End of training
Browse files- README.md +52 -52
- config.json +2 -2
- model.safetensors +2 -2
- runs/Feb28_17-27-44_3897ec21fae5/events.out.tfevents.1709141265.3897ec21fae5.75144.2 +2 -2
- runs/Feb28_17-51-03_3897ec21fae5/events.out.tfevents.1709142663.3897ec21fae5.81816.0 +3 -0
- runs/Feb28_18-13-19_3897ec21fae5/events.out.tfevents.1709144000.3897ec21fae5.81816.1 +3 -0
- tokenizer.json +72 -179
- training_args.bin +1 -1
README.md
CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Loss:
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -32,7 +32,7 @@ More information needed
|
|
32 |
### Training hyperparameters
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
-
- learning_rate: 0.
|
36 |
- train_batch_size: 512
|
37 |
- eval_batch_size: 512
|
38 |
- seed: 42
|
@@ -44,56 +44,56 @@ The following hyperparameters were used during training:
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
-
| 3.
|
48 |
-
|
|
49 |
-
|
|
50 |
-
|
|
51 |
-
|
|
52 |
-
|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
65 |
-
|
|
66 |
-
|
|
67 |
-
|
|
68 |
-
|
|
69 |
-
|
|
70 |
-
|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
76 |
-
|
|
77 |
-
|
|
78 |
-
|
|
79 |
-
|
|
80 |
-
|
|
81 |
-
|
|
82 |
-
|
|
83 |
-
|
|
84 |
-
|
|
85 |
-
|
|
86 |
-
|
|
87 |
-
|
|
88 |
-
|
|
89 |
-
|
|
90 |
-
|
|
91 |
-
|
|
92 |
-
|
|
93 |
-
|
|
94 |
-
|
|
95 |
-
|
|
96 |
-
|
|
97 |
|
98 |
|
99 |
### Framework versions
|
|
|
13 |
|
14 |
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 1.0813
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
32 |
### Training hyperparameters
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 0.0001
|
36 |
- train_batch_size: 512
|
37 |
- eval_batch_size: 512
|
38 |
- seed: 42
|
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| 3.8078 | 1.0 | 6 | 3.6115 |
|
48 |
+
| 3.5402 | 2.0 | 12 | 3.4403 |
|
49 |
+
| 3.3905 | 3.0 | 18 | 3.3023 |
|
50 |
+
| 3.2601 | 4.0 | 24 | 3.1757 |
|
51 |
+
| 3.1298 | 5.0 | 30 | 3.0465 |
|
52 |
+
| 2.9919 | 6.0 | 36 | 2.9159 |
|
53 |
+
| 2.8647 | 7.0 | 42 | 2.7868 |
|
54 |
+
| 2.7503 | 8.0 | 48 | 2.6616 |
|
55 |
+
| 2.6207 | 9.0 | 54 | 2.5386 |
|
56 |
+
| 2.4973 | 10.0 | 60 | 2.4256 |
|
57 |
+
| 2.3944 | 11.0 | 66 | 2.3203 |
|
58 |
+
| 2.2924 | 12.0 | 72 | 2.2263 |
|
59 |
+
| 2.2061 | 13.0 | 78 | 2.1487 |
|
60 |
+
| 2.117 | 14.0 | 84 | 2.0624 |
|
61 |
+
| 2.044 | 15.0 | 90 | 1.9910 |
|
62 |
+
| 1.9718 | 16.0 | 96 | 1.9239 |
|
63 |
+
| 1.9093 | 17.0 | 102 | 1.8786 |
|
64 |
+
| 1.8542 | 18.0 | 108 | 1.8129 |
|
65 |
+
| 1.8085 | 19.0 | 114 | 1.7692 |
|
66 |
+
| 1.7653 | 20.0 | 120 | 1.7316 |
|
67 |
+
| 1.7103 | 21.0 | 126 | 1.6790 |
|
68 |
+
| 1.6757 | 22.0 | 132 | 1.6199 |
|
69 |
+
| 1.6089 | 23.0 | 138 | 1.5592 |
|
70 |
+
| 1.5391 | 24.0 | 144 | 1.5067 |
|
71 |
+
| 1.4987 | 25.0 | 150 | 1.4640 |
|
72 |
+
| 1.4535 | 26.0 | 156 | 1.4296 |
|
73 |
+
| 1.4285 | 27.0 | 162 | 1.3858 |
|
74 |
+
| 1.3828 | 28.0 | 168 | 1.3493 |
|
75 |
+
| 1.3468 | 29.0 | 174 | 1.3184 |
|
76 |
+
| 1.3265 | 30.0 | 180 | 1.2910 |
|
77 |
+
| 1.2953 | 31.0 | 186 | 1.2636 |
|
78 |
+
| 1.2804 | 32.0 | 192 | 1.2402 |
|
79 |
+
| 1.2522 | 33.0 | 198 | 1.2223 |
|
80 |
+
| 1.2375 | 34.0 | 204 | 1.2094 |
|
81 |
+
| 1.219 | 35.0 | 210 | 1.1914 |
|
82 |
+
| 1.2133 | 36.0 | 216 | 1.1762 |
|
83 |
+
| 1.19 | 37.0 | 222 | 1.1606 |
|
84 |
+
| 1.1839 | 38.0 | 228 | 1.1532 |
|
85 |
+
| 1.1737 | 39.0 | 234 | 1.1380 |
|
86 |
+
| 1.1635 | 40.0 | 240 | 1.1267 |
|
87 |
+
| 1.1496 | 41.0 | 246 | 1.1219 |
|
88 |
+
| 1.1514 | 42.0 | 252 | 1.1104 |
|
89 |
+
| 1.1285 | 43.0 | 258 | 1.1056 |
|
90 |
+
| 1.1367 | 44.0 | 264 | 1.0976 |
|
91 |
+
| 1.1232 | 45.0 | 270 | 1.0949 |
|
92 |
+
| 1.1185 | 46.0 | 276 | 1.0896 |
|
93 |
+
| 1.1155 | 47.0 | 282 | 1.0836 |
|
94 |
+
| 1.1053 | 48.0 | 288 | 1.0834 |
|
95 |
+
| 1.1071 | 49.0 | 294 | 1.0823 |
|
96 |
+
| 1.1132 | 50.0 | 300 | 1.0813 |
|
97 |
|
98 |
|
99 |
### Framework versions
|
config.json
CHANGED
@@ -78,7 +78,7 @@
|
|
78 |
"typical_p": 1.0,
|
79 |
"use_bfloat16": false,
|
80 |
"use_cache": true,
|
81 |
-
"vocab_size":
|
82 |
},
|
83 |
"decoder_start_token_id": 2,
|
84 |
"encoder": {
|
@@ -157,7 +157,7 @@
|
|
157 |
"typical_p": 1.0,
|
158 |
"use_bfloat16": false,
|
159 |
"use_cache": true,
|
160 |
-
"vocab_size":
|
161 |
},
|
162 |
"eos_token_id": 0,
|
163 |
"is_encoder_decoder": true,
|
|
|
78 |
"typical_p": 1.0,
|
79 |
"use_bfloat16": false,
|
80 |
"use_cache": true,
|
81 |
+
"vocab_size": 52
|
82 |
},
|
83 |
"decoder_start_token_id": 2,
|
84 |
"encoder": {
|
|
|
157 |
"typical_p": 1.0,
|
158 |
"use_bfloat16": false,
|
159 |
"use_cache": true,
|
160 |
+
"vocab_size": 52
|
161 |
},
|
162 |
"eos_token_id": 0,
|
163 |
"is_encoder_decoder": true,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da4f203a50465bbaf1babcff0cb9459252480321b46aa69609402a6d6f466c22
|
3 |
+
size 31205552
|
runs/Feb28_17-27-44_3897ec21fae5/events.out.tfevents.1709141265.3897ec21fae5.75144.2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17ad020588818cc291fc63c1b1f289c36fadd200cf2b3ec0b9377ba7ee029b94
|
3 |
+
size 30026
|
runs/Feb28_17-51-03_3897ec21fae5/events.out.tfevents.1709142663.3897ec21fae5.81816.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25b8f65db3c899d839e9f3b2588506eab7eba12daa111d59e39fd50fce8e1d22
|
3 |
+
size 21928
|
runs/Feb28_18-13-19_3897ec21fae5/events.out.tfevents.1709144000.3897ec21fae5.81816.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b89e06fd11471306f0f3d62cc64f3f1eaa12eceeff2086ed0623e5f2fc6e7d82
|
3 |
+
size 29928
|
tokenizer.json
CHANGED
@@ -101,198 +101,91 @@
|
|
101 |
"[CLS]": 2,
|
102 |
"[PAD]": 3,
|
103 |
"+": 4,
|
104 |
-
"
|
105 |
-
"
|
106 |
-
"
|
107 |
-
"
|
108 |
-
"
|
109 |
-
"
|
110 |
-
"
|
111 |
-
"
|
112 |
-
"
|
113 |
-
"
|
114 |
-
"
|
115 |
-
"
|
116 |
-
"
|
117 |
-
"
|
118 |
-
"
|
119 |
-
"
|
120 |
-
"
|
121 |
-
"
|
122 |
-
"
|
123 |
-
"
|
124 |
-
"
|
125 |
-
"
|
126 |
-
"
|
127 |
-
"
|
128 |
"16": 29,
|
129 |
-
"
|
130 |
-
"
|
131 |
-
"
|
132 |
-
"
|
133 |
-
"
|
134 |
-
"
|
135 |
-
"
|
136 |
-
"
|
137 |
-
"
|
138 |
-
"
|
139 |
-
"
|
140 |
-
"
|
141 |
-
"
|
142 |
-
"
|
143 |
-
"
|
144 |
-
"
|
145 |
-
"
|
146 |
-
"
|
147 |
-
"
|
148 |
-
"
|
149 |
-
"
|
150 |
-
"
|
151 |
-
"24": 52,
|
152 |
-
"28": 53,
|
153 |
-
"35": 54,
|
154 |
-
"46": 55,
|
155 |
-
"64": 56,
|
156 |
-
"69": 57,
|
157 |
-
"78": 58,
|
158 |
-
"83": 59,
|
159 |
-
"84": 60,
|
160 |
-
"92": 61,
|
161 |
-
"94": 62,
|
162 |
-
"26": 63,
|
163 |
-
"27": 64,
|
164 |
-
"29": 65,
|
165 |
-
"30": 66,
|
166 |
-
"47": 67,
|
167 |
-
"49": 68,
|
168 |
-
"51": 69,
|
169 |
-
"58": 70,
|
170 |
-
"68": 71,
|
171 |
-
"73": 72,
|
172 |
-
"96": 73,
|
173 |
-
"13": 74,
|
174 |
-
"20": 75,
|
175 |
-
"23": 76,
|
176 |
-
"40": 77,
|
177 |
-
"61": 78,
|
178 |
-
"70": 79,
|
179 |
-
"82": 80,
|
180 |
-
"38": 81,
|
181 |
-
"74": 82,
|
182 |
-
"80": 83,
|
183 |
-
"98": 84,
|
184 |
-
"14": 85,
|
185 |
-
"41": 86,
|
186 |
-
"45": 87,
|
187 |
-
"52": 88,
|
188 |
-
"62": 89,
|
189 |
-
"63": 90,
|
190 |
-
"77": 91,
|
191 |
-
"86": 92,
|
192 |
-
"31": 93,
|
193 |
-
"34": 94,
|
194 |
-
"42": 95,
|
195 |
-
"43": 96,
|
196 |
-
"48": 97,
|
197 |
-
"76": 98,
|
198 |
-
"99": 99,
|
199 |
-
"15": 100,
|
200 |
-
"56": 101,
|
201 |
-
"97": 102,
|
202 |
-
"44": 103,
|
203 |
-
"67": 104
|
204 |
},
|
205 |
"merges": [
|
206 |
-
"
|
207 |
-
"9
|
|
|
208 |
"1 1",
|
209 |
-
"
|
210 |
-
"1 9",
|
211 |
-
"2 1",
|
212 |
-
"3 3",
|
213 |
-
"3 6",
|
214 |
-
"6 6",
|
215 |
-
"8 8",
|
216 |
"1 2",
|
217 |
-
"
|
218 |
-
"
|
219 |
-
"9 0",
|
220 |
-
"1 6",
|
221 |
-
"3 9",
|
222 |
-
"5 5",
|
223 |
-
"6 5",
|
224 |
-
"7 9",
|
225 |
-
"8 7",
|
226 |
"9 5",
|
227 |
-
"1
|
|
|
|
|
|
|
|
|
|
|
|
|
228 |
"1 8",
|
229 |
-
"2 5",
|
230 |
-
"3 2",
|
231 |
-
"3 7",
|
232 |
-
"5 3",
|
233 |
-
"5 4",
|
234 |
-
"5 7",
|
235 |
-
"5 9",
|
236 |
-
"7 1",
|
237 |
-
"7 2",
|
238 |
-
"7 5",
|
239 |
-
"8 5",
|
240 |
-
"8 9",
|
241 |
"9 1",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
242 |
"2 2",
|
|
|
|
|
|
|
243 |
"2 4",
|
244 |
-
"2
|
245 |
-
"3 5",
|
246 |
-
"4 6",
|
247 |
-
"6 4",
|
248 |
-
"6 9",
|
249 |
-
"7 8",
|
250 |
-
"8 3",
|
251 |
"8 4",
|
252 |
-
"
|
253 |
-
"9 4",
|
254 |
"2 6",
|
255 |
"2 7",
|
256 |
-
"2
|
257 |
-
"3 0",
|
258 |
-
"4 7",
|
259 |
-
"4 9",
|
260 |
-
"5 1",
|
261 |
-
"5 8",
|
262 |
-
"6 8",
|
263 |
-
"7 3",
|
264 |
-
"9 6",
|
265 |
-
"1 3",
|
266 |
-
"2 0",
|
267 |
-
"2 3",
|
268 |
-
"4 0",
|
269 |
-
"6 1",
|
270 |
-
"7 0",
|
271 |
-
"8 2",
|
272 |
-
"3 8",
|
273 |
-
"7 4",
|
274 |
-
"8 0",
|
275 |
-
"9 8",
|
276 |
-
"1 4",
|
277 |
-
"4 1",
|
278 |
-
"4 5",
|
279 |
-
"5 2",
|
280 |
-
"6 2",
|
281 |
-
"6 3",
|
282 |
-
"7 7",
|
283 |
-
"8 6",
|
284 |
-
"3 1",
|
285 |
-
"3 4",
|
286 |
-
"4 2",
|
287 |
-
"4 3",
|
288 |
-
"4 8",
|
289 |
-
"7 6",
|
290 |
-
"9 9",
|
291 |
-
"1 5",
|
292 |
-
"5 6",
|
293 |
-
"9 7",
|
294 |
-
"4 4",
|
295 |
-
"6 7"
|
296 |
]
|
297 |
}
|
298 |
}
|
|
|
101 |
"[CLS]": 2,
|
102 |
"[PAD]": 3,
|
103 |
"+": 4,
|
104 |
+
"-": 5,
|
105 |
+
"0": 6,
|
106 |
+
"1": 7,
|
107 |
+
"2": 8,
|
108 |
+
"3": 9,
|
109 |
+
"4": 10,
|
110 |
+
"5": 11,
|
111 |
+
"6": 12,
|
112 |
+
"7": 13,
|
113 |
+
"8": 14,
|
114 |
+
"9": 15,
|
115 |
+
"10": 16,
|
116 |
+
"99": 17,
|
117 |
+
"98": 18,
|
118 |
+
"11": 19,
|
119 |
+
"97": 20,
|
120 |
+
"12": 21,
|
121 |
+
"96": 22,
|
122 |
+
"13": 23,
|
123 |
+
"95": 24,
|
124 |
+
"14": 25,
|
125 |
+
"15": 26,
|
126 |
+
"94": 27,
|
127 |
+
"93": 28,
|
128 |
"16": 29,
|
129 |
+
"17": 30,
|
130 |
+
"92": 31,
|
131 |
+
"18": 32,
|
132 |
+
"91": 33,
|
133 |
+
"90": 34,
|
134 |
+
"19": 35,
|
135 |
+
"20": 36,
|
136 |
+
"89": 37,
|
137 |
+
"21": 38,
|
138 |
+
"88": 39,
|
139 |
+
"87": 40,
|
140 |
+
"22": 41,
|
141 |
+
"23": 42,
|
142 |
+
"86": 43,
|
143 |
+
"85": 44,
|
144 |
+
"24": 45,
|
145 |
+
"25": 46,
|
146 |
+
"84": 47,
|
147 |
+
"83": 48,
|
148 |
+
"26": 49,
|
149 |
+
"27": 50,
|
150 |
+
"82": 51
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
151 |
},
|
152 |
"merges": [
|
153 |
+
"1 0",
|
154 |
+
"9 9",
|
155 |
+
"9 8",
|
156 |
"1 1",
|
157 |
+
"9 7",
|
|
|
|
|
|
|
|
|
|
|
|
|
158 |
"1 2",
|
159 |
+
"9 6",
|
160 |
+
"1 3",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
161 |
"9 5",
|
162 |
+
"1 4",
|
163 |
+
"1 5",
|
164 |
+
"9 4",
|
165 |
+
"9 3",
|
166 |
+
"1 6",
|
167 |
+
"1 7",
|
168 |
+
"9 2",
|
169 |
"1 8",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
170 |
"9 1",
|
171 |
+
"9 0",
|
172 |
+
"1 9",
|
173 |
+
"2 0",
|
174 |
+
"8 9",
|
175 |
+
"2 1",
|
176 |
+
"8 8",
|
177 |
+
"8 7",
|
178 |
"2 2",
|
179 |
+
"2 3",
|
180 |
+
"8 6",
|
181 |
+
"8 5",
|
182 |
"2 4",
|
183 |
+
"2 5",
|
|
|
|
|
|
|
|
|
|
|
|
|
184 |
"8 4",
|
185 |
+
"8 3",
|
|
|
186 |
"2 6",
|
187 |
"2 7",
|
188 |
+
"8 2"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
189 |
]
|
190 |
}
|
191 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d67f255dd0132ad0e26dff40d45f3b9dccbb9a1d04a4e4d270f7a3e6fa02c0ec
|
3 |
size 4920
|