Hugging Face's logo

Ragab167
/
output

Text2Text Generation
Transformers
Safetensors
m2m_100
Generated from Trainer
Inference Endpoints
Model card Files Community
Ragab167 commited on
Commit
e3abaab
•
1 Parent(s): 3fbf416

End of training

Browse files
Files changed (3) hide show
  1. README.md +11 -231
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.6652
19
 
20
  ## Model description
21
 
@@ -35,242 +35,22 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 5e-05
38
- - train_batch_size: 8
39
- - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 15
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:-----:|:---------------:|
49
- | 3.8819 | 0.07 | 100 | 0.7677 |
50
- | 0.7529 | 0.13 | 200 | 0.6311 |
51
- | 0.6575 | 0.2 | 300 | 0.6079 |
52
- | 0.6478 | 0.27 | 400 | 0.5925 |
53
- | 0.5882 | 0.33 | 500 | 0.5750 |
54
- | 0.5882 | 0.4 | 600 | 0.5681 |
55
- | 0.5635 | 0.47 | 700 | 0.5575 |
56
- | 0.6301 | 0.53 | 800 | 0.5525 |
57
- | 0.5667 | 0.6 | 900 | 0.5472 |
58
- | 0.5591 | 0.66 | 1000 | 0.5430 |
59
- | 0.5761 | 0.73 | 1100 | 0.5298 |
60
- | 0.556 | 0.8 | 1200 | 0.5318 |
61
- | 0.5664 | 0.86 | 1300 | 0.5235 |
62
- | 0.5494 | 0.93 | 1400 | 0.5200 |
63
- | 0.5416 | 1.0 | 1500 | 0.5171 |
64
- | 0.4251 | 1.06 | 1600 | 0.5248 |
65
- | 0.4447 | 1.13 | 1700 | 0.5271 |
66
- | 0.437 | 1.2 | 1800 | 0.5172 |
67
- | 0.4064 | 1.26 | 1900 | 0.5146 |
68
- | 0.413 | 1.33 | 2000 | 0.5130 |
69
- | 0.4364 | 1.4 | 2100 | 0.5132 |
70
- | 0.4002 | 1.46 | 2200 | 0.5203 |
71
- | 0.4441 | 1.53 | 2300 | 0.5078 |
72
- | 0.4179 | 1.6 | 2400 | 0.5057 |
73
- | 0.4438 | 1.66 | 2500 | 0.5039 |
74
- | 0.4394 | 1.73 | 2600 | 0.5064 |
75
- | 0.4581 | 1.8 | 2700 | 0.5007 |
76
- | 0.4366 | 1.86 | 2800 | 0.4977 |
77
- | 0.4464 | 1.93 | 2900 | 0.4965 |
78
- | 0.447 | 1.99 | 3000 | 0.4940 |
79
- | 0.3333 | 2.06 | 3100 | 0.5052 |
80
- | 0.3355 | 2.13 | 3200 | 0.5053 |
81
- | 0.3227 | 2.19 | 3300 | 0.5066 |
82
- | 0.3298 | 2.26 | 3400 | 0.5072 |
83
- | 0.3276 | 2.33 | 3500 | 0.5075 |
84
- | 0.3252 | 2.39 | 3600 | 0.5025 |
85
- | 0.3132 | 2.46 | 3700 | 0.5022 |
86
- | 0.3247 | 2.53 | 3800 | 0.5062 |
87
- | 0.3311 | 2.59 | 3900 | 0.5010 |
88
- | 0.3385 | 2.66 | 4000 | 0.5019 |
89
- | 0.3496 | 2.73 | 4100 | 0.5010 |
90
- | 0.3164 | 2.79 | 4200 | 0.4975 |
91
- | 0.3458 | 2.86 | 4300 | 0.4989 |
92
- | 0.3288 | 2.93 | 4400 | 0.5002 |
93
- | 0.3341 | 2.99 | 4500 | 0.5034 |
94
- | 0.2293 | 3.06 | 4600 | 0.5090 |
95
- | 0.2301 | 3.12 | 4700 | 0.5108 |
96
- | 0.2253 | 3.19 | 4800 | 0.5088 |
97
- | 0.2288 | 3.26 | 4900 | 0.5117 |
98
- | 0.238 | 3.32 | 5000 | 0.5157 |
99
- | 0.2487 | 3.39 | 5100 | 0.5129 |
100
- | 0.2358 | 3.46 | 5200 | 0.5139 |
101
- | 0.2491 | 3.52 | 5300 | 0.5185 |
102
- | 0.2326 | 3.59 | 5400 | 0.5097 |
103
- | 0.243 | 3.66 | 5500 | 0.5142 |
104
- | 0.2635 | 3.72 | 5600 | 0.5094 |
105
- | 0.2568 | 3.79 | 5700 | 0.5136 |
106
- | 0.2608 | 3.86 | 5800 | 0.5053 |
107
- | 0.2709 | 3.92 | 5900 | 0.5104 |
108
- | 0.2442 | 3.99 | 6000 | 0.5116 |
109
- | 0.183 | 4.06 | 6100 | 0.5199 |
110
- | 0.1657 | 4.12 | 6200 | 0.5228 |
111
- | 0.1537 | 4.19 | 6300 | 0.5230 |
112
- | 0.1634 | 4.26 | 6400 | 0.5232 |
113
- | 0.1679 | 4.32 | 6500 | 0.5270 |
114
- | 0.1695 | 4.39 | 6600 | 0.5293 |
115
- | 0.1872 | 4.45 | 6700 | 0.5279 |
116
- | 0.1723 | 4.52 | 6800 | 0.5256 |
117
- | 0.1624 | 4.59 | 6900 | 0.5320 |
118
- | 0.1708 | 4.65 | 7000 | 0.5289 |
119
- | 0.1826 | 4.72 | 7100 | 0.5369 |
120
- | 0.1772 | 4.79 | 7200 | 0.5331 |
121
- | 0.1672 | 4.85 | 7300 | 0.5287 |
122
- | 0.1824 | 4.92 | 7400 | 0.5317 |
123
- | 0.1782 | 4.99 | 7500 | 0.5309 |
124
- | 0.1177 | 5.05 | 7600 | 0.5414 |
125
- | 0.1114 | 5.12 | 7700 | 0.5450 |
126
- | 0.1117 | 5.19 | 7800 | 0.5491 |
127
- | 0.1118 | 5.25 | 7900 | 0.5474 |
128
- | 0.1105 | 5.32 | 8000 | 0.5478 |
129
- | 0.1015 | 5.39 | 8100 | 0.5515 |
130
- | 0.1085 | 5.45 | 8200 | 0.5502 |
131
- | 0.1165 | 5.52 | 8300 | 0.5581 |
132
- | 0.1193 | 5.59 | 8400 | 0.5529 |
133
- | 0.1233 | 5.65 | 8500 | 0.5556 |
134
- | 0.122 | 5.72 | 8600 | 0.5494 |
135
- | 0.1261 | 5.78 | 8700 | 0.5515 |
136
- | 0.126 | 5.85 | 8800 | 0.5516 |
137
- | 0.1165 | 5.92 | 8900 | 0.5488 |
138
- | 0.1208 | 5.98 | 9000 | 0.5505 |
139
- | 0.0772 | 6.05 | 9100 | 0.5591 |
140
- | 0.0709 | 6.12 | 9200 | 0.5588 |
141
- | 0.0759 | 6.18 | 9300 | 0.5642 |
142
- | 0.0672 | 6.25 | 9400 | 0.5669 |
143
- | 0.0736 | 6.32 | 9500 | 0.5630 |
144
- | 0.0785 | 6.38 | 9600 | 0.5730 |
145
- | 0.0721 | 6.45 | 9700 | 0.5720 |
146
- | 0.0809 | 6.52 | 9800 | 0.5769 |
147
- | 0.0787 | 6.58 | 9900 | 0.5790 |
148
- | 0.0776 | 6.65 | 10000 | 0.5713 |
149
- | 0.0821 | 6.72 | 10100 | 0.5713 |
150
- | 0.0735 | 6.78 | 10200 | 0.5727 |
151
- | 0.0742 | 6.85 | 10300 | 0.5780 |
152
- | 0.0813 | 6.91 | 10400 | 0.5747 |
153
- | 0.0823 | 6.98 | 10500 | 0.5731 |
154
- | 0.0521 | 7.05 | 10600 | 0.5849 |
155
- | 0.0471 | 7.11 | 10700 | 0.5842 |
156
- | 0.0433 | 7.18 | 10800 | 0.5870 |
157
- | 0.0463 | 7.25 | 10900 | 0.5889 |
158
- | 0.0512 | 7.31 | 11000 | 0.5913 |
159
- | 0.0461 | 7.38 | 11100 | 0.5874 |
160
- | 0.0521 | 7.45 | 11200 | 0.5943 |
161
- | 0.0434 | 7.51 | 11300 | 0.5940 |
162
- | 0.0522 | 7.58 | 11400 | 0.5980 |
163
- | 0.0607 | 7.65 | 11500 | 0.5891 |
164
- | 0.049 | 7.71 | 11600 | 0.5916 |
165
- | 0.0494 | 7.78 | 11700 | 0.5960 |
166
- | 0.0526 | 7.85 | 11800 | 0.5942 |
167
- | 0.0505 | 7.91 | 11900 | 0.5972 |
168
- | 0.0579 | 7.98 | 12000 | 0.5930 |
169
- | 0.038 | 8.05 | 12100 | 0.6054 |
170
- | 0.0295 | 8.11 | 12200 | 0.6017 |
171
- | 0.0303 | 8.18 | 12300 | 0.6020 |
172
- | 0.0348 | 8.24 | 12400 | 0.6052 |
173
- | 0.0318 | 8.31 | 12500 | 0.6103 |
174
- | 0.0369 | 8.38 | 12600 | 0.6079 |
175
- | 0.0373 | 8.44 | 12700 | 0.6050 |
176
- | 0.0319 | 8.51 | 12800 | 0.6095 |
177
- | 0.0348 | 8.58 | 12900 | 0.6066 |
178
- | 0.0326 | 8.64 | 13000 | 0.6084 |
179
- | 0.0335 | 8.71 | 13100 | 0.6148 |
180
- | 0.0303 | 8.78 | 13200 | 0.6142 |
181
- | 0.0409 | 8.84 | 13300 | 0.6190 |
182
- | 0.0357 | 8.91 | 13400 | 0.6121 |
183
- | 0.0351 | 8.98 | 13500 | 0.6121 |
184
- | 0.0254 | 9.04 | 13600 | 0.6203 |
185
- | 0.0215 | 9.11 | 13700 | 0.6235 |
186
- | 0.0214 | 9.18 | 13800 | 0.6243 |
187
- | 0.0226 | 9.24 | 13900 | 0.6199 |
188
- | 0.0224 | 9.31 | 14000 | 0.6225 |
189
- | 0.0226 | 9.38 | 14100 | 0.6236 |
190
- | 0.0224 | 9.44 | 14200 | 0.6261 |
191
- | 0.0262 | 9.51 | 14300 | 0.6259 |
192
- | 0.022 | 9.57 | 14400 | 0.6223 |
193
- | 0.0248 | 9.64 | 14500 | 0.6275 |
194
- | 0.0236 | 9.71 | 14600 | 0.6261 |
195
- | 0.022 | 9.77 | 14700 | 0.6303 |
196
- | 0.0225 | 9.84 | 14800 | 0.6290 |
197
- | 0.0248 | 9.91 | 14900 | 0.6299 |
198
- | 0.0233 | 9.97 | 15000 | 0.6302 |
199
- | 0.021 | 10.04 | 15100 | 0.6297 |
200
- | 0.0153 | 10.11 | 15200 | 0.6355 |
201
- | 0.015 | 10.17 | 15300 | 0.6321 |
202
- | 0.0153 | 10.24 | 15400 | 0.6349 |
203
- | 0.0168 | 10.31 | 15500 | 0.6310 |
204
- | 0.0155 | 10.37 | 15600 | 0.6352 |
205
- | 0.0153 | 10.44 | 15700 | 0.6391 |
206
- | 0.0189 | 10.51 | 15800 | 0.6373 |
207
- | 0.0166 | 10.57 | 15900 | 0.6370 |
208
- | 0.016 | 10.64 | 16000 | 0.6348 |
209
- | 0.0191 | 10.7 | 16100 | 0.6381 |
210
- | 0.0172 | 10.77 | 16200 | 0.6394 |
211
- | 0.0171 | 10.84 | 16300 | 0.6408 |
212
- | 0.0185 | 10.9 | 16400 | 0.6378 |
213
- | 0.0167 | 10.97 | 16500 | 0.6437 |
214
- | 0.016 | 11.04 | 16600 | 0.6447 |
215
- | 0.0127 | 11.1 | 16700 | 0.6408 |
216
- | 0.0131 | 11.17 | 16800 | 0.6454 |
217
- | 0.0117 | 11.24 | 16900 | 0.6471 |
218
- | 0.0125 | 11.3 | 17000 | 0.6484 |
219
- | 0.0135 | 11.37 | 17100 | 0.6517 |
220
- | 0.0122 | 11.44 | 17200 | 0.6462 |
221
- | 0.0132 | 11.5 | 17300 | 0.6505 |
222
- | 0.012 | 11.57 | 17400 | 0.6524 |
223
- | 0.0152 | 11.64 | 17500 | 0.6491 |
224
- | 0.0147 | 11.7 | 17600 | 0.6506 |
225
- | 0.0144 | 11.77 | 17700 | 0.6482 |
226
- | 0.0143 | 11.84 | 17800 | 0.6482 |
227
- | 0.0121 | 11.9 | 17900 | 0.6475 |
228
- | 0.0131 | 11.97 | 18000 | 0.6480 |
229
- | 0.0113 | 12.03 | 18100 | 0.6491 |
230
- | 0.0117 | 12.1 | 18200 | 0.6543 |
231
- | 0.0092 | 12.17 | 18300 | 0.6575 |
232
- | 0.0102 | 12.23 | 18400 | 0.6530 |
233
- | 0.0099 | 12.3 | 18500 | 0.6612 |
234
- | 0.0099 | 12.37 | 18600 | 0.6547 |
235
- | 0.0089 | 12.43 | 18700 | 0.6553 |
236
- | 0.01 | 12.5 | 18800 | 0.6581 |
237
- | 0.0092 | 12.57 | 18900 | 0.6579 |
238
- | 0.0092 | 12.63 | 19000 | 0.6558 |
239
- | 0.0099 | 12.7 | 19100 | 0.6563 |
240
- | 0.0099 | 12.77 | 19200 | 0.6578 |
241
- | 0.0103 | 12.83 | 19300 | 0.6589 |
242
- | 0.0093 | 12.9 | 19400 | 0.6582 |
243
- | 0.0093 | 12.97 | 19500 | 0.6582 |
244
- | 0.0078 | 13.03 | 19600 | 0.6604 |
245
- | 0.0073 | 13.1 | 19700 | 0.6606 |
246
- | 0.0082 | 13.16 | 19800 | 0.6582 |
247
- | 0.0075 | 13.23 | 19900 | 0.6614 |
248
- | 0.0073 | 13.3 | 20000 | 0.6636 |
249
- | 0.0072 | 13.36 | 20100 | 0.6578 |
250
- | 0.0074 | 13.43 | 20200 | 0.6606 |
251
- | 0.009 | 13.5 | 20300 | 0.6623 |
252
- | 0.0149 | 13.56 | 20400 | 0.6615 |
253
- | 0.0078 | 13.63 | 20500 | 0.6616 |
254
- | 0.0069 | 13.7 | 20600 | 0.6653 |
255
- | 0.0085 | 13.76 | 20700 | 0.6607 |
256
- | 0.0074 | 13.83 | 20800 | 0.6619 |
257
- | 0.0088 | 13.9 | 20900 | 0.6621 |
258
- | 0.0069 | 13.96 | 21000 | 0.6613 |
259
- | 0.0076 | 14.03 | 21100 | 0.6630 |
260
- | 0.0062 | 14.1 | 21200 | 0.6635 |
261
- | 0.007 | 14.16 | 21300 | 0.6623 |
262
- | 0.0066 | 14.23 | 21400 | 0.6627 |
263
- | 0.0067 | 14.3 | 21500 | 0.6620 |
264
- | 0.0066 | 14.36 | 21600 | 0.6604 |
265
- | 0.0068 | 14.43 | 21700 | 0.6620 |
266
- | 0.0069 | 14.49 | 21800 | 0.6629 |
267
- | 0.0088 | 14.56 | 21900 | 0.6625 |
268
- | 0.0069 | 14.63 | 22000 | 0.6642 |
269
- | 0.0063 | 14.69 | 22100 | 0.6645 |
270
- | 0.0074 | 14.76 | 22200 | 0.6652 |
271
- | 0.0053 | 14.83 | 22300 | 0.6652 |
272
- | 0.0076 | 14.89 | 22400 | 0.6652 |
273
- | 0.0068 | 14.96 | 22500 | 0.6652 |
274
 
275
 
276
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.6403
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 5e-05
38
+ - train_batch_size: 64
39
+ - eval_batch_size: 64
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 3
44
 
45
  ### Training results
46
 
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 3.7937 | 0.53 | 100 | 0.9563 |
50
+ | 0.7881 | 1.06 | 200 | 0.6899 |
51
+ | 0.617 | 1.6 | 300 | 0.6622 |
52
+ | 0.6014 | 2.13 | 400 | 0.6468 |
53
+ | 0.5157 | 2.66 | 500 | 0.6403 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57c2dba693ad439907fd42db9c651a502d6bc4902e71f8c4de1ef5e9140964bb
3
  size 1935681888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22d0f4b654df6fc49e188a220d85f62f875f8c4e7708500c3cab3d0503d0ffcd
3
  size 1935681888
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99784449f25d0e78d0e9300bbcb7c08586cf752b844b61d70236070024f88a1a
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b823d0c5c9aac29284f1c01633432e7c8eca274f9327c7443e64fecaea1d3c82
3
  size 4984