eos_token_id\": 50257,\n",
3628
+ " \"max_length\": 448,\n",
3629
+ " \"pad_token_id\": 50257,\n",
3630
+ " \"suppress_tokens\": [],\n",
3631
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3632
+ " \"use_cache\": false\n",
3633
+ "}\n",
3634
+ "\n",
3635
+ "Generate config GenerationConfig {\n",
3636
+ " \"begin_suppress_tokens\": [\n",
3637
+ " 220,\n",
3638
+ " 50257\n",
3639
+ " ],\n",
3640
+ " \"bos_token_id\": 50257,\n",
3641
+ " \"decoder_start_token_id\": 50258,\n",
3642
+ " \"eos_token_id\": 50257,\n",
3643
+ " \"max_length\": 448,\n",
3644
+ " \"pad_token_id\": 50257,\n",
3645
+ " \"suppress_tokens\": [],\n",
3646
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3647
+ " \"use_cache\": false\n",
3648
+ "}\n",
3649
+ "\n",
3650
+ "Generate config GenerationConfig {\n",
3651
+ " \"begin_suppress_tokens\": [\n",
3652
+ " 220,\n",
3653
+ " 50257\n",
3654
+ " ],\n",
3655
+ " \"bos_token_id\": 50257,\n",
3656
+ " \"decoder_start_token_id\": 50258,\n",
3657
+ " \"eos_token_id\": 50257,\n",
3658
+ " \"max_length\": 448,\n",
3659
+ " \"pad_token_id\": 50257,\n",
3660
+ " \"suppress_tokens\": [],\n",
3661
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3662
+ " \"use_cache\": false\n",
3663
+ "}\n",
3664
+ "\n",
3665
+ "Generate config GenerationConfig {\n",
3666
+ " \"begin_suppress_tokens\": [\n",
3667
+ " 220,\n",
3668
+ " 50257\n",
3669
+ " ],\n",
3670
+ " \"bos_token_id\": 50257,\n",
3671
+ " \"decoder_start_token_id\": 50258,\n",
3672
+ " \"eos_token_id\": 50257,\n",
3673
+ " \"max_length\": 448,\n",
3674
+ " \"pad_token_id\": 50257,\n",
3675
+ " \"suppress_tokens\": [],\n",
3676
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3677
+ " \"use_cache\": false\n",
3678
+ "}\n",
3679
+ "\n",
3680
+ "Generate config GenerationConfig {\n",
3681
+ " \"begin_suppress_tokens\": [\n",
3682
+ " 220,\n",
3683
+ " 50257\n",
3684
+ " ],\n",
3685
+ " \"bos_token_id\": 50257,\n",
3686
+ " \"decoder_start_token_id\": 50258,\n",
3687
+ " \"eos_token_id\": 50257,\n",
3688
+ " \"max_length\": 448,\n",
3689
+ " \"pad_token_id\": 50257,\n",
3690
+ " \"suppress_tokens\": [],\n",
3691
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3692
+ " \"use_cache\": false\n",
3693
+ "}\n",
3694
+ "\n",
3695
+ "Generate config GenerationConfig {\n",
3696
+ " \"begin_suppress_tokens\": [\n",
3697
+ " 220,\n",
3698
+ " 50257\n",
3699
+ " ],\n",
3700
+ " \"bos_token_id\": 50257,\n",
3701
+ " \"decoder_start_token_id\": 50258,\n",
3702
+ " \"eos_token_id\": 50257,\n",
3703
+ " \"max_length\": 448,\n",
3704
+ " \"pad_token_id\": 50257,\n",
3705
+ " \"suppress_tokens\": [],\n",
3706
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3707
+ " \"use_cache\": false\n",
3708
+ "}\n",
3709
+ "\n",
3710
+ "Generate config GenerationConfig {\n",
3711
+ " \"begin_suppress_tokens\": [\n",
3712
+ " 220,\n",
3713
+ " 50257\n",
3714
+ " ],\n",
3715
+ " \"bos_token_id\": 50257,\n",
3716
+ " \"decoder_start_token_id\": 50258,\n",
3717
+ " \"eos_token_id\": 50257,\n",
3718
+ " \"max_length\": 448,\n",
3719
+ " \"pad_token_id\": 50257,\n",
3720
+ " \"suppress_tokens\": [],\n",
3721
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3722
+ " \"use_cache\": false\n",
3723
+ "}\n",
3724
+ "\n",
3725
+ "Generate config GenerationConfig {\n",
3726
+ " \"begin_suppress_tokens\": [\n",
3727
+ " 220,\n",
3728
+ " 50257\n",
3729
+ " ],\n",
3730
+ " \"bos_token_id\": 50257,\n",
3731
+ " \"decoder_start_token_id\": 50258,\n",
3732
+ " \"eos_token_id\": 50257,\n",
3733
+ " \"max_length\": 448,\n",
3734
+ " \"pad_token_id\": 50257,\n",
3735
+ " \"suppress_tokens\": [],\n",
3736
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3737
+ " \"use_cache\": false\n",
3738
+ "}\n",
3739
+ "\n",
3740
+ "Generate config GenerationConfig {\n",
3741
+ " \"begin_suppress_tokens\": [\n",
3742
+ " 220,\n",
3743
+ " 50257\n",
3744
+ " ],\n",
3745
+ " \"bos_token_id\": 50257,\n",
3746
+ " \"decoder_start_token_id\": 50258,\n",
3747
+ " \"eos_token_id\": 50257,\n",
3748
+ " \"max_length\": 448,\n",
3749
+ " \"pad_token_id\": 50257,\n",
3750
+ " \"suppress_tokens\": [],\n",
3751
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3752
+ " \"use_cache\": false\n",
3753
+ "}\n",
3754
+ "\n",
3755
+ "Generate config GenerationConfig {\n",
3756
+ " \"begin_suppress_tokens\": [\n",
3757
+ " 220,\n",
3758
+ " 50257\n",
3759
+ " ],\n",
3760
+ " \"bos_token_id\": 50257,\n",
3761
+ " \"decoder_start_token_id\": 50258,\n",
3762
+ " \"eos_token_id\": 50257,\n",
3763
+ " \"max_length\": 448,\n",
3764
+ " \"pad_token_id\": 50257,\n",
3765
+ " \"suppress_tokens\": [],\n",
3766
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3767
+ " \"use_cache\": false\n",
3768
+ "}\n",
3769
+ "\n",
3770
+ "Generate config GenerationConfig {\n",
3771
+ " \"begin_suppress_tokens\": [\n",
3772
+ " 220,\n",
3773
+ " 50257\n",
3774
+ " ],\n",
3775
+ " \"bos_token_id\": 50257,\n",
3776
+ " \"decoder_start_token_id\": 50258,\n",
3777
+ " \"eos_token_id\": 50257,\n",
3778
+ " \"max_length\": 448,\n",
3779
+ " \"pad_token_id\": 50257,\n",
3780
+ " \"suppress_tokens\": [],\n",
3781
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3782
+ " \"use_cache\": false\n",
3783
+ "}\n",
3784
+ "\n",
3785
+ "Generate config GenerationConfig {\n",
3786
+ " \"begin_suppress_tokens\": [\n",
3787
+ " 220,\n",
3788
+ " 50257\n",
3789
+ " ],\n",
3790
+ " \"bos_token_id\": 50257,\n",
3791
+ " \"decoder_start_token_id\": 50258,\n",
3792
+ " \"eos_token_id\": 50257,\n",
3793
+ " \"max_length\": 448,\n",
3794
+ " \"pad_token_id\": 50257,\n",
3795
+ " \"suppress_tokens\": [],\n",
3796
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3797
+ " \"use_cache\": false\n",
3798
+ "}\n",
3799
+ "\n",
3800
+ "Generate config GenerationConfig {\n",
3801
+ " \"begin_suppress_tokens\": [\n",
3802
+ " 220,\n",
3803
+ " 50257\n",
3804
+ " ],\n",
3805
+ " \"bos_token_id\": 50257,\n",
3806
+ " \"decoder_start_token_id\": 50258,\n",
3807
+ " \"eos_token_id\": 50257,\n",
3808
+ " \"max_length\": 448,\n",
3809
+ " \"pad_token_id\": 50257,\n",
3810
+ " \"suppress_tokens\": [],\n",
3811
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3812
+ " \"use_cache\": false\n",
3813
+ "}\n",
3814
+ "\n",
3815
+ "Generate config GenerationConfig {\n",
3816
+ " \"begin_suppress_tokens\": [\n",
3817
+ " 220,\n",
3818
+ " 50257\n",
3819
+ " ],\n",
3820
+ " \"bos_token_id\": 50257,\n",
3821
+ " \"decoder_start_token_id\": 50258,\n",
3822
+ " \"eos_token_id\": 50257,\n",
3823
+ " \"max_length\": 448,\n",
3824
+ " \"pad_token_id\": 50257,\n",
3825
+ " \"suppress_tokens\": [],\n",
3826
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3827
+ " \"use_cache\": false\n",
3828
+ "}\n",
3829
+ "\n",
3830
+ "Generate config GenerationConfig {\n",
3831
+ " \"begin_suppress_tokens\": [\n",
3832
+ " 220,\n",
3833
+ " 50257\n",
3834
+ " ],\n",
3835
+ " \"bos_token_id\": 50257,\n",
3836
+ " \"decoder_start_token_id\": 50258,\n",
3837
+ " \"eos_token_id\": 50257,\n",
3838
+ " \"max_length\": 448,\n",
3839
+ " \"pad_token_id\": 50257,\n",
3840
+ " \"suppress_tokens\": [],\n",
3841
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3842
+ " \"use_cache\": false\n",
3843
+ "}\n",
3844
+ "\n",
3845
+ "Generate config GenerationConfig {\n",
3846
+ " \"begin_suppress_tokens\": [\n",
3847
+ " 220,\n",
3848
+ " 50257\n",
3849
+ " ],\n",
3850
+ " \"bos_token_id\": 50257,\n",
3851
+ " \"decoder_start_token_id\": 50258,\n",
3852
+ " \"eos_token_id\": 50257,\n",
3853
+ " \"max_length\": 448,\n",
3854
+ " \"pad_token_id\": 50257,\n",
3855
+ " \"suppress_tokens\": [],\n",
3856
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3857
+ " \"use_cache\": false\n",
3858
+ "}\n",
3859
+ "\n",
3860
+ "Generate config GenerationConfig {\n",
3861
+ " \"begin_suppress_tokens\": [\n",
3862
+ " 220,\n",
3863
+ " 50257\n",
3864
+ " ],\n",
3865
+ " \"bos_token_id\": 50257,\n",
3866
+ " \"decoder_start_token_id\": 50258,\n",
3867
+ " \"eos_token_id\": 50257,\n",
3868
+ " \"max_length\": 448,\n",
3869
+ " \"pad_token_id\": 50257,\n",
3870
+ " \"suppress_tokens\": [],\n",
3871
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3872
+ " \"use_cache\": false\n",
3873
+ "}\n",
3874
+ "\n",
3875
+ "Generate config GenerationConfig {\n",
3876
+ " \"begin_suppress_tokens\": [\n",
3877
+ " 220,\n",
3878
+ " 50257\n",
3879
+ " ],\n",
3880
+ " \"bos_token_id\": 50257,\n",
3881
+ " \"decoder_start_token_id\": 50258,\n",
3882
+ " \"eos_token_id\": 50257,\n",
3883
+ " \"max_length\": 448,\n",
3884
+ " \"pad_token_id\": 50257,\n",
3885
+ " \"suppress_tokens\": [],\n",
3886
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3887
+ " \"use_cache\": false\n",
3888
+ "}\n",
3889
+ "\n",
3890
+ "Generate config GenerationConfig {\n",
3891
+ " \"begin_suppress_tokens\": [\n",
3892
+ " 220,\n",
3893
+ " 50257\n",
3894
+ " ],\n",
3895
+ " \"bos_token_id\": 50257,\n",
3896
+ " \"decoder_start_token_id\": 50258,\n",
3897
+ " \"eos_token_id\": 50257,\n",
3898
+ " \"max_length\": 448,\n",
3899
+ " \"pad_token_id\": 50257,\n",
3900
+ " \"suppress_tokens\": [],\n",
3901
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3902
+ " \"use_cache\": false\n",
3903
+ "}\n",
3904
+ "\n",
3905
+ "Generate config GenerationConfig {\n",
3906
+ " \"begin_suppress_tokens\": [\n",
3907
+ " 220,\n",
3908
+ " 50257\n",
3909
+ " ],\n",
3910
+ " \"bos_token_id\": 50257,\n",
3911
+ " \"decoder_start_token_id\": 50258,\n",
3912
+ " \"eos_token_id\": 50257,\n",
3913
+ " \"max_length\": 448,\n",
3914
+ " \"pad_token_id\": 50257,\n",
3915
+ " \"suppress_tokens\": [],\n",
3916
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3917
+ " \"use_cache\": false\n",
3918
+ "}\n",
3919
+ "\n",
3920
+ "Generate config GenerationConfig {\n",
3921
+ " \"begin_suppress_tokens\": [\n",
3922
+ " 220,\n",
3923
+ " 50257\n",
3924
+ " ],\n",
3925
+ " \"bos_token_id\": 50257,\n",
3926
+ " \"decoder_start_token_id\": 50258,\n",
3927
+ " \"eos_token_id\": 50257,\n",
3928
+ " \"max_length\": 448,\n",
3929
+ " \"pad_token_id\": 50257,\n",
3930
+ " \"suppress_tokens\": [],\n",
3931
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3932
+ " \"use_cache\": false\n",
3933
+ "}\n",
3934
+ "\n",
3935
+ "Generate config GenerationConfig {\n",
3936
+ " \"begin_suppress_tokens\": [\n",
3937
+ " 220,\n",
3938
+ " 50257\n",
3939
+ " ],\n",
3940
+ " \"bos_token_id\": 50257,\n",
3941
+ " \"decoder_start_token_id\": 50258,\n",
3942
+ " \"eos_token_id\": 50257,\n",
3943
+ " \"max_length\": 448,\n",
3944
+ " \"pad_token_id\": 50257,\n",
3945
+ " \"suppress_tokens\": [],\n",
3946
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3947
+ " \"use_cache\": false\n",
3948
+ "}\n",
3949
+ "\n",
3950
+ "Generate config GenerationConfig {\n",
3951
+ " \"begin_suppress_tokens\": [\n",
3952
+ " 220,\n",
3953
+ " 50257\n",
3954
+ " ],\n",
3955
+ " \"bos_token_id\": 50257,\n",
3956
+ " \"decoder_start_token_id\": 50258,\n",
3957
+ " \"eos_token_id\": 50257,\n",
3958
+ " \"max_length\": 448,\n",
3959
+ " \"pad_token_id\": 50257,\n",
3960
+ " \"suppress_tokens\": [],\n",
3961
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3962
+ " \"use_cache\": false\n",
3963
+ "}\n",
3964
+ "\n",
3965
+ "Generate config GenerationConfig {\n",
3966
+ " \"begin_suppress_tokens\": [\n",
3967
+ " 220,\n",
3968
+ " 50257\n",
3969
+ " ],\n",
3970
+ " \"bos_token_id\": 50257,\n",
3971
+ " \"decoder_start_token_id\": 50258,\n",
3972
+ " \"eos_token_id\": 50257,\n",
3973
+ " \"max_length\": 448,\n",
3974
+ " \"pad_token_id\": 50257,\n",
3975
+ " \"suppress_tokens\": [],\n",
3976
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3977
+ " \"use_cache\": false\n",
3978
+ "}\n",
3979
+ "\n",
3980
+ "Generate config GenerationConfig {\n",
3981
+ " \"begin_suppress_tokens\": [\n",
3982
+ " 220,\n",
3983
+ " 50257\n",
3984
+ " ],\n",
3985
+ " \"bos_token_id\": 50257,\n",
3986
+ " \"decoder_start_token_id\": 50258,\n",
3987
+ " \"eos_token_id\": 50257,\n",
3988
+ " \"max_length\": 448,\n",
3989
+ " \"pad_token_id\": 50257,\n",
3990
+ " \"suppress_tokens\": [],\n",
3991
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
3992
+ " \"use_cache\": false\n",
3993
+ "}\n",
3994
+ "\n",
3995
+ "Generate config GenerationConfig {\n",
3996
+ " \"begin_suppress_tokens\": [\n",
3997
+ " 220,\n",
3998
+ " 50257\n",
3999
+ " ],\n",
4000
+ " \"bos_token_id\": 50257,\n",
4001
+ " \"decoder_start_token_id\": 50258,\n",
4002
+ " \"eos_token_id\": 50257,\n",
4003
+ " \"max_length\": 448,\n",
4004
+ " \"pad_token_id\": 50257,\n",
4005
+ " \"suppress_tokens\": [],\n",
4006
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4007
+ " \"use_cache\": false\n",
4008
+ "}\n",
4009
+ "\n",
4010
+ "Generate config GenerationConfig {\n",
4011
+ " \"begin_suppress_tokens\": [\n",
4012
+ " 220,\n",
4013
+ " 50257\n",
4014
+ " ],\n",
4015
+ " \"bos_token_id\": 50257,\n",
4016
+ " \"decoder_start_token_id\": 50258,\n",
4017
+ " \"eos_token_id\": 50257,\n",
4018
+ " \"max_length\": 448,\n",
4019
+ " \"pad_token_id\": 50257,\n",
4020
+ " \"suppress_tokens\": [],\n",
4021
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4022
+ " \"use_cache\": false\n",
4023
+ "}\n",
4024
+ "\n",
4025
+ "Generate config GenerationConfig {\n",
4026
+ " \"begin_suppress_tokens\": [\n",
4027
+ " 220,\n",
4028
+ " 50257\n",
4029
+ " ],\n",
4030
+ " \"bos_token_id\": 50257,\n",
4031
+ " \"decoder_start_token_id\": 50258,\n",
4032
+ " \"eos_token_id\": 50257,\n",
4033
+ " \"max_length\": 448,\n",
4034
+ " \"pad_token_id\": 50257,\n",
4035
+ " \"suppress_tokens\": [],\n",
4036
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4037
+ " \"use_cache\": false\n",
4038
+ "}\n",
4039
+ "\n",
4040
+ "Generate config GenerationConfig {\n",
4041
+ " \"begin_suppress_tokens\": [\n",
4042
+ " 220,\n",
4043
+ " 50257\n",
4044
+ " ],\n",
4045
+ " \"bos_token_id\": 50257,\n",
4046
+ " \"decoder_start_token_id\": 50258,\n",
4047
+ " \"eos_token_id\": 50257,\n",
4048
+ " \"max_length\": 448,\n",
4049
+ " \"pad_token_id\": 50257,\n",
4050
+ " \"suppress_tokens\": [],\n",
4051
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4052
+ " \"use_cache\": false\n",
4053
+ "}\n",
4054
+ "\n",
4055
+ "Generate config GenerationConfig {\n",
4056
+ " \"begin_suppress_tokens\": [\n",
4057
+ " 220,\n",
4058
+ " 50257\n",
4059
+ " ],\n",
4060
+ " \"bos_token_id\": 50257,\n",
4061
+ " \"decoder_start_token_id\": 50258,\n",
4062
+ " \"eos_token_id\": 50257,\n",
4063
+ " \"max_length\": 448,\n",
4064
+ " \"pad_token_id\": 50257,\n",
4065
+ " \"suppress_tokens\": [],\n",
4066
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4067
+ " \"use_cache\": false\n",
4068
+ "}\n",
4069
+ "\n",
4070
+ "Generate config GenerationConfig {\n",
4071
+ " \"begin_suppress_tokens\": [\n",
4072
+ " 220,\n",
4073
+ " 50257\n",
4074
+ " ],\n",
4075
+ " \"bos_token_id\": 50257,\n",
4076
+ " \"decoder_start_token_id\": 50258,\n",
4077
+ " \"eos_token_id\": 50257,\n",
4078
+ " \"max_length\": 448,\n",
4079
+ " \"pad_token_id\": 50257,\n",
4080
+ " \"suppress_tokens\": [],\n",
4081
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4082
+ " \"use_cache\": false\n",
4083
+ "}\n",
4084
+ "\n",
4085
+ "Generate config GenerationConfig {\n",
4086
+ " \"begin_suppress_tokens\": [\n",
4087
+ " 220,\n",
4088
+ " 50257\n",
4089
+ " ],\n",
4090
+ " \"bos_token_id\": 50257,\n",
4091
+ " \"decoder_start_token_id\": 50258,\n",
4092
+ " \"eos_token_id\": 50257,\n",
4093
+ " \"max_length\": 448,\n",
4094
+ " \"pad_token_id\": 50257,\n",
4095
+ " \"suppress_tokens\": [],\n",
4096
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4097
+ " \"use_cache\": false\n",
4098
+ "}\n",
4099
+ "\n",
4100
+ "Generate config GenerationConfig {\n",
4101
+ " \"begin_suppress_tokens\": [\n",
4102
+ " 220,\n",
4103
+ " 50257\n",
4104
+ " ],\n",
4105
+ " \"bos_token_id\": 50257,\n",
4106
+ " \"decoder_start_token_id\": 50258,\n",
4107
+ " \"eos_token_id\": 50257,\n",
4108
+ " \"max_length\": 448,\n",
4109
+ " \"pad_token_id\": 50257,\n",
4110
+ " \"suppress_tokens\": [],\n",
4111
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4112
+ " \"use_cache\": false\n",
4113
+ "}\n",
4114
+ "\n",
4115
+ "Generate config GenerationConfig {\n",
4116
+ " \"begin_suppress_tokens\": [\n",
4117
+ " 220,\n",
4118
+ " 50257\n",
4119
+ " ],\n",
4120
+ " \"bos_token_id\": 50257,\n",
4121
+ " \"decoder_start_token_id\": 50258,\n",
4122
+ " \"eos_token_id\": 50257,\n",
4123
+ " \"max_length\": 448,\n",
4124
+ " \"pad_token_id\": 50257,\n",
4125
+ " \"suppress_tokens\": [],\n",
4126
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4127
+ " \"use_cache\": false\n",
4128
+ "}\n",
4129
+ "\n",
4130
+ "Generate config GenerationConfig {\n",
4131
+ " \"begin_suppress_tokens\": [\n",
4132
+ " 220,\n",
4133
+ " 50257\n",
4134
+ " ],\n",
4135
+ " \"bos_token_id\": 50257,\n",
4136
+ " \"decoder_start_token_id\": 50258,\n",
4137
+ " \"eos_token_id\": 50257,\n",
4138
+ " \"max_length\": 448,\n",
4139
+ " \"pad_token_id\": 50257,\n",
4140
+ " \"suppress_tokens\": [],\n",
4141
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4142
+ " \"use_cache\": false\n",
4143
+ "}\n",
4144
+ "\n",
4145
+ "Generate config GenerationConfig {\n",
4146
+ " \"begin_suppress_tokens\": [\n",
4147
+ " 220,\n",
4148
+ " 50257\n",
4149
+ " ],\n",
4150
+ " \"bos_token_id\": 50257,\n",
4151
+ " \"decoder_start_token_id\": 50258,\n",
4152
+ " \"eos_token_id\": 50257,\n",
4153
+ " \"max_length\": 448,\n",
4154
+ " \"pad_token_id\": 50257,\n",
4155
+ " \"suppress_tokens\": [],\n",
4156
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4157
+ " \"use_cache\": false\n",
4158
+ "}\n",
4159
+ "\n",
4160
+ "Generate config GenerationConfig {\n",
4161
+ " \"begin_suppress_tokens\": [\n",
4162
+ " 220,\n",
4163
+ " 50257\n",
4164
+ " ],\n",
4165
+ " \"bos_token_id\": 50257,\n",
4166
+ " \"decoder_start_token_id\": 50258,\n",
4167
+ " \"eos_token_id\": 50257,\n",
4168
+ " \"max_length\": 448,\n",
4169
+ " \"pad_token_id\": 50257,\n",
4170
+ " \"suppress_tokens\": [],\n",
4171
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4172
+ " \"use_cache\": false\n",
4173
+ "}\n",
4174
+ "\n",
4175
+ "Generate config GenerationConfig {\n",
4176
+ " \"begin_suppress_tokens\": [\n",
4177
+ " 220,\n",
4178
+ " 50257\n",
4179
+ " ],\n",
4180
+ " \"bos_token_id\": 50257,\n",
4181
+ " \"decoder_start_token_id\": 50258,\n",
4182
+ " \"eos_token_id\": 50257,\n",
4183
+ " \"max_length\": 448,\n",
4184
+ " \"pad_token_id\": 50257,\n",
4185
+ " \"suppress_tokens\": [],\n",
4186
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4187
+ " \"use_cache\": false\n",
4188
+ "}\n",
4189
+ "\n",
4190
+ "Generate config GenerationConfig {\n",
4191
+ " \"begin_suppress_tokens\": [\n",
4192
+ " 220,\n",
4193
+ " 50257\n",
4194
+ " ],\n",
4195
+ " \"bos_token_id\": 50257,\n",
4196
+ " \"decoder_start_token_id\": 50258,\n",
4197
+ " \"eos_token_id\": 50257,\n",
4198
+ " \"max_length\": 448,\n",
4199
+ " \"pad_token_id\": 50257,\n",
4200
+ " \"suppress_tokens\": [],\n",
4201
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4202
+ " \"use_cache\": false\n",
4203
+ "}\n",
4204
+ "\n",
4205
+ "Generate config GenerationConfig {\n",
4206
+ " \"begin_suppress_tokens\": [\n",
4207
+ " 220,\n",
4208
+ " 50257\n",
4209
+ " ],\n",
4210
+ " \"bos_token_id\": 50257,\n",
4211
+ " \"decoder_start_token_id\": 50258,\n",
4212
+ " \"eos_token_id\": 50257,\n",
4213
+ " \"max_length\": 448,\n",
4214
+ " \"pad_token_id\": 50257,\n",
4215
+ " \"suppress_tokens\": [],\n",
4216
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4217
+ " \"use_cache\": false\n",
4218
+ "}\n",
4219
+ "\n",
4220
+ "Generate config GenerationConfig {\n",
4221
+ " \"begin_suppress_tokens\": [\n",
4222
+ " 220,\n",
4223
+ " 50257\n",
4224
+ " ],\n",
4225
+ " \"bos_token_id\": 50257,\n",
4226
+ " \"decoder_start_token_id\": 50258,\n",
4227
+ " \"eos_token_id\": 50257,\n",
4228
+ " \"max_length\": 448,\n",
4229
+ " \"pad_token_id\": 50257,\n",
4230
+ " \"suppress_tokens\": [],\n",
4231
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4232
+ " \"use_cache\": false\n",
4233
+ "}\n",
4234
+ "\n",
4235
+ "Generate config GenerationConfig {\n",
4236
+ " \"begin_suppress_tokens\": [\n",
4237
+ " 220,\n",
4238
+ " 50257\n",
4239
+ " ],\n",
4240
+ " \"bos_token_id\": 50257,\n",
4241
+ " \"decoder_start_token_id\": 50258,\n",
4242
+ " \"eos_token_id\": 50257,\n",
4243
+ " \"max_length\": 448,\n",
4244
+ " \"pad_token_id\": 50257,\n",
4245
+ " \"suppress_tokens\": [],\n",
4246
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4247
+ " \"use_cache\": false\n",
4248
+ "}\n",
4249
+ "\n",
4250
+ "Generate config GenerationConfig {\n",
4251
+ " \"begin_suppress_tokens\": [\n",
4252
+ " 220,\n",
4253
+ " 50257\n",
4254
+ " ],\n",
4255
+ " \"bos_token_id\": 50257,\n",
4256
+ " \"decoder_start_token_id\": 50258,\n",
4257
+ " \"eos_token_id\": 50257,\n",
4258
+ " \"max_length\": 448,\n",
4259
+ " \"pad_token_id\": 50257,\n",
4260
+ " \"suppress_tokens\": [],\n",
4261
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4262
+ " \"use_cache\": false\n",
4263
+ "}\n",
4264
+ "\n",
4265
+ "Generate config GenerationConfig {\n",
4266
+ " \"begin_suppress_tokens\": [\n",
4267
+ " 220,\n",
4268
+ " 50257\n",
4269
+ " ],\n",
4270
+ " \"bos_token_id\": 50257,\n",
4271
+ " \"decoder_start_token_id\": 50258,\n",
4272
+ " \"eos_token_id\": 50257,\n",
4273
+ " \"max_length\": 448,\n",
4274
+ " \"pad_token_id\": 50257,\n",
4275
+ " \"suppress_tokens\": [],\n",
4276
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4277
+ " \"use_cache\": false\n",
4278
+ "}\n",
4279
+ "\n",
4280
+ "Generate config GenerationConfig {\n",
4281
+ " \"begin_suppress_tokens\": [\n",
4282
+ " 220,\n",
4283
+ " 50257\n",
4284
+ " ],\n",
4285
+ " \"bos_token_id\": 50257,\n",
4286
+ " \"decoder_start_token_id\": 50258,\n",
4287
+ " \"eos_token_id\": 50257,\n",
4288
+ " \"max_length\": 448,\n",
4289
+ " \"pad_token_id\": 50257,\n",
4290
+ " \"suppress_tokens\": [],\n",
4291
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4292
+ " \"use_cache\": false\n",
4293
+ "}\n",
4294
+ "\n",
4295
+ "Generate config GenerationConfig {\n",
4296
+ " \"begin_suppress_tokens\": [\n",
4297
+ " 220,\n",
4298
+ " 50257\n",
4299
+ " ],\n",
4300
+ " \"bos_token_id\": 50257,\n",
4301
+ " \"decoder_start_token_id\": 50258,\n",
4302
+ " \"eos_token_id\": 50257,\n",
4303
+ " \"max_length\": 448,\n",
4304
+ " \"pad_token_id\": 50257,\n",
4305
+ " \"suppress_tokens\": [],\n",
4306
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4307
+ " \"use_cache\": false\n",
4308
+ "}\n",
4309
+ "\n",
4310
+ "Generate config GenerationConfig {\n",
4311
+ " \"begin_suppress_tokens\": [\n",
4312
+ " 220,\n",
4313
+ " 50257\n",
4314
+ " ],\n",
4315
+ " \"bos_token_id\": 50257,\n",
4316
+ " \"decoder_start_token_id\": 50258,\n",
4317
+ " \"eos_token_id\": 50257,\n",
4318
+ " \"max_length\": 448,\n",
4319
+ " \"pad_token_id\": 50257,\n",
4320
+ " \"suppress_tokens\": [],\n",
4321
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4322
+ " \"use_cache\": false\n",
4323
+ "}\n",
4324
+ "\n",
4325
+ "Generate config GenerationConfig {\n",
4326
+ " \"begin_suppress_tokens\": [\n",
4327
+ " 220,\n",
4328
+ " 50257\n",
4329
+ " ],\n",
4330
+ " \"bos_token_id\": 50257,\n",
4331
+ " \"decoder_start_token_id\": 50258,\n",
4332
+ " \"eos_token_id\": 50257,\n",
4333
+ " \"max_length\": 448,\n",
4334
+ " \"pad_token_id\": 50257,\n",
4335
+ " \"suppress_tokens\": [],\n",
4336
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4337
+ " \"use_cache\": false\n",
4338
+ "}\n",
4339
+ "\n",
4340
+ "Generate config GenerationConfig {\n",
4341
+ " \"begin_suppress_tokens\": [\n",
4342
+ " 220,\n",
4343
+ " 50257\n",
4344
+ " ],\n",
4345
+ " \"bos_token_id\": 50257,\n",
4346
+ " \"decoder_start_token_id\": 50258,\n",
4347
+ " \"eos_token_id\": 50257,\n",
4348
+ " \"max_length\": 448,\n",
4349
+ " \"pad_token_id\": 50257,\n",
4350
+ " \"suppress_tokens\": [],\n",
4351
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4352
+ " \"use_cache\": false\n",
4353
+ "}\n",
4354
+ "\n",
4355
+ "Generate config GenerationConfig {\n",
4356
+ " \"begin_suppress_tokens\": [\n",
4357
+ " 220,\n",
4358
+ " 50257\n",
4359
+ " ],\n",
4360
+ " \"bos_token_id\": 50257,\n",
4361
+ " \"decoder_start_token_id\": 50258,\n",
4362
+ " \"eos_token_id\": 50257,\n",
4363
+ " \"max_length\": 448,\n",
4364
+ " \"pad_token_id\": 50257,\n",
4365
+ " \"suppress_tokens\": [],\n",
4366
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4367
+ " \"use_cache\": false\n",
4368
+ "}\n",
4369
+ "\n",
4370
+ "Generate config GenerationConfig {\n",
4371
+ " \"begin_suppress_tokens\": [\n",
4372
+ " 220,\n",
4373
+ " 50257\n",
4374
+ " ],\n",
4375
+ " \"bos_token_id\": 50257,\n",
4376
+ " \"decoder_start_token_id\": 50258,\n",
4377
+ " \"eos_token_id\": 50257,\n",
4378
+ " \"max_length\": 448,\n",
4379
+ " \"pad_token_id\": 50257,\n",
4380
+ " \"suppress_tokens\": [],\n",
4381
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4382
+ " \"use_cache\": false\n",
4383
+ "}\n",
4384
+ "\n",
4385
+ "Generate config GenerationConfig {\n",
4386
+ " \"begin_suppress_tokens\": [\n",
4387
+ " 220,\n",
4388
+ " 50257\n",
4389
+ " ],\n",
4390
+ " \"bos_token_id\": 50257,\n",
4391
+ " \"decoder_start_token_id\": 50258,\n",
4392
+ " \"eos_token_id\": 50257,\n",
4393
+ " \"max_length\": 448,\n",
4394
+ " \"pad_token_id\": 50257,\n",
4395
+ " \"suppress_tokens\": [],\n",
4396
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4397
+ " \"use_cache\": false\n",
4398
+ "}\n",
4399
+ "\n",
4400
+ "Generate config GenerationConfig {\n",
4401
+ " \"begin_suppress_tokens\": [\n",
4402
+ " 220,\n",
4403
+ " 50257\n",
4404
+ " ],\n",
4405
+ " \"bos_token_id\": 50257,\n",
4406
+ " \"decoder_start_token_id\": 50258,\n",
4407
+ " \"eos_token_id\": 50257,\n",
4408
+ " \"max_length\": 448,\n",
4409
+ " \"pad_token_id\": 50257,\n",
4410
+ " \"suppress_tokens\": [],\n",
4411
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4412
+ " \"use_cache\": false\n",
4413
+ "}\n",
4414
+ "\n",
4415
+ "Generate config GenerationConfig {\n",
4416
+ " \"begin_suppress_tokens\": [\n",
4417
+ " 220,\n",
4418
+ " 50257\n",
4419
+ " ],\n",
4420
+ " \"bos_token_id\": 50257,\n",
4421
+ " \"decoder_start_token_id\": 50258,\n",
4422
+ " \"eos_token_id\": 50257,\n",
4423
+ " \"max_length\": 448,\n",
4424
+ " \"pad_token_id\": 50257,\n",
4425
+ " \"suppress_tokens\": [],\n",
4426
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4427
+ " \"use_cache\": false\n",
4428
+ "}\n",
4429
+ "\n",
4430
+ "Generate config GenerationConfig {\n",
4431
+ " \"begin_suppress_tokens\": [\n",
4432
+ " 220,\n",
4433
+ " 50257\n",
4434
+ " ],\n",
4435
+ " \"bos_token_id\": 50257,\n",
4436
+ " \"decoder_start_token_id\": 50258,\n",
4437
+ " \"eos_token_id\": 50257,\n",
4438
+ " \"max_length\": 448,\n",
4439
+ " \"pad_token_id\": 50257,\n",
4440
+ " \"suppress_tokens\": [],\n",
4441
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4442
+ " \"use_cache\": false\n",
4443
+ "}\n",
4444
+ "\n",
4445
+ "Generate config GenerationConfig {\n",
4446
+ " \"begin_suppress_tokens\": [\n",
4447
+ " 220,\n",
4448
+ " 50257\n",
4449
+ " ],\n",
4450
+ " \"bos_token_id\": 50257,\n",
4451
+ " \"decoder_start_token_id\": 50258,\n",
4452
+ " \"eos_token_id\": 50257,\n",
4453
+ " \"max_length\": 448,\n",
4454
+ " \"pad_token_id\": 50257,\n",
4455
+ " \"suppress_tokens\": [],\n",
4456
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4457
+ " \"use_cache\": false\n",
4458
+ "}\n",
4459
+ "\n",
4460
+ "Generate config GenerationConfig {\n",
4461
+ " \"begin_suppress_tokens\": [\n",
4462
+ " 220,\n",
4463
+ " 50257\n",
4464
+ " ],\n",
4465
+ " \"bos_token_id\": 50257,\n",
4466
+ " \"decoder_start_token_id\": 50258,\n",
4467
+ " \"eos_token_id\": 50257,\n",
4468
+ " \"max_length\": 448,\n",
4469
+ " \"pad_token_id\": 50257,\n",
4470
+ " \"suppress_tokens\": [],\n",
4471
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4472
+ " \"use_cache\": false\n",
4473
+ "}\n",
4474
+ "\n",
4475
+ "Generate config GenerationConfig {\n",
4476
+ " \"begin_suppress_tokens\": [\n",
4477
+ " 220,\n",
4478
+ " 50257\n",
4479
+ " ],\n",
4480
+ " \"bos_token_id\": 50257,\n",
4481
+ " \"decoder_start_token_id\": 50258,\n",
4482
+ " \"eos_token_id\": 50257,\n",
4483
+ " \"max_length\": 448,\n",
4484
+ " \"pad_token_id\": 50257,\n",
4485
+ " \"suppress_tokens\": [],\n",
4486
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4487
+ " \"use_cache\": false\n",
4488
+ "}\n",
4489
+ "\n",
4490
+ "Generate config GenerationConfig {\n",
4491
+ " \"begin_suppress_tokens\": [\n",
4492
+ " 220,\n",
4493
+ " 50257\n",
4494
+ " ],\n",
4495
+ " \"bos_token_id\": 50257,\n",
4496
+ " \"decoder_start_token_id\": 50258,\n",
4497
+ " \"eos_token_id\": 50257,\n",
4498
+ " \"max_length\": 448,\n",
4499
+ " \"pad_token_id\": 50257,\n",
4500
+ " \"suppress_tokens\": [],\n",
4501
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4502
+ " \"use_cache\": false\n",
4503
+ "}\n",
4504
+ "\n",
4505
+ "Generate config GenerationConfig {\n",
4506
+ " \"begin_suppress_tokens\": [\n",
4507
+ " 220,\n",
4508
+ " 50257\n",
4509
+ " ],\n",
4510
+ " \"bos_token_id\": 50257,\n",
4511
+ " \"decoder_start_token_id\": 50258,\n",
4512
+ " \"eos_token_id\": 50257,\n",
4513
+ " \"max_length\": 448,\n",
4514
+ " \"pad_token_id\": 50257,\n",
4515
+ " \"suppress_tokens\": [],\n",
4516
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4517
+ " \"use_cache\": false\n",
4518
+ "}\n",
4519
+ "\n",
4520
+ "Generate config GenerationConfig {\n",
4521
+ " \"begin_suppress_tokens\": [\n",
4522
+ " 220,\n",
4523
+ " 50257\n",
4524
+ " ],\n",
4525
+ " \"bos_token_id\": 50257,\n",
4526
+ " \"decoder_start_token_id\": 50258,\n",
4527
+ " \"eos_token_id\": 50257,\n",
4528
+ " \"max_length\": 448,\n",
4529
+ " \"pad_token_id\": 50257,\n",
4530
+ " \"suppress_tokens\": [],\n",
4531
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4532
+ " \"use_cache\": false\n",
4533
+ "}\n",
4534
+ "\n",
4535
+ "Generate config GenerationConfig {\n",
4536
+ " \"begin_suppress_tokens\": [\n",
4537
+ " 220,\n",
4538
+ " 50257\n",
4539
+ " ],\n",
4540
+ " \"bos_token_id\": 50257,\n",
4541
+ " \"decoder_start_token_id\": 50258,\n",
4542
+ " \"eos_token_id\": 50257,\n",
4543
+ " \"max_length\": 448,\n",
4544
+ " \"pad_token_id\": 50257,\n",
4545
+ " \"suppress_tokens\": [],\n",
4546
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4547
+ " \"use_cache\": false\n",
4548
+ "}\n",
4549
+ "\n",
4550
+ "Generate config GenerationConfig {\n",
4551
+ " \"begin_suppress_tokens\": [\n",
4552
+ " 220,\n",
4553
+ " 50257\n",
4554
+ " ],\n",
4555
+ " \"bos_token_id\": 50257,\n",
4556
+ " \"decoder_start_token_id\": 50258,\n",
4557
+ " \"eos_token_id\": 50257,\n",
4558
+ " \"max_length\": 448,\n",
4559
+ " \"pad_token_id\": 50257,\n",
4560
+ " \"suppress_tokens\": [],\n",
4561
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4562
+ " \"use_cache\": false\n",
4563
+ "}\n",
4564
+ "\n",
4565
+ "Generate config GenerationConfig {\n",
4566
+ " \"begin_suppress_tokens\": [\n",
4567
+ " 220,\n",
4568
+ " 50257\n",
4569
+ " ],\n",
4570
+ " \"bos_token_id\": 50257,\n",
4571
+ " \"decoder_start_token_id\": 50258,\n",
4572
+ " \"eos_token_id\": 50257,\n",
4573
+ " \"max_length\": 448,\n",
4574
+ " \"pad_token_id\": 50257,\n",
4575
+ " \"suppress_tokens\": [],\n",
4576
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4577
+ " \"use_cache\": false\n",
4578
+ "}\n",
4579
+ "\n",
4580
+ "Generate config GenerationConfig {\n",
4581
+ " \"begin_suppress_tokens\": [\n",
4582
+ " 220,\n",
4583
+ " 50257\n",
4584
+ " ],\n",
4585
+ " \"bos_token_id\": 50257,\n",
4586
+ " \"decoder_start_token_id\": 50258,\n",
4587
+ " \"eos_token_id\": 50257,\n",
4588
+ " \"max_length\": 448,\n",
4589
+ " \"pad_token_id\": 50257,\n",
4590
+ " \"suppress_tokens\": [],\n",
4591
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4592
+ " \"use_cache\": false\n",
4593
+ "}\n",
4594
+ "\n",
4595
+ "Generate config GenerationConfig {\n",
4596
+ " \"begin_suppress_tokens\": [\n",
4597
+ " 220,\n",
4598
+ " 50257\n",
4599
+ " ],\n",
4600
+ " \"bos_token_id\": 50257,\n",
4601
+ " \"decoder_start_token_id\": 50258,\n",
4602
+ " \"eos_token_id\": 50257,\n",
4603
+ " \"max_length\": 448,\n",
4604
+ " \"pad_token_id\": 50257,\n",
4605
+ " \"suppress_tokens\": [],\n",
4606
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4607
+ " \"use_cache\": false\n",
4608
+ "}\n",
4609
+ "\n",
4610
+ "Generate config GenerationConfig {\n",
4611
+ " \"begin_suppress_tokens\": [\n",
4612
+ " 220,\n",
4613
+ " 50257\n",
4614
+ " ],\n",
4615
+ " \"bos_token_id\": 50257,\n",
4616
+ " \"decoder_start_token_id\": 50258,\n",
4617
+ " \"eos_token_id\": 50257,\n",
4618
+ " \"max_length\": 448,\n",
4619
+ " \"pad_token_id\": 50257,\n",
4620
+ " \"suppress_tokens\": [],\n",
4621
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4622
+ " \"use_cache\": false\n",
4623
+ "}\n",
4624
+ "\n",
4625
+ "Generate config GenerationConfig {\n",
4626
+ " \"begin_suppress_tokens\": [\n",
4627
+ " 220,\n",
4628
+ " 50257\n",
4629
+ " ],\n",
4630
+ " \"bos_token_id\": 50257,\n",
4631
+ " \"decoder_start_token_id\": 50258,\n",
4632
+ " \"eos_token_id\": 50257,\n",
4633
+ " \"max_length\": 448,\n",
4634
+ " \"pad_token_id\": 50257,\n",
4635
+ " \"suppress_tokens\": [],\n",
4636
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4637
+ " \"use_cache\": false\n",
4638
+ "}\n",
4639
+ "\n",
4640
+ "Generate config GenerationConfig {\n",
4641
+ " \"begin_suppress_tokens\": [\n",
4642
+ " 220,\n",
4643
+ " 50257\n",
4644
+ " ],\n",
4645
+ " \"bos_token_id\": 50257,\n",
4646
+ " \"decoder_start_token_id\": 50258,\n",
4647
+ " \"eos_token_id\": 50257,\n",
4648
+ " \"max_length\": 448,\n",
4649
+ " \"pad_token_id\": 50257,\n",
4650
+ " \"suppress_tokens\": [],\n",
4651
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4652
+ " \"use_cache\": false\n",
4653
+ "}\n",
4654
+ "\n",
4655
+ "Generate config GenerationConfig {\n",
4656
+ " \"begin_suppress_tokens\": [\n",
4657
+ " 220,\n",
4658
+ " 50257\n",
4659
+ " ],\n",
4660
+ " \"bos_token_id\": 50257,\n",
4661
+ " \"decoder_start_token_id\": 50258,\n",
4662
+ " \"eos_token_id\": 50257,\n",
4663
+ " \"max_length\": 448,\n",
4664
+ " \"pad_token_id\": 50257,\n",
4665
+ " \"suppress_tokens\": [],\n",
4666
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4667
+ " \"use_cache\": false\n",
4668
+ "}\n",
4669
+ "\n",
4670
+ "Generate config GenerationConfig {\n",
4671
+ " \"begin_suppress_tokens\": [\n",
4672
+ " 220,\n",
4673
+ " 50257\n",
4674
+ " ],\n",
4675
+ " \"bos_token_id\": 50257,\n",
4676
+ " \"decoder_start_token_id\": 50258,\n",
4677
+ " \"eos_token_id\": 50257,\n",
4678
+ " \"max_length\": 448,\n",
4679
+ " \"pad_token_id\": 50257,\n",
4680
+ " \"suppress_tokens\": [],\n",
4681
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4682
+ " \"use_cache\": false\n",
4683
+ "}\n",
4684
+ "\n",
4685
+ "Generate config GenerationConfig {\n",
4686
+ " \"begin_suppress_tokens\": [\n",
4687
+ " 220,\n",
4688
+ " 50257\n",
4689
+ " ],\n",
4690
+ " \"bos_token_id\": 50257,\n",
4691
+ " \"decoder_start_token_id\": 50258,\n",
4692
+ " \"eos_token_id\": 50257,\n",
4693
+ " \"max_length\": 448,\n",
4694
+ " \"pad_token_id\": 50257,\n",
4695
+ " \"suppress_tokens\": [],\n",
4696
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4697
+ " \"use_cache\": false\n",
4698
+ "}\n",
4699
+ "\n",
4700
+ "Generate config GenerationConfig {\n",
4701
+ " \"begin_suppress_tokens\": [\n",
4702
+ " 220,\n",
4703
+ " 50257\n",
4704
+ " ],\n",
4705
+ " \"bos_token_id\": 50257,\n",
4706
+ " \"decoder_start_token_id\": 50258,\n",
4707
+ " \"eos_token_id\": 50257,\n",
4708
+ " \"max_length\": 448,\n",
4709
+ " \"pad_token_id\": 50257,\n",
4710
+ " \"suppress_tokens\": [],\n",
4711
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4712
+ " \"use_cache\": false\n",
4713
+ "}\n",
4714
+ "\n",
4715
+ "Generate config GenerationConfig {\n",
4716
+ " \"begin_suppress_tokens\": [\n",
4717
+ " 220,\n",
4718
+ " 50257\n",
4719
+ " ],\n",
4720
+ " \"bos_token_id\": 50257,\n",
4721
+ " \"decoder_start_token_id\": 50258,\n",
4722
+ " \"eos_token_id\": 50257,\n",
4723
+ " \"max_length\": 448,\n",
4724
+ " \"pad_token_id\": 50257,\n",
4725
+ " \"suppress_tokens\": [],\n",
4726
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4727
+ " \"use_cache\": false\n",
4728
+ "}\n",
4729
+ "\n",
4730
+ "Generate config GenerationConfig {\n",
4731
+ " \"begin_suppress_tokens\": [\n",
4732
+ " 220,\n",
4733
+ " 50257\n",
4734
+ " ],\n",
4735
+ " \"bos_token_id\": 50257,\n",
4736
+ " \"decoder_start_token_id\": 50258,\n",
4737
+ " \"eos_token_id\": 50257,\n",
4738
+ " \"max_length\": 448,\n",
4739
+ " \"pad_token_id\": 50257,\n",
4740
+ " \"suppress_tokens\": [],\n",
4741
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4742
+ " \"use_cache\": false\n",
4743
+ "}\n",
4744
+ "\n",
4745
+ "Generate config GenerationConfig {\n",
4746
+ " \"begin_suppress_tokens\": [\n",
4747
+ " 220,\n",
4748
+ " 50257\n",
4749
+ " ],\n",
4750
+ " \"bos_token_id\": 50257,\n",
4751
+ " \"decoder_start_token_id\": 50258,\n",
4752
+ " \"eos_token_id\": 50257,\n",
4753
+ " \"max_length\": 448,\n",
4754
+ " \"pad_token_id\": 50257,\n",
4755
+ " \"suppress_tokens\": [],\n",
4756
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4757
+ " \"use_cache\": false\n",
4758
+ "}\n",
4759
+ "\n",
4760
+ "Generate config GenerationConfig {\n",
4761
+ " \"begin_suppress_tokens\": [\n",
4762
+ " 220,\n",
4763
+ " 50257\n",
4764
+ " ],\n",
4765
+ " \"bos_token_id\": 50257,\n",
4766
+ " \"decoder_start_token_id\": 50258,\n",
4767
+ " \"eos_token_id\": 50257,\n",
4768
+ " \"max_length\": 448,\n",
4769
+ " \"pad_token_id\": 50257,\n",
4770
+ " \"suppress_tokens\": [],\n",
4771
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4772
+ " \"use_cache\": false\n",
4773
+ "}\n",
4774
+ "\n",
4775
+ "Generate config GenerationConfig {\n",
4776
+ " \"begin_suppress_tokens\": [\n",
4777
+ " 220,\n",
4778
+ " 50257\n",
4779
+ " ],\n",
4780
+ " \"bos_token_id\": 50257,\n",
4781
+ " \"decoder_start_token_id\": 50258,\n",
4782
+ " \"eos_token_id\": 50257,\n",
4783
+ " \"max_length\": 448,\n",
4784
+ " \"pad_token_id\": 50257,\n",
4785
+ " \"suppress_tokens\": [],\n",
4786
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4787
+ " \"use_cache\": false\n",
4788
+ "}\n",
4789
+ "\n",
4790
+ "Generate config GenerationConfig {\n",
4791
+ " \"begin_suppress_tokens\": [\n",
4792
+ " 220,\n",
4793
+ " 50257\n",
4794
+ " ],\n",
4795
+ " \"bos_token_id\": 50257,\n",
4796
+ " \"decoder_start_token_id\": 50258,\n",
4797
+ " \"eos_token_id\": 50257,\n",
4798
+ " \"max_length\": 448,\n",
4799
+ " \"pad_token_id\": 50257,\n",
4800
+ " \"suppress_tokens\": [],\n",
4801
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4802
+ " \"use_cache\": false\n",
4803
+ "}\n",
4804
+ "\n",
4805
+ "Generate config GenerationConfig {\n",
4806
+ " \"begin_suppress_tokens\": [\n",
4807
+ " 220,\n",
4808
+ " 50257\n",
4809
+ " ],\n",
4810
+ " \"bos_token_id\": 50257,\n",
4811
+ " \"decoder_start_token_id\": 50258,\n",
4812
+ " \"eos_token_id\": 50257,\n",
4813
+ " \"max_length\": 448,\n",
4814
+ " \"pad_token_id\": 50257,\n",
4815
+ " \"suppress_tokens\": [],\n",
4816
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4817
+ " \"use_cache\": false\n",
4818
+ "}\n",
4819
+ "\n",
4820
+ "Generate config GenerationConfig {\n",
4821
+ " \"begin_suppress_tokens\": [\n",
4822
+ " 220,\n",
4823
+ " 50257\n",
4824
+ " ],\n",
4825
+ " \"bos_token_id\": 50257,\n",
4826
+ " \"decoder_start_token_id\": 50258,\n",
4827
+ " \"eos_token_id\": 50257,\n",
4828
+ " \"max_length\": 448,\n",
4829
+ " \"pad_token_id\": 50257,\n",
4830
+ " \"suppress_tokens\": [],\n",
4831
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4832
+ " \"use_cache\": false\n",
4833
+ "}\n",
4834
+ "\n",
4835
+ "Generate config GenerationConfig {\n",
4836
+ " \"begin_suppress_tokens\": [\n",
4837
+ " 220,\n",
4838
+ " 50257\n",
4839
+ " ],\n",
4840
+ " \"bos_token_id\": 50257,\n",
4841
+ " \"decoder_start_token_id\": 50258,\n",
4842
+ " \"eos_token_id\": 50257,\n",
4843
+ " \"max_length\": 448,\n",
4844
+ " \"pad_token_id\": 50257,\n",
4845
+ " \"suppress_tokens\": [],\n",
4846
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4847
+ " \"use_cache\": false\n",
4848
+ "}\n",
4849
+ "\n",
4850
+ "Generate config GenerationConfig {\n",
4851
+ " \"begin_suppress_tokens\": [\n",
4852
+ " 220,\n",
4853
+ " 50257\n",
4854
+ " ],\n",
4855
+ " \"bos_token_id\": 50257,\n",
4856
+ " \"decoder_start_token_id\": 50258,\n",
4857
+ " \"eos_token_id\": 50257,\n",
4858
+ " \"max_length\": 448,\n",
4859
+ " \"pad_token_id\": 50257,\n",
4860
+ " \"suppress_tokens\": [],\n",
4861
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4862
+ " \"use_cache\": false\n",
4863
+ "}\n",
4864
+ "\n",
4865
+ "Generate config GenerationConfig {\n",
4866
+ " \"begin_suppress_tokens\": [\n",
4867
+ " 220,\n",
4868
+ " 50257\n",
4869
+ " ],\n",
4870
+ " \"bos_token_id\": 50257,\n",
4871
+ " \"decoder_start_token_id\": 50258,\n",
4872
+ " \"eos_token_id\": 50257,\n",
4873
+ " \"max_length\": 448,\n",
4874
+ " \"pad_token_id\": 50257,\n",
4875
+ " \"suppress_tokens\": [],\n",
4876
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4877
+ " \"use_cache\": false\n",
4878
+ "}\n",
4879
+ "\n",
4880
+ "Generate config GenerationConfig {\n",
4881
+ " \"begin_suppress_tokens\": [\n",
4882
+ " 220,\n",
4883
+ " 50257\n",
4884
+ " ],\n",
4885
+ " \"bos_token_id\": 50257,\n",
4886
+ " \"decoder_start_token_id\": 50258,\n",
4887
+ " \"eos_token_id\": 50257,\n",
4888
+ " \"max_length\": 448,\n",
4889
+ " \"pad_token_id\": 50257,\n",
4890
+ " \"suppress_tokens\": [],\n",
4891
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4892
+ " \"use_cache\": false\n",
4893
+ "}\n",
4894
+ "\n",
4895
+ "Generate config GenerationConfig {\n",
4896
+ " \"begin_suppress_tokens\": [\n",
4897
+ " 220,\n",
4898
+ " 50257\n",
4899
+ " ],\n",
4900
+ " \"bos_token_id\": 50257,\n",
4901
+ " \"decoder_start_token_id\": 50258,\n",
4902
+ " \"eos_token_id\": 50257,\n",
4903
+ " \"max_length\": 448,\n",
4904
+ " \"pad_token_id\": 50257,\n",
4905
+ " \"suppress_tokens\": [],\n",
4906
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4907
+ " \"use_cache\": false\n",
4908
+ "}\n",
4909
+ "\n",
4910
+ "Generate config GenerationConfig {\n",
4911
+ " \"begin_suppress_tokens\": [\n",
4912
+ " 220,\n",
4913
+ " 50257\n",
4914
+ " ],\n",
4915
+ " \"bos_token_id\": 50257,\n",
4916
+ " \"decoder_start_token_id\": 50258,\n",
4917
+ " \"eos_token_id\": 50257,\n",
4918
+ " \"max_length\": 448,\n",
4919
+ " \"pad_token_id\": 50257,\n",
4920
+ " \"suppress_tokens\": [],\n",
4921
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4922
+ " \"use_cache\": false\n",
4923
+ "}\n",
4924
+ "\n",
4925
+ "Generate config GenerationConfig {\n",
4926
+ " \"begin_suppress_tokens\": [\n",
4927
+ " 220,\n",
4928
+ " 50257\n",
4929
+ " ],\n",
4930
+ " \"bos_token_id\": 50257,\n",
4931
+ " \"decoder_start_token_id\": 50258,\n",
4932
+ " \"eos_token_id\": 50257,\n",
4933
+ " \"max_length\": 448,\n",
4934
+ " \"pad_token_id\": 50257,\n",
4935
+ " \"suppress_tokens\": [],\n",
4936
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4937
+ " \"use_cache\": false\n",
4938
+ "}\n",
4939
+ "\n",
4940
+ "Generate config GenerationConfig {\n",
4941
+ " \"begin_suppress_tokens\": [\n",
4942
+ " 220,\n",
4943
+ " 50257\n",
4944
+ " ],\n",
4945
+ " \"bos_token_id\": 50257,\n",
4946
+ " \"decoder_start_token_id\": 50258,\n",
4947
+ " \"eos_token_id\": 50257,\n",
4948
+ " \"max_length\": 448,\n",
4949
+ " \"pad_token_id\": 50257,\n",
4950
+ " \"suppress_tokens\": [],\n",
4951
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4952
+ " \"use_cache\": false\n",
4953
+ "}\n",
4954
+ "\n",
4955
+ "Generate config GenerationConfig {\n",
4956
+ " \"begin_suppress_tokens\": [\n",
4957
+ " 220,\n",
4958
+ " 50257\n",
4959
+ " ],\n",
4960
+ " \"bos_token_id\": 50257,\n",
4961
+ " \"decoder_start_token_id\": 50258,\n",
4962
+ " \"eos_token_id\": 50257,\n",
4963
+ " \"max_length\": 448,\n",
4964
+ " \"pad_token_id\": 50257,\n",
4965
+ " \"suppress_tokens\": [],\n",
4966
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4967
+ " \"use_cache\": false\n",
4968
+ "}\n",
4969
+ "\n",
4970
+ "Generate config GenerationConfig {\n",
4971
+ " \"begin_suppress_tokens\": [\n",
4972
+ " 220,\n",
4973
+ " 50257\n",
4974
+ " ],\n",
4975
+ " \"bos_token_id\": 50257,\n",
4976
+ " \"decoder_start_token_id\": 50258,\n",
4977
+ " \"eos_token_id\": 50257,\n",
4978
+ " \"max_length\": 448,\n",
4979
+ " \"pad_token_id\": 50257,\n",
4980
+ " \"suppress_tokens\": [],\n",
4981
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4982
+ " \"use_cache\": false\n",
4983
+ "}\n",
4984
+ "\n",
4985
+ "Generate config GenerationConfig {\n",
4986
+ " \"begin_suppress_tokens\": [\n",
4987
+ " 220,\n",
4988
+ " 50257\n",
4989
+ " ],\n",
4990
+ " \"bos_token_id\": 50257,\n",
4991
+ " \"decoder_start_token_id\": 50258,\n",
4992
+ " \"eos_token_id\": 50257,\n",
4993
+ " \"max_length\": 448,\n",
4994
+ " \"pad_token_id\": 50257,\n",
4995
+ " \"suppress_tokens\": [],\n",
4996
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
4997
+ " \"use_cache\": false\n",
4998
+ "}\n",
4999
+ "\n",
5000
+ "Generate config GenerationConfig {\n",
5001
+ " \"begin_suppress_tokens\": [\n",
5002
+ " 220,\n",
5003
+ " 50257\n",
5004
+ " ],\n",
5005
+ " \"bos_token_id\": 50257,\n",
5006
+ " \"decoder_start_token_id\": 50258,\n",
5007
+ " \"eos_token_id\": 50257,\n",
5008
+ " \"max_length\": 448,\n",
5009
+ " \"pad_token_id\": 50257,\n",
5010
+ " \"suppress_tokens\": [],\n",
5011
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5012
+ " \"use_cache\": false\n",
5013
+ "}\n",
5014
+ "\n",
5015
+ "Generate config GenerationConfig {\n",
5016
+ " \"begin_suppress_tokens\": [\n",
5017
+ " 220,\n",
5018
+ " 50257\n",
5019
+ " ],\n",
5020
+ " \"bos_token_id\": 50257,\n",
5021
+ " \"decoder_start_token_id\": 50258,\n",
5022
+ " \"eos_token_id\": 50257,\n",
5023
+ " \"max_length\": 448,\n",
5024
+ " \"pad_token_id\": 50257,\n",
5025
+ " \"suppress_tokens\": [],\n",
5026
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5027
+ " \"use_cache\": false\n",
5028
+ "}\n",
5029
+ "\n",
5030
+ "Generate config GenerationConfig {\n",
5031
+ " \"begin_suppress_tokens\": [\n",
5032
+ " 220,\n",
5033
+ " 50257\n",
5034
+ " ],\n",
5035
+ " \"bos_token_id\": 50257,\n",
5036
+ " \"decoder_start_token_id\": 50258,\n",
5037
+ " \"eos_token_id\": 50257,\n",
5038
+ " \"max_length\": 448,\n",
5039
+ " \"pad_token_id\": 50257,\n",
5040
+ " \"suppress_tokens\": [],\n",
5041
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5042
+ " \"use_cache\": false\n",
5043
+ "}\n",
5044
+ "\n",
5045
+ "Generate config GenerationConfig {\n",
5046
+ " \"begin_suppress_tokens\": [\n",
5047
+ " 220,\n",
5048
+ " 50257\n",
5049
+ " ],\n",
5050
+ " \"bos_token_id\": 50257,\n",
5051
+ " \"decoder_start_token_id\": 50258,\n",
5052
+ " \"eos_token_id\": 50257,\n",
5053
+ " \"max_length\": 448,\n",
5054
+ " \"pad_token_id\": 50257,\n",
5055
+ " \"suppress_tokens\": [],\n",
5056
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5057
+ " \"use_cache\": false\n",
5058
+ "}\n",
5059
+ "\n",
5060
+ "Generate config GenerationConfig {\n",
5061
+ " \"begin_suppress_tokens\": [\n",
5062
+ " 220,\n",
5063
+ " 50257\n",
5064
+ " ],\n",
5065
+ " \"bos_token_id\": 50257,\n",
5066
+ " \"decoder_start_token_id\": 50258,\n",
5067
+ " \"eos_token_id\": 50257,\n",
5068
+ " \"max_length\": 448,\n",
5069
+ " \"pad_token_id\": 50257,\n",
5070
+ " \"suppress_tokens\": [],\n",
5071
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5072
+ " \"use_cache\": false\n",
5073
+ "}\n",
5074
+ "\n",
5075
+ "Generate config GenerationConfig {\n",
5076
+ " \"begin_suppress_tokens\": [\n",
5077
+ " 220,\n",
5078
+ " 50257\n",
5079
+ " ],\n",
5080
+ " \"bos_token_id\": 50257,\n",
5081
+ " \"decoder_start_token_id\": 50258,\n",
5082
+ " \"eos_token_id\": 50257,\n",
5083
+ " \"max_length\": 448,\n",
5084
+ " \"pad_token_id\": 50257,\n",
5085
+ " \"suppress_tokens\": [],\n",
5086
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5087
+ " \"use_cache\": false\n",
5088
+ "}\n",
5089
+ "\n",
5090
+ "Generate config GenerationConfig {\n",
5091
+ " \"begin_suppress_tokens\": [\n",
5092
+ " 220,\n",
5093
+ " 50257\n",
5094
+ " ],\n",
5095
+ " \"bos_token_id\": 50257,\n",
5096
+ " \"decoder_start_token_id\": 50258,\n",
5097
+ " \"eos_token_id\": 50257,\n",
5098
+ " \"max_length\": 448,\n",
5099
+ " \"pad_token_id\": 50257,\n",
5100
+ " \"suppress_tokens\": [],\n",
5101
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5102
+ " \"use_cache\": false\n",
5103
+ "}\n",
5104
+ "\n",
5105
+ "Generate config GenerationConfig {\n",
5106
+ " \"begin_suppress_tokens\": [\n",
5107
+ " 220,\n",
5108
+ " 50257\n",
5109
+ " ],\n",
5110
+ " \"bos_token_id\": 50257,\n",
5111
+ " \"decoder_start_token_id\": 50258,\n",
5112
+ " \"eos_token_id\": 50257,\n",
5113
+ " \"max_length\": 448,\n",
5114
+ " \"pad_token_id\": 50257,\n",
5115
+ " \"suppress_tokens\": [],\n",
5116
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5117
+ " \"use_cache\": false\n",
5118
+ "}\n",
5119
+ "\n",
5120
+ "Generate config GenerationConfig {\n",
5121
+ " \"begin_suppress_tokens\": [\n",
5122
+ " 220,\n",
5123
+ " 50257\n",
5124
+ " ],\n",
5125
+ " \"bos_token_id\": 50257,\n",
5126
+ " \"decoder_start_token_id\": 50258,\n",
5127
+ " \"eos_token_id\": 50257,\n",
5128
+ " \"max_length\": 448,\n",
5129
+ " \"pad_token_id\": 50257,\n",
5130
+ " \"suppress_tokens\": [],\n",
5131
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5132
+ " \"use_cache\": false\n",
5133
+ "}\n",
5134
+ "\n",
5135
+ "Generate config GenerationConfig {\n",
5136
+ " \"begin_suppress_tokens\": [\n",
5137
+ " 220,\n",
5138
+ " 50257\n",
5139
+ " ],\n",
5140
+ " \"bos_token_id\": 50257,\n",
5141
+ " \"decoder_start_token_id\": 50258,\n",
5142
+ " \"eos_token_id\": 50257,\n",
5143
+ " \"max_length\": 448,\n",
5144
+ " \"pad_token_id\": 50257,\n",
5145
+ " \"suppress_tokens\": [],\n",
5146
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5147
+ " \"use_cache\": false\n",
5148
+ "}\n",
5149
+ "\n",
5150
+ "Generate config GenerationConfig {\n",
5151
+ " \"begin_suppress_tokens\": [\n",
5152
+ " 220,\n",
5153
+ " 50257\n",
5154
+ " ],\n",
5155
+ " \"bos_token_id\": 50257,\n",
5156
+ " \"decoder_start_token_id\": 50258,\n",
5157
+ " \"eos_token_id\": 50257,\n",
5158
+ " \"max_length\": 448,\n",
5159
+ " \"pad_token_id\": 50257,\n",
5160
+ " \"suppress_tokens\": [],\n",
5161
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5162
+ " \"use_cache\": false\n",
5163
+ "}\n",
5164
+ "\n",
5165
+ "Generate config GenerationConfig {\n",
5166
+ " \"begin_suppress_tokens\": [\n",
5167
+ " 220,\n",
5168
+ " 50257\n",
5169
+ " ],\n",
5170
+ " \"bos_token_id\": 50257,\n",
5171
+ " \"decoder_start_token_id\": 50258,\n",
5172
+ " \"eos_token_id\": 50257,\n",
5173
+ " \"max_length\": 448,\n",
5174
+ " \"pad_token_id\": 50257,\n",
5175
+ " \"suppress_tokens\": [],\n",
5176
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5177
+ " \"use_cache\": false\n",
5178
+ "}\n",
5179
+ "\n",
5180
+ "Generate config GenerationConfig {\n",
5181
+ " \"begin_suppress_tokens\": [\n",
5182
+ " 220,\n",
5183
+ " 50257\n",
5184
+ " ],\n",
5185
+ " \"bos_token_id\": 50257,\n",
5186
+ " \"decoder_start_token_id\": 50258,\n",
5187
+ " \"eos_token_id\": 50257,\n",
5188
+ " \"max_length\": 448,\n",
5189
+ " \"pad_token_id\": 50257,\n",
5190
+ " \"suppress_tokens\": [],\n",
5191
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5192
+ " \"use_cache\": false\n",
5193
+ "}\n",
5194
+ "\n",
5195
+ "Generate config GenerationConfig {\n",
5196
+ " \"begin_suppress_tokens\": [\n",
5197
+ " 220,\n",
5198
+ " 50257\n",
5199
+ " ],\n",
5200
+ " \"bos_token_id\": 50257,\n",
5201
+ " \"decoder_start_token_id\": 50258,\n",
5202
+ " \"eos_token_id\": 50257,\n",
5203
+ " \"max_length\": 448,\n",
5204
+ " \"pad_token_id\": 50257,\n",
5205
+ " \"suppress_tokens\": [],\n",
5206
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5207
+ " \"use_cache\": false\n",
5208
+ "}\n",
5209
+ "\n",
5210
+ "Generate config GenerationConfig {\n",
5211
+ " \"begin_suppress_tokens\": [\n",
5212
+ " 220,\n",
5213
+ " 50257\n",
5214
+ " ],\n",
5215
+ " \"bos_token_id\": 50257,\n",
5216
+ " \"decoder_start_token_id\": 50258,\n",
5217
+ " \"eos_token_id\": 50257,\n",
5218
+ " \"max_length\": 448,\n",
5219
+ " \"pad_token_id\": 50257,\n",
5220
+ " \"suppress_tokens\": [],\n",
5221
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5222
+ " \"use_cache\": false\n",
5223
+ "}\n",
5224
+ "\n",
5225
+ "Generate config GenerationConfig {\n",
5226
+ " \"begin_suppress_tokens\": [\n",
5227
+ " 220,\n",
5228
+ " 50257\n",
5229
+ " ],\n",
5230
+ " \"bos_token_id\": 50257,\n",
5231
+ " \"decoder_start_token_id\": 50258,\n",
5232
+ " \"eos_token_id\": 50257,\n",
5233
+ " \"max_length\": 448,\n",
5234
+ " \"pad_token_id\": 50257,\n",
5235
+ " \"suppress_tokens\": [],\n",
5236
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5237
+ " \"use_cache\": false\n",
5238
+ "}\n",
5239
+ "\n",
5240
+ "Generate config GenerationConfig {\n",
5241
+ " \"begin_suppress_tokens\": [\n",
5242
+ " 220,\n",
5243
+ " 50257\n",
5244
+ " ],\n",
5245
+ " \"bos_token_id\": 50257,\n",
5246
+ " \"decoder_start_token_id\": 50258,\n",
5247
+ " \"eos_token_id\": 50257,\n",
5248
+ " \"max_length\": 448,\n",
5249
+ " \"pad_token_id\": 50257,\n",
5250
+ " \"suppress_tokens\": [],\n",
5251
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5252
+ " \"use_cache\": false\n",
5253
+ "}\n",
5254
+ "\n",
5255
+ "Generate config GenerationConfig {\n",
5256
+ " \"begin_suppress_tokens\": [\n",
5257
+ " 220,\n",
5258
+ " 50257\n",
5259
+ " ],\n",
5260
+ " \"bos_token_id\": 50257,\n",
5261
+ " \"decoder_start_token_id\": 50258,\n",
5262
+ " \"eos_token_id\": 50257,\n",
5263
+ " \"max_length\": 448,\n",
5264
+ " \"pad_token_id\": 50257,\n",
5265
+ " \"suppress_tokens\": [],\n",
5266
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5267
+ " \"use_cache\": false\n",
5268
+ "}\n",
5269
+ "\n",
5270
+ "Generate config GenerationConfig {\n",
5271
+ " \"begin_suppress_tokens\": [\n",
5272
+ " 220,\n",
5273
+ " 50257\n",
5274
+ " ],\n",
5275
+ " \"bos_token_id\": 50257,\n",
5276
+ " \"decoder_start_token_id\": 50258,\n",
5277
+ " \"eos_token_id\": 50257,\n",
5278
+ " \"max_length\": 448,\n",
5279
+ " \"pad_token_id\": 50257,\n",
5280
+ " \"suppress_tokens\": [],\n",
5281
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5282
+ " \"use_cache\": false\n",
5283
+ "}\n",
5284
+ "\n",
5285
+ "Generate config GenerationConfig {\n",
5286
+ " \"begin_suppress_tokens\": [\n",
5287
+ " 220,\n",
5288
+ " 50257\n",
5289
+ " ],\n",
5290
+ " \"bos_token_id\": 50257,\n",
5291
+ " \"decoder_start_token_id\": 50258,\n",
5292
+ " \"eos_token_id\": 50257,\n",
5293
+ " \"max_length\": 448,\n",
5294
+ " \"pad_token_id\": 50257,\n",
5295
+ " \"suppress_tokens\": [],\n",
5296
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5297
+ " \"use_cache\": false\n",
5298
+ "}\n",
5299
+ "\n",
5300
+ "Generate config GenerationConfig {\n",
5301
+ " \"begin_suppress_tokens\": [\n",
5302
+ " 220,\n",
5303
+ " 50257\n",
5304
+ " ],\n",
5305
+ " \"bos_token_id\": 50257,\n",
5306
+ " \"decoder_start_token_id\": 50258,\n",
5307
+ " \"eos_token_id\": 50257,\n",
5308
+ " \"max_length\": 448,\n",
5309
+ " \"pad_token_id\": 50257,\n",
5310
+ " \"suppress_tokens\": [],\n",
5311
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5312
+ " \"use_cache\": false\n",
5313
+ "}\n",
5314
+ "\n",
5315
+ "Generate config GenerationConfig {\n",
5316
+ " \"begin_suppress_tokens\": [\n",
5317
+ " 220,\n",
5318
+ " 50257\n",
5319
+ " ],\n",
5320
+ " \"bos_token_id\": 50257,\n",
5321
+ " \"decoder_start_token_id\": 50258,\n",
5322
+ " \"eos_token_id\": 50257,\n",
5323
+ " \"max_length\": 448,\n",
5324
+ " \"pad_token_id\": 50257,\n",
5325
+ " \"suppress_tokens\": [],\n",
5326
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5327
+ " \"use_cache\": false\n",
5328
+ "}\n",
5329
+ "\n",
5330
+ "Generate config GenerationConfig {\n",
5331
+ " \"begin_suppress_tokens\": [\n",
5332
+ " 220,\n",
5333
+ " 50257\n",
5334
+ " ],\n",
5335
+ " \"bos_token_id\": 50257,\n",
5336
+ " \"decoder_start_token_id\": 50258,\n",
5337
+ " \"eos_token_id\": 50257,\n",
5338
+ " \"max_length\": 448,\n",
5339
+ " \"pad_token_id\": 50257,\n",
5340
+ " \"suppress_tokens\": [],\n",
5341
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5342
+ " \"use_cache\": false\n",
5343
+ "}\n",
5344
+ "\n",
5345
+ "Generate config GenerationConfig {\n",
5346
+ " \"begin_suppress_tokens\": [\n",
5347
+ " 220,\n",
5348
+ " 50257\n",
5349
+ " ],\n",
5350
+ " \"bos_token_id\": 50257,\n",
5351
+ " \"decoder_start_token_id\": 50258,\n",
5352
+ " \"eos_token_id\": 50257,\n",
5353
+ " \"max_length\": 448,\n",
5354
+ " \"pad_token_id\": 50257,\n",
5355
+ " \"suppress_tokens\": [],\n",
5356
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5357
+ " \"use_cache\": false\n",
5358
+ "}\n",
5359
+ "\n",
5360
+ "Generate config GenerationConfig {\n",
5361
+ " \"begin_suppress_tokens\": [\n",
5362
+ " 220,\n",
5363
+ " 50257\n",
5364
+ " ],\n",
5365
+ " \"bos_token_id\": 50257,\n",
5366
+ " \"decoder_start_token_id\": 50258,\n",
5367
+ " \"eos_token_id\": 50257,\n",
5368
+ " \"max_length\": 448,\n",
5369
+ " \"pad_token_id\": 50257,\n",
5370
+ " \"suppress_tokens\": [],\n",
5371
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5372
+ " \"use_cache\": false\n",
5373
+ "}\n",
5374
+ "\n",
5375
+ "Generate config GenerationConfig {\n",
5376
+ " \"begin_suppress_tokens\": [\n",
5377
+ " 220,\n",
5378
+ " 50257\n",
5379
+ " ],\n",
5380
+ " \"bos_token_id\": 50257,\n",
5381
+ " \"decoder_start_token_id\": 50258,\n",
5382
+ " \"eos_token_id\": 50257,\n",
5383
+ " \"max_length\": 448,\n",
5384
+ " \"pad_token_id\": 50257,\n",
5385
+ " \"suppress_tokens\": [],\n",
5386
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5387
+ " \"use_cache\": false\n",
5388
+ "}\n",
5389
+ "\n",
5390
+ "Generate config GenerationConfig {\n",
5391
+ " \"begin_suppress_tokens\": [\n",
5392
+ " 220,\n",
5393
+ " 50257\n",
5394
+ " ],\n",
5395
+ " \"bos_token_id\": 50257,\n",
5396
+ " \"decoder_start_token_id\": 50258,\n",
5397
+ " \"eos_token_id\": 50257,\n",
5398
+ " \"max_length\": 448,\n",
5399
+ " \"pad_token_id\": 50257,\n",
5400
+ " \"suppress_tokens\": [],\n",
5401
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5402
+ " \"use_cache\": false\n",
5403
+ "}\n",
5404
+ "\n",
5405
+ "Generate config GenerationConfig {\n",
5406
+ " \"begin_suppress_tokens\": [\n",
5407
+ " 220,\n",
5408
+ " 50257\n",
5409
+ " ],\n",
5410
+ " \"bos_token_id\": 50257,\n",
5411
+ " \"decoder_start_token_id\": 50258,\n",
5412
+ " \"eos_token_id\": 50257,\n",
5413
+ " \"max_length\": 448,\n",
5414
+ " \"pad_token_id\": 50257,\n",
5415
+ " \"suppress_tokens\": [],\n",
5416
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5417
+ " \"use_cache\": false\n",
5418
+ "}\n",
5419
+ "\n",
5420
+ "Generate config GenerationConfig {\n",
5421
+ " \"begin_suppress_tokens\": [\n",
5422
+ " 220,\n",
5423
+ " 50257\n",
5424
+ " ],\n",
5425
+ " \"bos_token_id\": 50257,\n",
5426
+ " \"decoder_start_token_id\": 50258,\n",
5427
+ " \"eos_token_id\": 50257,\n",
5428
+ " \"max_length\": 448,\n",
5429
+ " \"pad_token_id\": 50257,\n",
5430
+ " \"suppress_tokens\": [],\n",
5431
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5432
+ " \"use_cache\": false\n",
5433
+ "}\n",
5434
+ "\n",
5435
+ "Generate config GenerationConfig {\n",
5436
+ " \"begin_suppress_tokens\": [\n",
5437
+ " 220,\n",
5438
+ " 50257\n",
5439
+ " ],\n",
5440
+ " \"bos_token_id\": 50257,\n",
5441
+ " \"decoder_start_token_id\": 50258,\n",
5442
+ " \"eos_token_id\": 50257,\n",
5443
+ " \"max_length\": 448,\n",
5444
+ " \"pad_token_id\": 50257,\n",
5445
+ " \"suppress_tokens\": [],\n",
5446
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5447
+ " \"use_cache\": false\n",
5448
+ "}\n",
5449
+ "\n",
5450
+ "Generate config GenerationConfig {\n",
5451
+ " \"begin_suppress_tokens\": [\n",
5452
+ " 220,\n",
5453
+ " 50257\n",
5454
+ " ],\n",
5455
+ " \"bos_token_id\": 50257,\n",
5456
+ " \"decoder_start_token_id\": 50258,\n",
5457
+ " \"eos_token_id\": 50257,\n",
5458
+ " \"max_length\": 448,\n",
5459
+ " \"pad_token_id\": 50257,\n",
5460
+ " \"suppress_tokens\": [],\n",
5461
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5462
+ " \"use_cache\": false\n",
5463
+ "}\n",
5464
+ "\n",
5465
+ "Generate config GenerationConfig {\n",
5466
+ " \"begin_suppress_tokens\": [\n",
5467
+ " 220,\n",
5468
+ " 50257\n",
5469
+ " ],\n",
5470
+ " \"bos_token_id\": 50257,\n",
5471
+ " \"decoder_start_token_id\": 50258,\n",
5472
+ " \"eos_token_id\": 50257,\n",
5473
+ " \"max_length\": 448,\n",
5474
+ " \"pad_token_id\": 50257,\n",
5475
+ " \"suppress_tokens\": [],\n",
5476
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5477
+ " \"use_cache\": false\n",
5478
+ "}\n",
5479
+ "\n",
5480
+ "Generate config GenerationConfig {\n",
5481
+ " \"begin_suppress_tokens\": [\n",
5482
+ " 220,\n",
5483
+ " 50257\n",
5484
+ " ],\n",
5485
+ " \"bos_token_id\": 50257,\n",
5486
+ " \"decoder_start_token_id\": 50258,\n",
5487
+ " \"eos_token_id\": 50257,\n",
5488
+ " \"max_length\": 448,\n",
5489
+ " \"pad_token_id\": 50257,\n",
5490
+ " \"suppress_tokens\": [],\n",
5491
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5492
+ " \"use_cache\": false\n",
5493
+ "}\n",
5494
+ "\n",
5495
+ "Generate config GenerationConfig {\n",
5496
+ " \"begin_suppress_tokens\": [\n",
5497
+ " 220,\n",
5498
+ " 50257\n",
5499
+ " ],\n",
5500
+ " \"bos_token_id\": 50257,\n",
5501
+ " \"decoder_start_token_id\": 50258,\n",
5502
+ " \"eos_token_id\": 50257,\n",
5503
+ " \"max_length\": 448,\n",
5504
+ " \"pad_token_id\": 50257,\n",
5505
+ " \"suppress_tokens\": [],\n",
5506
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5507
+ " \"use_cache\": false\n",
5508
+ "}\n",
5509
+ "\n",
5510
+ "Generate config GenerationConfig {\n",
5511
+ " \"begin_suppress_tokens\": [\n",
5512
+ " 220,\n",
5513
+ " 50257\n",
5514
+ " ],\n",
5515
+ " \"bos_token_id\": 50257,\n",
5516
+ " \"decoder_start_token_id\": 50258,\n",
5517
+ " \"eos_token_id\": 50257,\n",
5518
+ " \"max_length\": 448,\n",
5519
+ " \"pad_token_id\": 50257,\n",
5520
+ " \"suppress_tokens\": [],\n",
5521
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5522
+ " \"use_cache\": false\n",
5523
+ "}\n",
5524
+ "\n",
5525
+ "Generate config GenerationConfig {\n",
5526
+ " \"begin_suppress_tokens\": [\n",
5527
+ " 220,\n",
5528
+ " 50257\n",
5529
+ " ],\n",
5530
+ " \"bos_token_id\": 50257,\n",
5531
+ " \"decoder_start_token_id\": 50258,\n",
5532
+ " \"eos_token_id\": 50257,\n",
5533
+ " \"max_length\": 448,\n",
5534
+ " \"pad_token_id\": 50257,\n",
5535
+ " \"suppress_tokens\": [],\n",
5536
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5537
+ " \"use_cache\": false\n",
5538
+ "}\n",
5539
+ "\n",
5540
+ "Generate config GenerationConfig {\n",
5541
+ " \"begin_suppress_tokens\": [\n",
5542
+ " 220,\n",
5543
+ " 50257\n",
5544
+ " ],\n",
5545
+ " \"bos_token_id\": 50257,\n",
5546
+ " \"decoder_start_token_id\": 50258,\n",
5547
+ " \"eos_token_id\": 50257,\n",
5548
+ " \"max_length\": 448,\n",
5549
+ " \"pad_token_id\": 50257,\n",
5550
+ " \"suppress_tokens\": [],\n",
5551
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5552
+ " \"use_cache\": false\n",
5553
+ "}\n",
5554
+ "\n",
5555
+ "Generate config GenerationConfig {\n",
5556
+ " \"begin_suppress_tokens\": [\n",
5557
+ " 220,\n",
5558
+ " 50257\n",
5559
+ " ],\n",
5560
+ " \"bos_token_id\": 50257,\n",
5561
+ " \"decoder_start_token_id\": 50258,\n",
5562
+ " \"eos_token_id\": 50257,\n",
5563
+ " \"max_length\": 448,\n",
5564
+ " \"pad_token_id\": 50257,\n",
5565
+ " \"suppress_tokens\": [],\n",
5566
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5567
+ " \"use_cache\": false\n",
5568
+ "}\n",
5569
+ "\n",
5570
+ "Generate config GenerationConfig {\n",
5571
+ " \"begin_suppress_tokens\": [\n",
5572
+ " 220,\n",
5573
+ " 50257\n",
5574
+ " ],\n",
5575
+ " \"bos_token_id\": 50257,\n",
5576
+ " \"decoder_start_token_id\": 50258,\n",
5577
+ " \"eos_token_id\": 50257,\n",
5578
+ " \"max_length\": 448,\n",
5579
+ " \"pad_token_id\": 50257,\n",
5580
+ " \"suppress_tokens\": [],\n",
5581
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5582
+ " \"use_cache\": false\n",
5583
+ "}\n",
5584
+ "\n",
5585
+ "Generate config GenerationConfig {\n",
5586
+ " \"begin_suppress_tokens\": [\n",
5587
+ " 220,\n",
5588
+ " 50257\n",
5589
+ " ],\n",
5590
+ " \"bos_token_id\": 50257,\n",
5591
+ " \"decoder_start_token_id\": 50258,\n",
5592
+ " \"eos_token_id\": 50257,\n",
5593
+ " \"max_length\": 448,\n",
5594
+ " \"pad_token_id\": 50257,\n",
5595
+ " \"suppress_tokens\": [],\n",
5596
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5597
+ " \"use_cache\": false\n",
5598
+ "}\n",
5599
+ "\n",
5600
+ "Generate config GenerationConfig {\n",
5601
+ " \"begin_suppress_tokens\": [\n",
5602
+ " 220,\n",
5603
+ " 50257\n",
5604
+ " ],\n",
5605
+ " \"bos_token_id\": 50257,\n",
5606
+ " \"decoder_start_token_id\": 50258,\n",
5607
+ " \"eos_token_id\": 50257,\n",
5608
+ " \"max_length\": 448,\n",
5609
+ " \"pad_token_id\": 50257,\n",
5610
+ " \"suppress_tokens\": [],\n",
5611
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5612
+ " \"use_cache\": false\n",
5613
+ "}\n",
5614
+ "\n",
5615
+ "Generate config GenerationConfig {\n",
5616
+ " \"begin_suppress_tokens\": [\n",
5617
+ " 220,\n",
5618
+ " 50257\n",
5619
+ " ],\n",
5620
+ " \"bos_token_id\": 50257,\n",
5621
+ " \"decoder_start_token_id\": 50258,\n",
5622
+ " \"eos_token_id\": 50257,\n",
5623
+ " \"max_length\": 448,\n",
5624
+ " \"pad_token_id\": 50257,\n",
5625
+ " \"suppress_tokens\": [],\n",
5626
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5627
+ " \"use_cache\": false\n",
5628
+ "}\n",
5629
+ "\n",
5630
+ "Generate config GenerationConfig {\n",
5631
+ " \"begin_suppress_tokens\": [\n",
5632
+ " 220,\n",
5633
+ " 50257\n",
5634
+ " ],\n",
5635
+ " \"bos_token_id\": 50257,\n",
5636
+ " \"decoder_start_token_id\": 50258,\n",
5637
+ " \"eos_token_id\": 50257,\n",
5638
+ " \"max_length\": 448,\n",
5639
+ " \"pad_token_id\": 50257,\n",
5640
+ " \"suppress_tokens\": [],\n",
5641
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5642
+ " \"use_cache\": false\n",
5643
+ "}\n",
5644
+ "\n",
5645
+ "Generate config GenerationConfig {\n",
5646
+ " \"begin_suppress_tokens\": [\n",
5647
+ " 220,\n",
5648
+ " 50257\n",
5649
+ " ],\n",
5650
+ " \"bos_token_id\": 50257,\n",
5651
+ " \"decoder_start_token_id\": 50258,\n",
5652
+ " \"eos_token_id\": 50257,\n",
5653
+ " \"max_length\": 448,\n",
5654
+ " \"pad_token_id\": 50257,\n",
5655
+ " \"suppress_tokens\": [],\n",
5656
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5657
+ " \"use_cache\": false\n",
5658
+ "}\n",
5659
+ "\n",
5660
+ "Generate config GenerationConfig {\n",
5661
+ " \"begin_suppress_tokens\": [\n",
5662
+ " 220,\n",
5663
+ " 50257\n",
5664
+ " ],\n",
5665
+ " \"bos_token_id\": 50257,\n",
5666
+ " \"decoder_start_token_id\": 50258,\n",
5667
+ " \"eos_token_id\": 50257,\n",
5668
+ " \"max_length\": 448,\n",
5669
+ " \"pad_token_id\": 50257,\n",
5670
+ " \"suppress_tokens\": [],\n",
5671
+ " \"transformers_version\": \"4.26.0.dev0\",\n",
5672
+ " \"use_cache\": false\n",
5673
+ "}\n",
5674
+ "\n",
5675
+ "Saving model checkpoint to ./checkpoint-300\n",
5676
+ "Configuration saved in ./checkpoint-300/config.json\n",
5677
+ "Model weights saved in ./checkpoint-300/pytorch_model.bin\n",
5678
+ "Feature extractor saved in ./checkpoint-300/preprocessor_config.json\n",
5679
+ "tokenizer config file saved in ./checkpoint-300/tokenizer_config.json\n",
5680
+ "Special tokens file saved in ./checkpoint-300/special_tokens_map.json\n",
5681
+ "added tokens file saved in ./checkpoint-300/added_tokens.json\n",
5682
+ "Feature extractor saved in ./preprocessor_config.json\n",
5683
+ "tokenizer config file saved in ./tokenizer_config.json\n",
5684
+ "Special tokens file saved in ./special_tokens_map.json\n",
5685
+ "added tokens file saved in ./added_tokens.json\n"
5686
  ]
5687
  }
5688
  ],
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5798d99f0dd8fcce462a9d40f4eaf4f926a8c21159994c7acea3e963cf2038b
3
  size 6173655480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe3120a2e1029e21f4adf86697a4cb97142000cc984f096c2231833af34a037
3
  size 6173655480
runs/Dec20_16-04-54_129-146-50-243/events.out.tfevents.1671552308.129-146-50-243.731508.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35b2d3d760e5e857918235f8d94b0b5e21ce9b1d1c59ae8bf0c068f00f4b4902
3
- size 27772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46d1fa2f4491ec68929f699be304babf80e290e98e8b66ed2c36f5a20f2b11b
3
+ size 51640