anashrivastava commited on
Commit
f9ce20e
1 Parent(s): 641661e

Training in progress, epoch 0

Browse files
Files changed (4) hide show
  1. README.md +615 -2
  2. adapter_model.safetensors +1 -1
  3. tokenizer.json +6 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -5,7 +5,7 @@ tags:
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
- base_model: TinyLlama/TinyLlama-1.1B-Chat-v0.3
9
  model-index:
10
  - name: tinyllama-rephraser-lora
11
  results: []
@@ -16,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # tinyllama-rephraser-lora
18
 
19
- This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v0.3](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.3) on an unknown dataset.
 
 
20
 
21
  ## Model description
22
 
@@ -46,6 +48,617 @@ The following hyperparameters were used during training:
46
  - lr_scheduler_warmup_ratio: 0.1
47
  - num_epochs: 5
48
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  ### Framework versions
50
 
51
  - PEFT 0.9.0
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
+ base_model: unsloth/tinyllama-bnb-4bit
9
  model-index:
10
  - name: tinyllama-rephraser-lora
11
  results: []
 
16
 
17
  # tinyllama-rephraser-lora
18
 
19
+ This model is a fine-tuned version of [unsloth/tinyllama-bnb-4bit](https://huggingface.co/unsloth/tinyllama-bnb-4bit) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.6524
22
 
23
  ## Model description
24
 
 
48
  - lr_scheduler_warmup_ratio: 0.1
49
  - num_epochs: 5
50
 
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-----:|:----:|:---------------:|
55
+ | 2.3576 | 0.01 | 1 | 2.4199 |
56
+ | 2.4431 | 0.02 | 2 | 2.4179 |
57
+ | 2.5987 | 0.02 | 3 | 2.4198 |
58
+ | 2.3902 | 0.03 | 4 | 2.4175 |
59
+ | 2.4699 | 0.04 | 5 | 2.4176 |
60
+ | 2.408 | 0.05 | 6 | 2.4171 |
61
+ | 2.4169 | 0.06 | 7 | 2.4192 |
62
+ | 2.4351 | 0.07 | 8 | 2.4169 |
63
+ | 2.3709 | 0.07 | 9 | 2.4181 |
64
+ | 2.4303 | 0.08 | 10 | 2.4174 |
65
+ | 2.3925 | 0.09 | 11 | 2.4162 |
66
+ | 2.4358 | 0.1 | 12 | 2.4150 |
67
+ | 2.5119 | 0.11 | 13 | 2.4158 |
68
+ | 2.4336 | 0.12 | 14 | 2.4139 |
69
+ | 2.3145 | 0.12 | 15 | 2.4137 |
70
+ | 2.3547 | 0.13 | 16 | 2.4139 |
71
+ | 2.4008 | 0.14 | 17 | 2.4124 |
72
+ | 2.3856 | 0.15 | 18 | 2.4107 |
73
+ | 2.4702 | 0.16 | 19 | 2.4101 |
74
+ | 2.4401 | 0.16 | 20 | 2.4101 |
75
+ | 2.4957 | 0.17 | 21 | 2.4074 |
76
+ | 2.4915 | 0.18 | 22 | 2.4044 |
77
+ | 2.3463 | 0.19 | 23 | 2.4051 |
78
+ | 2.2404 | 0.2 | 24 | 2.4044 |
79
+ | 2.469 | 0.21 | 25 | 2.4023 |
80
+ | 2.4707 | 0.21 | 26 | 2.4002 |
81
+ | 2.4167 | 0.22 | 27 | 2.4003 |
82
+ | 2.3213 | 0.23 | 28 | 2.3969 |
83
+ | 2.5036 | 0.24 | 29 | 2.3942 |
84
+ | 2.3594 | 0.25 | 30 | 2.3920 |
85
+ | 2.3971 | 0.26 | 31 | 2.3910 |
86
+ | 2.3863 | 0.26 | 32 | 2.3880 |
87
+ | 2.4845 | 0.27 | 33 | 2.3836 |
88
+ | 2.3076 | 0.28 | 34 | 2.3844 |
89
+ | 2.4448 | 0.29 | 35 | 2.3810 |
90
+ | 2.3576 | 0.3 | 36 | 2.3789 |
91
+ | 2.3279 | 0.3 | 37 | 2.3744 |
92
+ | 2.4572 | 0.31 | 38 | 2.3744 |
93
+ | 2.4527 | 0.32 | 39 | 2.3702 |
94
+ | 2.5135 | 0.33 | 40 | 2.3645 |
95
+ | 2.3704 | 0.34 | 41 | 2.3638 |
96
+ | 2.4071 | 0.35 | 42 | 2.3586 |
97
+ | 2.3059 | 0.35 | 43 | 2.3567 |
98
+ | 2.4828 | 0.36 | 44 | 2.3525 |
99
+ | 2.3812 | 0.37 | 45 | 2.3474 |
100
+ | 2.3066 | 0.38 | 46 | 2.3432 |
101
+ | 2.3644 | 0.39 | 47 | 2.3396 |
102
+ | 2.3855 | 0.4 | 48 | 2.3357 |
103
+ | 2.3533 | 0.4 | 49 | 2.3299 |
104
+ | 2.3486 | 0.41 | 50 | 2.3252 |
105
+ | 2.3527 | 0.42 | 51 | 2.3194 |
106
+ | 2.3593 | 0.43 | 52 | 2.3150 |
107
+ | 2.3743 | 0.44 | 53 | 2.3117 |
108
+ | 2.5021 | 0.44 | 54 | 2.3026 |
109
+ | 2.3785 | 0.45 | 55 | 2.2974 |
110
+ | 2.17 | 0.46 | 56 | 2.2931 |
111
+ | 2.2599 | 0.47 | 57 | 2.2851 |
112
+ | 2.2211 | 0.48 | 58 | 2.2794 |
113
+ | 2.2464 | 0.49 | 59 | 2.2716 |
114
+ | 2.2058 | 0.49 | 60 | 2.2622 |
115
+ | 2.3164 | 0.5 | 61 | 2.2560 |
116
+ | 2.3093 | 0.51 | 62 | 2.2445 |
117
+ | 2.2846 | 0.52 | 63 | 2.2353 |
118
+ | 2.1138 | 0.53 | 64 | 2.2271 |
119
+ | 2.3286 | 0.53 | 65 | 2.2170 |
120
+ | 2.1988 | 0.54 | 66 | 2.2077 |
121
+ | 2.2598 | 0.55 | 67 | 2.1968 |
122
+ | 2.2303 | 0.56 | 68 | 2.1880 |
123
+ | 2.2419 | 0.57 | 69 | 2.1790 |
124
+ | 2.2628 | 0.58 | 70 | 2.1689 |
125
+ | 2.1922 | 0.58 | 71 | 2.1573 |
126
+ | 2.2353 | 0.59 | 72 | 2.1498 |
127
+ | 2.2111 | 0.6 | 73 | 2.1376 |
128
+ | 2.1128 | 0.61 | 74 | 2.1271 |
129
+ | 2.2167 | 0.62 | 75 | 2.1184 |
130
+ | 2.1878 | 0.63 | 76 | 2.1085 |
131
+ | 2.1391 | 0.63 | 77 | 2.0950 |
132
+ | 2.1336 | 0.64 | 78 | 2.0818 |
133
+ | 2.1266 | 0.65 | 79 | 2.0730 |
134
+ | 1.9823 | 0.66 | 80 | 2.0634 |
135
+ | 2.1003 | 0.67 | 81 | 2.0490 |
136
+ | 2.0681 | 0.67 | 82 | 2.0353 |
137
+ | 2.1475 | 0.68 | 83 | 2.0218 |
138
+ | 1.996 | 0.69 | 84 | 2.0082 |
139
+ | 1.9981 | 0.7 | 85 | 1.9951 |
140
+ | 2.0693 | 0.71 | 86 | 1.9823 |
141
+ | 1.9524 | 0.72 | 87 | 1.9719 |
142
+ | 2.058 | 0.72 | 88 | 1.9587 |
143
+ | 1.9211 | 0.73 | 89 | 1.9455 |
144
+ | 1.9496 | 0.74 | 90 | 1.9311 |
145
+ | 1.9495 | 0.75 | 91 | 1.9200 |
146
+ | 2.0249 | 0.76 | 92 | 1.9062 |
147
+ | 1.9044 | 0.77 | 93 | 1.8940 |
148
+ | 1.9373 | 0.77 | 94 | 1.8817 |
149
+ | 1.8604 | 0.78 | 95 | 1.8675 |
150
+ | 1.8957 | 0.79 | 96 | 1.8584 |
151
+ | 1.8673 | 0.8 | 97 | 1.8471 |
152
+ | 1.9002 | 0.81 | 98 | 1.8337 |
153
+ | 1.9025 | 0.81 | 99 | 1.8226 |
154
+ | 1.8356 | 0.82 | 100 | 1.8099 |
155
+ | 1.7723 | 0.83 | 101 | 1.7994 |
156
+ | 1.7628 | 0.84 | 102 | 1.7902 |
157
+ | 1.7014 | 0.85 | 103 | 1.7788 |
158
+ | 1.7383 | 0.86 | 104 | 1.7678 |
159
+ | 1.7647 | 0.86 | 105 | 1.7581 |
160
+ | 1.7835 | 0.87 | 106 | 1.7466 |
161
+ | 1.7645 | 0.88 | 107 | 1.7367 |
162
+ | 1.7654 | 0.89 | 108 | 1.7267 |
163
+ | 1.8344 | 0.9 | 109 | 1.7173 |
164
+ | 1.6528 | 0.91 | 110 | 1.7068 |
165
+ | 1.676 | 0.91 | 111 | 1.6989 |
166
+ | 1.5894 | 0.92 | 112 | 1.6882 |
167
+ | 1.6154 | 0.93 | 113 | 1.6778 |
168
+ | 1.609 | 0.94 | 114 | 1.6697 |
169
+ | 1.6803 | 0.95 | 115 | 1.6592 |
170
+ | 1.6487 | 0.95 | 116 | 1.6484 |
171
+ | 1.6905 | 0.96 | 117 | 1.6403 |
172
+ | 1.6258 | 0.97 | 118 | 1.6300 |
173
+ | 1.5744 | 0.98 | 119 | 1.6189 |
174
+ | 1.4791 | 0.99 | 120 | 1.6088 |
175
+ | 1.6177 | 1.0 | 121 | 1.5975 |
176
+ | 1.582 | 1.0 | 122 | 1.5860 |
177
+ | 1.5378 | 1.01 | 123 | 1.5760 |
178
+ | 1.5691 | 1.02 | 124 | 1.5658 |
179
+ | 1.5387 | 1.03 | 125 | 1.5540 |
180
+ | 1.5527 | 1.04 | 126 | 1.5429 |
181
+ | 1.4642 | 1.05 | 127 | 1.5316 |
182
+ | 1.4867 | 1.05 | 128 | 1.5199 |
183
+ | 1.5204 | 1.06 | 129 | 1.5075 |
184
+ | 1.5997 | 1.07 | 130 | 1.4962 |
185
+ | 1.4419 | 1.08 | 131 | 1.4833 |
186
+ | 1.5799 | 1.09 | 132 | 1.4718 |
187
+ | 1.5103 | 1.09 | 133 | 1.4584 |
188
+ | 1.5444 | 1.1 | 134 | 1.4472 |
189
+ | 1.4835 | 1.11 | 135 | 1.4351 |
190
+ | 1.4326 | 1.12 | 136 | 1.4213 |
191
+ | 1.4079 | 1.13 | 137 | 1.4088 |
192
+ | 1.5206 | 1.14 | 138 | 1.3971 |
193
+ | 1.3868 | 1.14 | 139 | 1.3822 |
194
+ | 1.4778 | 1.15 | 140 | 1.3702 |
195
+ | 1.4627 | 1.16 | 141 | 1.3558 |
196
+ | 1.3555 | 1.17 | 142 | 1.3444 |
197
+ | 1.3143 | 1.18 | 143 | 1.3323 |
198
+ | 1.3754 | 1.19 | 144 | 1.3192 |
199
+ | 1.2488 | 1.19 | 145 | 1.3082 |
200
+ | 1.2821 | 1.2 | 146 | 1.2969 |
201
+ | 1.2804 | 1.21 | 147 | 1.2856 |
202
+ | 1.233 | 1.22 | 148 | 1.2747 |
203
+ | 1.3502 | 1.23 | 149 | 1.2633 |
204
+ | 1.2224 | 1.23 | 150 | 1.2536 |
205
+ | 1.199 | 1.24 | 151 | 1.2419 |
206
+ | 1.1749 | 1.25 | 152 | 1.2321 |
207
+ | 1.305 | 1.26 | 153 | 1.2220 |
208
+ | 1.1391 | 1.27 | 154 | 1.2100 |
209
+ | 1.3063 | 1.28 | 155 | 1.1990 |
210
+ | 1.2402 | 1.28 | 156 | 1.1878 |
211
+ | 1.1104 | 1.29 | 157 | 1.1772 |
212
+ | 1.24 | 1.3 | 158 | 1.1670 |
213
+ | 1.0549 | 1.31 | 159 | 1.1555 |
214
+ | 1.1417 | 1.32 | 160 | 1.1452 |
215
+ | 1.0898 | 1.33 | 161 | 1.1351 |
216
+ | 1.1035 | 1.33 | 162 | 1.1259 |
217
+ | 1.1088 | 1.34 | 163 | 1.1158 |
218
+ | 1.086 | 1.35 | 164 | 1.1069 |
219
+ | 1.15 | 1.36 | 165 | 1.0975 |
220
+ | 1.0394 | 1.37 | 166 | 1.0888 |
221
+ | 1.1268 | 1.37 | 167 | 1.0806 |
222
+ | 1.0803 | 1.38 | 168 | 1.0710 |
223
+ | 1.0198 | 1.39 | 169 | 1.0624 |
224
+ | 1.0765 | 1.4 | 170 | 1.0534 |
225
+ | 1.0318 | 1.41 | 171 | 1.0447 |
226
+ | 1.0098 | 1.42 | 172 | 1.0369 |
227
+ | 1.0013 | 1.42 | 173 | 1.0284 |
228
+ | 0.9773 | 1.43 | 174 | 1.0210 |
229
+ | 1.0233 | 1.44 | 175 | 1.0130 |
230
+ | 0.985 | 1.45 | 176 | 1.0053 |
231
+ | 0.9806 | 1.46 | 177 | 0.9983 |
232
+ | 1.0393 | 1.47 | 178 | 0.9906 |
233
+ | 0.9191 | 1.47 | 179 | 0.9844 |
234
+ | 0.9454 | 1.48 | 180 | 0.9781 |
235
+ | 0.9354 | 1.49 | 181 | 0.9710 |
236
+ | 0.9598 | 1.5 | 182 | 0.9658 |
237
+ | 1.0652 | 1.51 | 183 | 0.9584 |
238
+ | 0.9002 | 1.51 | 184 | 0.9538 |
239
+ | 0.9477 | 1.52 | 185 | 0.9472 |
240
+ | 0.9203 | 1.53 | 186 | 0.9414 |
241
+ | 0.8837 | 1.54 | 187 | 0.9361 |
242
+ | 0.91 | 1.55 | 188 | 0.9313 |
243
+ | 0.8616 | 1.56 | 189 | 0.9258 |
244
+ | 0.9201 | 1.56 | 190 | 0.9205 |
245
+ | 0.9408 | 1.57 | 191 | 0.9147 |
246
+ | 0.9274 | 1.58 | 192 | 0.9093 |
247
+ | 1.0009 | 1.59 | 193 | 0.9064 |
248
+ | 0.9202 | 1.6 | 194 | 0.9009 |
249
+ | 0.9886 | 1.6 | 195 | 0.8959 |
250
+ | 0.9289 | 1.61 | 196 | 0.8913 |
251
+ | 0.9603 | 1.62 | 197 | 0.8875 |
252
+ | 0.9138 | 1.63 | 198 | 0.8837 |
253
+ | 0.8794 | 1.64 | 199 | 0.8787 |
254
+ | 0.8315 | 1.65 | 200 | 0.8750 |
255
+ | 0.8745 | 1.65 | 201 | 0.8705 |
256
+ | 1.013 | 1.66 | 202 | 0.8673 |
257
+ | 0.8565 | 1.67 | 203 | 0.8634 |
258
+ | 0.9121 | 1.68 | 204 | 0.8596 |
259
+ | 0.7825 | 1.69 | 205 | 0.8558 |
260
+ | 0.9171 | 1.7 | 206 | 0.8524 |
261
+ | 0.7595 | 1.7 | 207 | 0.8488 |
262
+ | 0.8611 | 1.71 | 208 | 0.8453 |
263
+ | 0.7212 | 1.72 | 209 | 0.8421 |
264
+ | 0.8745 | 1.73 | 210 | 0.8389 |
265
+ | 0.93 | 1.74 | 211 | 0.8354 |
266
+ | 0.9183 | 1.74 | 212 | 0.8321 |
267
+ | 0.8482 | 1.75 | 213 | 0.8293 |
268
+ | 0.8155 | 1.76 | 214 | 0.8256 |
269
+ | 0.9113 | 1.77 | 215 | 0.8224 |
270
+ | 0.8009 | 1.78 | 216 | 0.8190 |
271
+ | 0.6555 | 1.79 | 217 | 0.8165 |
272
+ | 0.7727 | 1.79 | 218 | 0.8133 |
273
+ | 0.7987 | 1.8 | 219 | 0.8105 |
274
+ | 0.7794 | 1.81 | 220 | 0.8074 |
275
+ | 0.8248 | 1.82 | 221 | 0.8043 |
276
+ | 0.7818 | 1.83 | 222 | 0.8020 |
277
+ | 0.741 | 1.84 | 223 | 0.7995 |
278
+ | 0.6907 | 1.84 | 224 | 0.7969 |
279
+ | 0.789 | 1.85 | 225 | 0.7938 |
280
+ | 0.7101 | 1.86 | 226 | 0.7910 |
281
+ | 0.7178 | 1.87 | 227 | 0.7887 |
282
+ | 0.7109 | 1.88 | 228 | 0.7865 |
283
+ | 0.6699 | 1.88 | 229 | 0.7838 |
284
+ | 0.8443 | 1.89 | 230 | 0.7814 |
285
+ | 0.7397 | 1.9 | 231 | 0.7789 |
286
+ | 0.7888 | 1.91 | 232 | 0.7760 |
287
+ | 0.7725 | 1.92 | 233 | 0.7735 |
288
+ | 0.7797 | 1.93 | 234 | 0.7707 |
289
+ | 0.7988 | 1.93 | 235 | 0.7678 |
290
+ | 0.7548 | 1.94 | 236 | 0.7660 |
291
+ | 0.904 | 1.95 | 237 | 0.7631 |
292
+ | 0.8183 | 1.96 | 238 | 0.7616 |
293
+ | 0.8292 | 1.97 | 239 | 0.7582 |
294
+ | 0.7144 | 1.98 | 240 | 0.7561 |
295
+ | 0.753 | 1.98 | 241 | 0.7538 |
296
+ | 0.7629 | 1.99 | 242 | 0.7525 |
297
+ | 0.8713 | 2.0 | 243 | 0.7497 |
298
+ | 0.7355 | 2.01 | 244 | 0.7477 |
299
+ | 0.6998 | 2.02 | 245 | 0.7459 |
300
+ | 0.7567 | 2.02 | 246 | 0.7438 |
301
+ | 0.6594 | 2.03 | 247 | 0.7420 |
302
+ | 0.7124 | 2.04 | 248 | 0.7405 |
303
+ | 0.9188 | 2.05 | 249 | 0.7380 |
304
+ | 0.7406 | 2.06 | 250 | 0.7364 |
305
+ | 0.7091 | 2.07 | 251 | 0.7341 |
306
+ | 0.8144 | 2.07 | 252 | 0.7319 |
307
+ | 0.7122 | 2.08 | 253 | 0.7307 |
308
+ | 0.7504 | 2.09 | 254 | 0.7291 |
309
+ | 0.7409 | 2.1 | 255 | 0.7276 |
310
+ | 0.7844 | 2.11 | 256 | 0.7258 |
311
+ | 0.8328 | 2.12 | 257 | 0.7234 |
312
+ | 0.7149 | 2.12 | 258 | 0.7221 |
313
+ | 0.7063 | 2.13 | 259 | 0.7205 |
314
+ | 0.6629 | 2.14 | 260 | 0.7195 |
315
+ | 0.5896 | 2.15 | 261 | 0.7177 |
316
+ | 0.734 | 2.16 | 262 | 0.7165 |
317
+ | 0.7293 | 2.16 | 263 | 0.7157 |
318
+ | 0.6819 | 2.17 | 264 | 0.7142 |
319
+ | 0.6928 | 2.18 | 265 | 0.7133 |
320
+ | 0.6026 | 2.19 | 266 | 0.7119 |
321
+ | 0.6704 | 2.2 | 267 | 0.7114 |
322
+ | 0.7118 | 2.21 | 268 | 0.7099 |
323
+ | 0.8447 | 2.21 | 269 | 0.7084 |
324
+ | 0.6857 | 2.22 | 270 | 0.7075 |
325
+ | 0.7257 | 2.23 | 271 | 0.7066 |
326
+ | 0.6884 | 2.24 | 272 | 0.7058 |
327
+ | 0.5883 | 2.25 | 273 | 0.7047 |
328
+ | 0.6798 | 2.26 | 274 | 0.7036 |
329
+ | 0.6575 | 2.26 | 275 | 0.7024 |
330
+ | 0.627 | 2.27 | 276 | 0.7017 |
331
+ | 0.7029 | 2.28 | 277 | 0.7016 |
332
+ | 0.7248 | 2.29 | 278 | 0.7009 |
333
+ | 0.6947 | 2.3 | 279 | 0.6996 |
334
+ | 0.708 | 2.3 | 280 | 0.6991 |
335
+ | 0.5384 | 2.31 | 281 | 0.6981 |
336
+ | 0.5539 | 2.32 | 282 | 0.6975 |
337
+ | 0.6751 | 2.33 | 283 | 0.6962 |
338
+ | 0.5809 | 2.34 | 284 | 0.6957 |
339
+ | 0.7105 | 2.35 | 285 | 0.6952 |
340
+ | 0.735 | 2.35 | 286 | 0.6945 |
341
+ | 0.7564 | 2.36 | 287 | 0.6936 |
342
+ | 0.732 | 2.37 | 288 | 0.6925 |
343
+ | 0.6892 | 2.38 | 289 | 0.6919 |
344
+ | 0.6454 | 2.39 | 290 | 0.6910 |
345
+ | 0.6919 | 2.4 | 291 | 0.6901 |
346
+ | 0.6842 | 2.4 | 292 | 0.6893 |
347
+ | 0.6044 | 2.41 | 293 | 0.6889 |
348
+ | 0.5893 | 2.42 | 294 | 0.6885 |
349
+ | 0.7235 | 2.43 | 295 | 0.6875 |
350
+ | 0.7216 | 2.44 | 296 | 0.6873 |
351
+ | 0.7677 | 2.44 | 297 | 0.6865 |
352
+ | 0.5953 | 2.45 | 298 | 0.6862 |
353
+ | 0.8029 | 2.46 | 299 | 0.6853 |
354
+ | 0.6425 | 2.47 | 300 | 0.6846 |
355
+ | 0.5764 | 2.48 | 301 | 0.6846 |
356
+ | 0.7721 | 2.49 | 302 | 0.6831 |
357
+ | 0.7315 | 2.49 | 303 | 0.6831 |
358
+ | 0.6483 | 2.5 | 304 | 0.6829 |
359
+ | 0.8087 | 2.51 | 305 | 0.6825 |
360
+ | 0.6676 | 2.52 | 306 | 0.6816 |
361
+ | 0.6153 | 2.53 | 307 | 0.6813 |
362
+ | 0.6388 | 2.53 | 308 | 0.6812 |
363
+ | 0.6322 | 2.54 | 309 | 0.6803 |
364
+ | 0.5539 | 2.55 | 310 | 0.6803 |
365
+ | 0.6124 | 2.56 | 311 | 0.6796 |
366
+ | 0.6905 | 2.57 | 312 | 0.6791 |
367
+ | 0.6522 | 2.58 | 313 | 0.6782 |
368
+ | 0.5722 | 2.58 | 314 | 0.6784 |
369
+ | 0.6271 | 2.59 | 315 | 0.6776 |
370
+ | 0.6927 | 2.6 | 316 | 0.6783 |
371
+ | 0.733 | 2.61 | 317 | 0.6768 |
372
+ | 0.6622 | 2.62 | 318 | 0.6765 |
373
+ | 0.7042 | 2.63 | 319 | 0.6765 |
374
+ | 0.8197 | 2.63 | 320 | 0.6763 |
375
+ | 0.8398 | 2.64 | 321 | 0.6758 |
376
+ | 0.6703 | 2.65 | 322 | 0.6756 |
377
+ | 0.6722 | 2.66 | 323 | 0.6750 |
378
+ | 0.7457 | 2.67 | 324 | 0.6748 |
379
+ | 0.6385 | 2.67 | 325 | 0.6746 |
380
+ | 0.557 | 2.68 | 326 | 0.6743 |
381
+ | 0.6835 | 2.69 | 327 | 0.6739 |
382
+ | 0.6078 | 2.7 | 328 | 0.6735 |
383
+ | 0.8021 | 2.71 | 329 | 0.6733 |
384
+ | 0.5652 | 2.72 | 330 | 0.6732 |
385
+ | 0.7898 | 2.72 | 331 | 0.6723 |
386
+ | 0.5717 | 2.73 | 332 | 0.6720 |
387
+ | 0.6912 | 2.74 | 333 | 0.6718 |
388
+ | 0.641 | 2.75 | 334 | 0.6717 |
389
+ | 0.6551 | 2.76 | 335 | 0.6714 |
390
+ | 0.7743 | 2.77 | 336 | 0.6706 |
391
+ | 0.631 | 2.77 | 337 | 0.6710 |
392
+ | 0.6843 | 2.78 | 338 | 0.6703 |
393
+ | 0.6913 | 2.79 | 339 | 0.6701 |
394
+ | 0.6482 | 2.8 | 340 | 0.6697 |
395
+ | 0.6251 | 2.81 | 341 | 0.6696 |
396
+ | 0.6712 | 2.81 | 342 | 0.6694 |
397
+ | 0.6543 | 2.82 | 343 | 0.6693 |
398
+ | 0.7393 | 2.83 | 344 | 0.6687 |
399
+ | 0.7283 | 2.84 | 345 | 0.6686 |
400
+ | 0.673 | 2.85 | 346 | 0.6686 |
401
+ | 0.6263 | 2.86 | 347 | 0.6680 |
402
+ | 0.6574 | 2.86 | 348 | 0.6678 |
403
+ | 0.7178 | 2.87 | 349 | 0.6677 |
404
+ | 0.6941 | 2.88 | 350 | 0.6673 |
405
+ | 0.5781 | 2.89 | 351 | 0.6675 |
406
+ | 0.6024 | 2.9 | 352 | 0.6671 |
407
+ | 0.6324 | 2.91 | 353 | 0.6667 |
408
+ | 0.7445 | 2.91 | 354 | 0.6663 |
409
+ | 0.5899 | 2.92 | 355 | 0.6664 |
410
+ | 0.7318 | 2.93 | 356 | 0.6659 |
411
+ | 0.7341 | 2.94 | 357 | 0.6656 |
412
+ | 0.7439 | 2.95 | 358 | 0.6656 |
413
+ | 0.7061 | 2.95 | 359 | 0.6652 |
414
+ | 0.7121 | 2.96 | 360 | 0.6649 |
415
+ | 0.6754 | 2.97 | 361 | 0.6649 |
416
+ | 0.7367 | 2.98 | 362 | 0.6646 |
417
+ | 0.7033 | 2.99 | 363 | 0.6646 |
418
+ | 0.6652 | 3.0 | 364 | 0.6640 |
419
+ | 0.707 | 3.0 | 365 | 0.6639 |
420
+ | 0.5992 | 3.01 | 366 | 0.6636 |
421
+ | 0.6483 | 3.02 | 367 | 0.6633 |
422
+ | 0.8483 | 3.03 | 368 | 0.6623 |
423
+ | 0.7052 | 3.04 | 369 | 0.6628 |
424
+ | 0.7748 | 3.05 | 370 | 0.6624 |
425
+ | 0.7242 | 3.05 | 371 | 0.6621 |
426
+ | 0.7835 | 3.06 | 372 | 0.6621 |
427
+ | 0.6273 | 3.07 | 373 | 0.6621 |
428
+ | 0.6937 | 3.08 | 374 | 0.6617 |
429
+ | 0.7308 | 3.09 | 375 | 0.6615 |
430
+ | 0.6431 | 3.09 | 376 | 0.6613 |
431
+ | 0.6486 | 3.1 | 377 | 0.6612 |
432
+ | 0.6671 | 3.11 | 378 | 0.6613 |
433
+ | 0.6046 | 3.12 | 379 | 0.6605 |
434
+ | 0.5741 | 3.13 | 380 | 0.6605 |
435
+ | 0.6746 | 3.14 | 381 | 0.6606 |
436
+ | 0.6525 | 3.14 | 382 | 0.6604 |
437
+ | 0.6483 | 3.15 | 383 | 0.6602 |
438
+ | 0.6631 | 3.16 | 384 | 0.6602 |
439
+ | 0.5769 | 3.17 | 385 | 0.6603 |
440
+ | 0.6648 | 3.18 | 386 | 0.6596 |
441
+ | 0.6933 | 3.19 | 387 | 0.6592 |
442
+ | 0.6597 | 3.19 | 388 | 0.6596 |
443
+ | 0.5871 | 3.2 | 389 | 0.6596 |
444
+ | 0.5976 | 3.21 | 390 | 0.6593 |
445
+ | 0.6025 | 3.22 | 391 | 0.6591 |
446
+ | 0.7157 | 3.23 | 392 | 0.6588 |
447
+ | 0.6419 | 3.23 | 393 | 0.6587 |
448
+ | 0.5579 | 3.24 | 394 | 0.6589 |
449
+ | 0.7142 | 3.25 | 395 | 0.6588 |
450
+ | 0.5773 | 3.26 | 396 | 0.6581 |
451
+ | 0.5624 | 3.27 | 397 | 0.6583 |
452
+ | 0.6029 | 3.28 | 398 | 0.6579 |
453
+ | 0.6642 | 3.28 | 399 | 0.6582 |
454
+ | 0.7 | 3.29 | 400 | 0.6579 |
455
+ | 0.7918 | 3.3 | 401 | 0.6579 |
456
+ | 0.563 | 3.31 | 402 | 0.6577 |
457
+ | 0.7208 | 3.32 | 403 | 0.6575 |
458
+ | 0.6769 | 3.33 | 404 | 0.6570 |
459
+ | 0.7093 | 3.33 | 405 | 0.6571 |
460
+ | 0.5287 | 3.34 | 406 | 0.6570 |
461
+ | 0.5828 | 3.35 | 407 | 0.6572 |
462
+ | 0.5703 | 3.36 | 408 | 0.6566 |
463
+ | 0.6647 | 3.37 | 409 | 0.6566 |
464
+ | 0.6879 | 3.37 | 410 | 0.6568 |
465
+ | 0.7325 | 3.38 | 411 | 0.6566 |
466
+ | 0.6021 | 3.39 | 412 | 0.6565 |
467
+ | 0.6777 | 3.4 | 413 | 0.6565 |
468
+ | 0.6057 | 3.41 | 414 | 0.6560 |
469
+ | 0.5996 | 3.42 | 415 | 0.6558 |
470
+ | 0.6841 | 3.42 | 416 | 0.6556 |
471
+ | 0.6096 | 3.43 | 417 | 0.6557 |
472
+ | 0.6245 | 3.44 | 418 | 0.6559 |
473
+ | 0.664 | 3.45 | 419 | 0.6556 |
474
+ | 0.7183 | 3.46 | 420 | 0.6561 |
475
+ | 0.6449 | 3.47 | 421 | 0.6558 |
476
+ | 0.6497 | 3.47 | 422 | 0.6557 |
477
+ | 0.8151 | 3.48 | 423 | 0.6554 |
478
+ | 0.813 | 3.49 | 424 | 0.6552 |
479
+ | 0.6278 | 3.5 | 425 | 0.6553 |
480
+ | 0.6376 | 3.51 | 426 | 0.6556 |
481
+ | 0.697 | 3.51 | 427 | 0.6554 |
482
+ | 0.628 | 3.52 | 428 | 0.6550 |
483
+ | 0.7049 | 3.53 | 429 | 0.6553 |
484
+ | 0.6641 | 3.54 | 430 | 0.6549 |
485
+ | 0.6465 | 3.55 | 431 | 0.6552 |
486
+ | 0.7366 | 3.56 | 432 | 0.6550 |
487
+ | 0.6325 | 3.56 | 433 | 0.6545 |
488
+ | 0.5621 | 3.57 | 434 | 0.6550 |
489
+ | 0.5846 | 3.58 | 435 | 0.6553 |
490
+ | 0.6516 | 3.59 | 436 | 0.6551 |
491
+ | 0.7258 | 3.6 | 437 | 0.6546 |
492
+ | 0.6027 | 3.6 | 438 | 0.6547 |
493
+ | 0.5344 | 3.61 | 439 | 0.6549 |
494
+ | 0.6988 | 3.62 | 440 | 0.6546 |
495
+ | 0.6863 | 3.63 | 441 | 0.6548 |
496
+ | 0.627 | 3.64 | 442 | 0.6544 |
497
+ | 0.6353 | 3.65 | 443 | 0.6548 |
498
+ | 0.5361 | 3.65 | 444 | 0.6541 |
499
+ | 0.6774 | 3.66 | 445 | 0.6548 |
500
+ | 0.668 | 3.67 | 446 | 0.6546 |
501
+ | 0.544 | 3.68 | 447 | 0.6545 |
502
+ | 0.5683 | 3.69 | 448 | 0.6546 |
503
+ | 0.6955 | 3.7 | 449 | 0.6543 |
504
+ | 0.6316 | 3.7 | 450 | 0.6543 |
505
+ | 0.647 | 3.71 | 451 | 0.6544 |
506
+ | 0.6797 | 3.72 | 452 | 0.6541 |
507
+ | 0.6566 | 3.73 | 453 | 0.6541 |
508
+ | 0.6585 | 3.74 | 454 | 0.6544 |
509
+ | 0.6632 | 3.74 | 455 | 0.6541 |
510
+ | 0.5798 | 3.75 | 456 | 0.6540 |
511
+ | 0.6417 | 3.76 | 457 | 0.6540 |
512
+ | 0.706 | 3.77 | 458 | 0.6538 |
513
+ | 0.6709 | 3.78 | 459 | 0.6542 |
514
+ | 0.7047 | 3.79 | 460 | 0.6536 |
515
+ | 0.5466 | 3.79 | 461 | 0.6538 |
516
+ | 0.5479 | 3.8 | 462 | 0.6540 |
517
+ | 0.6476 | 3.81 | 463 | 0.6535 |
518
+ | 0.6584 | 3.82 | 464 | 0.6534 |
519
+ | 0.6515 | 3.83 | 465 | 0.6540 |
520
+ | 0.5812 | 3.84 | 466 | 0.6535 |
521
+ | 0.6339 | 3.84 | 467 | 0.6537 |
522
+ | 0.6521 | 3.85 | 468 | 0.6537 |
523
+ | 0.6451 | 3.86 | 469 | 0.6538 |
524
+ | 0.6655 | 3.87 | 470 | 0.6532 |
525
+ | 0.7017 | 3.88 | 471 | 0.6533 |
526
+ | 0.5794 | 3.88 | 472 | 0.6530 |
527
+ | 0.6485 | 3.89 | 473 | 0.6536 |
528
+ | 0.6723 | 3.9 | 474 | 0.6533 |
529
+ | 0.72 | 3.91 | 475 | 0.6534 |
530
+ | 0.6114 | 3.92 | 476 | 0.6535 |
531
+ | 0.596 | 3.93 | 477 | 0.6536 |
532
+ | 0.5961 | 3.93 | 478 | 0.6538 |
533
+ | 0.6629 | 3.94 | 479 | 0.6531 |
534
+ | 0.6682 | 3.95 | 480 | 0.6534 |
535
+ | 0.7007 | 3.96 | 481 | 0.6534 |
536
+ | 0.6594 | 3.97 | 482 | 0.6535 |
537
+ | 0.7607 | 3.98 | 483 | 0.6531 |
538
+ | 0.5735 | 3.98 | 484 | 0.6532 |
539
+ | 0.7111 | 3.99 | 485 | 0.6531 |
540
+ | 0.6498 | 4.0 | 486 | 0.6533 |
541
+ | 0.624 | 4.01 | 487 | 0.6529 |
542
+ | 0.7284 | 4.02 | 488 | 0.6535 |
543
+ | 0.5665 | 4.02 | 489 | 0.6531 |
544
+ | 0.6473 | 4.03 | 490 | 0.6534 |
545
+ | 0.614 | 4.04 | 491 | 0.6534 |
546
+ | 0.6663 | 4.05 | 492 | 0.6528 |
547
+ | 0.6309 | 4.06 | 493 | 0.6527 |
548
+ | 0.6926 | 4.07 | 494 | 0.6530 |
549
+ | 0.6112 | 4.07 | 495 | 0.6531 |
550
+ | 0.6879 | 4.08 | 496 | 0.6526 |
551
+ | 0.6939 | 4.09 | 497 | 0.6529 |
552
+ | 0.7551 | 4.1 | 498 | 0.6530 |
553
+ | 0.6085 | 4.11 | 499 | 0.6530 |
554
+ | 0.6741 | 4.12 | 500 | 0.6533 |
555
+ | 0.5913 | 4.12 | 501 | 0.6529 |
556
+ | 0.6337 | 4.13 | 502 | 0.6529 |
557
+ | 0.6061 | 4.14 | 503 | 0.6527 |
558
+ | 0.6511 | 4.15 | 504 | 0.6529 |
559
+ | 0.6358 | 4.16 | 505 | 0.6531 |
560
+ | 0.6537 | 4.16 | 506 | 0.6527 |
561
+ | 0.5757 | 4.17 | 507 | 0.6532 |
562
+ | 0.6143 | 4.18 | 508 | 0.6529 |
563
+ | 0.5723 | 4.19 | 509 | 0.6530 |
564
+ | 0.5647 | 4.2 | 510 | 0.6528 |
565
+ | 0.5878 | 4.21 | 511 | 0.6531 |
566
+ | 0.6119 | 4.21 | 512 | 0.6527 |
567
+ | 0.743 | 4.22 | 513 | 0.6530 |
568
+ | 0.6942 | 4.23 | 514 | 0.6528 |
569
+ | 0.5967 | 4.24 | 515 | 0.6527 |
570
+ | 0.6869 | 4.25 | 516 | 0.6530 |
571
+ | 0.62 | 4.26 | 517 | 0.6529 |
572
+ | 0.7596 | 4.26 | 518 | 0.6530 |
573
+ | 0.6483 | 4.27 | 519 | 0.6530 |
574
+ | 0.6449 | 4.28 | 520 | 0.6527 |
575
+ | 0.56 | 4.29 | 521 | 0.6529 |
576
+ | 0.673 | 4.3 | 522 | 0.6527 |
577
+ | 0.5469 | 4.3 | 523 | 0.6527 |
578
+ | 0.6084 | 4.31 | 524 | 0.6528 |
579
+ | 0.5118 | 4.32 | 525 | 0.6527 |
580
+ | 0.7318 | 4.33 | 526 | 0.6529 |
581
+ | 0.7787 | 4.34 | 527 | 0.6525 |
582
+ | 0.7177 | 4.35 | 528 | 0.6532 |
583
+ | 0.6294 | 4.35 | 529 | 0.6531 |
584
+ | 0.6758 | 4.36 | 530 | 0.6527 |
585
+ | 0.6679 | 4.37 | 531 | 0.6526 |
586
+ | 0.5373 | 4.38 | 532 | 0.6525 |
587
+ | 0.6655 | 4.39 | 533 | 0.6529 |
588
+ | 0.6738 | 4.4 | 534 | 0.6527 |
589
+ | 0.6849 | 4.4 | 535 | 0.6528 |
590
+ | 0.5894 | 4.41 | 536 | 0.6530 |
591
+ | 0.7516 | 4.42 | 537 | 0.6533 |
592
+ | 0.7417 | 4.43 | 538 | 0.6530 |
593
+ | 0.6239 | 4.44 | 539 | 0.6529 |
594
+ | 0.6543 | 4.44 | 540 | 0.6528 |
595
+ | 0.6201 | 4.45 | 541 | 0.6529 |
596
+ | 0.6552 | 4.46 | 542 | 0.6528 |
597
+ | 0.5647 | 4.47 | 543 | 0.6529 |
598
+ | 0.6798 | 4.48 | 544 | 0.6530 |
599
+ | 0.6152 | 4.49 | 545 | 0.6528 |
600
+ | 0.7099 | 4.49 | 546 | 0.6531 |
601
+ | 0.7073 | 4.5 | 547 | 0.6528 |
602
+ | 0.76 | 4.51 | 548 | 0.6531 |
603
+ | 0.7266 | 4.52 | 549 | 0.6526 |
604
+ | 0.7659 | 4.53 | 550 | 0.6527 |
605
+ | 0.7033 | 4.53 | 551 | 0.6532 |
606
+ | 0.6679 | 4.54 | 552 | 0.6534 |
607
+ | 0.5671 | 4.55 | 553 | 0.6533 |
608
+ | 0.6845 | 4.56 | 554 | 0.6527 |
609
+ | 0.655 | 4.57 | 555 | 0.6524 |
610
+ | 0.7154 | 4.58 | 556 | 0.6526 |
611
+ | 0.7778 | 4.58 | 557 | 0.6524 |
612
+ | 0.6404 | 4.59 | 558 | 0.6524 |
613
+ | 0.6133 | 4.6 | 559 | 0.6526 |
614
+ | 0.6241 | 4.61 | 560 | 0.6525 |
615
+ | 0.6255 | 4.62 | 561 | 0.6527 |
616
+ | 0.5877 | 4.63 | 562 | 0.6526 |
617
+ | 0.7624 | 4.63 | 563 | 0.6526 |
618
+ | 0.613 | 4.64 | 564 | 0.6522 |
619
+ | 0.6014 | 4.65 | 565 | 0.6524 |
620
+ | 0.6217 | 4.66 | 566 | 0.6525 |
621
+ | 0.5651 | 4.67 | 567 | 0.6525 |
622
+ | 0.7227 | 4.67 | 568 | 0.6526 |
623
+ | 0.6247 | 4.68 | 569 | 0.6525 |
624
+ | 0.6886 | 4.69 | 570 | 0.6524 |
625
+ | 0.6894 | 4.7 | 571 | 0.6524 |
626
+ | 0.6543 | 4.71 | 572 | 0.6525 |
627
+ | 0.5932 | 4.72 | 573 | 0.6522 |
628
+ | 0.6069 | 4.72 | 574 | 0.6523 |
629
+ | 0.614 | 4.73 | 575 | 0.6525 |
630
+ | 0.5748 | 4.74 | 576 | 0.6526 |
631
+ | 0.5907 | 4.75 | 577 | 0.6523 |
632
+ | 0.6707 | 4.76 | 578 | 0.6526 |
633
+ | 0.642 | 4.77 | 579 | 0.6525 |
634
+ | 0.6228 | 4.77 | 580 | 0.6522 |
635
+ | 0.6178 | 4.78 | 581 | 0.6525 |
636
+ | 0.5958 | 4.79 | 582 | 0.6528 |
637
+ | 0.6532 | 4.8 | 583 | 0.6527 |
638
+ | 0.5752 | 4.81 | 584 | 0.6526 |
639
+ | 0.7058 | 4.81 | 585 | 0.6525 |
640
+ | 0.642 | 4.82 | 586 | 0.6526 |
641
+ | 0.6599 | 4.83 | 587 | 0.6525 |
642
+ | 0.7673 | 4.84 | 588 | 0.6526 |
643
+ | 0.6626 | 4.85 | 589 | 0.6525 |
644
+ | 0.5326 | 4.86 | 590 | 0.6525 |
645
+ | 0.6512 | 4.86 | 591 | 0.6524 |
646
+ | 0.5914 | 4.87 | 592 | 0.6524 |
647
+ | 0.6415 | 4.88 | 593 | 0.6523 |
648
+ | 0.7693 | 4.89 | 594 | 0.6523 |
649
+ | 0.6389 | 4.9 | 595 | 0.6524 |
650
+ | 0.6151 | 4.91 | 596 | 0.6524 |
651
+ | 0.6561 | 4.91 | 597 | 0.6524 |
652
+ | 0.6443 | 4.92 | 598 | 0.6524 |
653
+ | 0.6596 | 4.93 | 599 | 0.6524 |
654
+ | 0.6413 | 4.94 | 600 | 0.6524 |
655
+ | 0.6235 | 4.95 | 601 | 0.6524 |
656
+ | 0.598 | 4.95 | 602 | 0.6524 |
657
+ | 0.7232 | 4.96 | 603 | 0.6524 |
658
+ | 0.6172 | 4.97 | 604 | 0.6524 |
659
+ | 0.7063 | 4.98 | 605 | 0.6524 |
660
+
661
+
662
  ### Framework versions
663
 
664
  - PEFT 0.9.0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5c21acb95427422a0d00d66b22170f669011165647db1883b7334dbf9db053c
3
  size 2264400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b4258089eee4205e1d39effe7e3cfb2fe5e459bca01754c576dca33f8dc64e3
3
  size 2264400
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 1024,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3ee5d8c8eaa58183a4868661183f09d364aea58e8de6a9118175958da40cf70
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb800b9ad7afa7c74f06e675e56b86098ca6d75ca8d36a334b39c31ff4dea80
3
  size 4920