End of training
Browse files- README.md +33 -43
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- runs/Mar01_00-04-39_f85640113c2d/events.out.tfevents.1709251480.f85640113c2d.685.0 +3 -0
- tokenizer.json +30 -30
- training_args.bin +2 -2
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: 0.
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -38,57 +38,47 @@ The following hyperparameters were used during training:
|
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
-
- num_epochs:
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
-
| 2.
|
48 |
-
| 2.
|
49 |
-
| 1.
|
50 |
-
| 1.
|
51 |
-
| 1.
|
52 |
-
|
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.2269 | 31.0 | 186 | 0.2068 |
|
78 |
-
| 0.2272 | 32.0 | 192 | 0.2047 |
|
79 |
-
| 0.2174 | 33.0 | 198 | 0.1927 |
|
80 |
-
| 0.2097 | 34.0 | 204 | 0.1848 |
|
81 |
-
| 0.1966 | 35.0 | 210 | 0.1817 |
|
82 |
-
| 0.1894 | 36.0 | 216 | 0.1768 |
|
83 |
-
| 0.1939 | 37.0 | 222 | 0.1760 |
|
84 |
-
| 0.1884 | 38.0 | 228 | 0.1701 |
|
85 |
-
| 0.1863 | 39.0 | 234 | 0.1683 |
|
86 |
-
| 0.1824 | 40.0 | 240 | 0.1675 |
|
87 |
|
88 |
|
89 |
### Framework versions
|
90 |
|
91 |
-
- Transformers 4.
|
92 |
- Pytorch 2.1.0+cu121
|
93 |
- Datasets 2.17.1
|
94 |
- Tokenizers 0.15.2
|
|
|
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: 0.3578
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 30
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| 2.9444 | 1.0 | 6 | 2.3826 |
|
48 |
+
| 2.1543 | 2.0 | 12 | 1.8663 |
|
49 |
+
| 1.7072 | 3.0 | 18 | 1.5640 |
|
50 |
+
| 1.4261 | 4.0 | 24 | 1.3127 |
|
51 |
+
| 1.2227 | 5.0 | 30 | 1.1949 |
|
52 |
+
| 1.061 | 6.0 | 36 | 1.0322 |
|
53 |
+
| 0.9789 | 7.0 | 42 | 0.9130 |
|
54 |
+
| 0.8812 | 8.0 | 48 | 0.8633 |
|
55 |
+
| 0.8289 | 9.0 | 54 | 0.7872 |
|
56 |
+
| 0.693 | 10.0 | 60 | 0.7300 |
|
57 |
+
| 0.7416 | 11.0 | 66 | 0.7454 |
|
58 |
+
| 0.6965 | 12.0 | 72 | 0.6641 |
|
59 |
+
| 0.6592 | 13.0 | 78 | 0.6362 |
|
60 |
+
| 0.6411 | 14.0 | 84 | 0.5824 |
|
61 |
+
| 0.5677 | 15.0 | 90 | 0.5541 |
|
62 |
+
| 0.5575 | 16.0 | 96 | 0.5299 |
|
63 |
+
| 0.5305 | 17.0 | 102 | 0.5435 |
|
64 |
+
| 0.5371 | 18.0 | 108 | 0.4937 |
|
65 |
+
| 0.4795 | 19.0 | 114 | 0.4800 |
|
66 |
+
| 0.4693 | 20.0 | 120 | 0.4486 |
|
67 |
+
| 0.4836 | 21.0 | 126 | 0.4478 |
|
68 |
+
| 0.4351 | 22.0 | 132 | 0.4323 |
|
69 |
+
| 0.47 | 23.0 | 138 | 0.4131 |
|
70 |
+
| 0.414 | 24.0 | 144 | 0.4023 |
|
71 |
+
| 0.4396 | 25.0 | 150 | 0.3961 |
|
72 |
+
| 0.4079 | 26.0 | 156 | 0.3870 |
|
73 |
+
| 0.4052 | 27.0 | 162 | 0.3846 |
|
74 |
+
| 0.3914 | 28.0 | 168 | 0.3676 |
|
75 |
+
| 0.4287 | 29.0 | 174 | 0.3593 |
|
76 |
+
| 0.3583 | 30.0 | 180 | 0.3578 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
|
78 |
|
79 |
### Framework versions
|
80 |
|
81 |
+
- Transformers 4.38.1
|
82 |
- Pytorch 2.1.0+cu121
|
83 |
- Datasets 2.17.1
|
84 |
- Tokenizers 0.15.2
|
config.json
CHANGED
@@ -164,6 +164,6 @@
|
|
164 |
"model_type": "encoder-decoder",
|
165 |
"pad_token_id": 3,
|
166 |
"torch_dtype": "float32",
|
167 |
-
"transformers_version": "4.
|
168 |
"unk_token_id": null
|
169 |
}
|
|
|
164 |
"model_type": "encoder-decoder",
|
165 |
"pad_token_id": 3,
|
166 |
"torch_dtype": "float32",
|
167 |
+
"transformers_version": "4.38.1",
|
168 |
"unk_token_id": null
|
169 |
}
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"decoder_start_token_id": 2,
|
4 |
"eos_token_id": 0,
|
5 |
"pad_token_id": 3,
|
6 |
-
"transformers_version": "4.
|
7 |
}
|
|
|
3 |
"decoder_start_token_id": 2,
|
4 |
"eos_token_id": 0,
|
5 |
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.38.1"
|
7 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 31207604
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:167f72c4e239a9640669bd8575ebb02c93b5e1a3e22a64d06dd428bbe1e8cd7b
|
3 |
size 31207604
|
runs/Mar01_00-04-39_f85640113c2d/events.out.tfevents.1709251480.f85640113c2d.685.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28d6cd48ae835475c67b1692920019d15893296a60deb4426426b4342aae3e7f
|
3 |
+
size 23177
|
tokenizer.json
CHANGED
@@ -113,76 +113,76 @@
|
|
113 |
"8": 14,
|
114 |
"9": 15,
|
115 |
"=": 16,
|
116 |
-
"
|
117 |
-
"
|
118 |
-
"
|
119 |
-
"
|
120 |
"97": 21,
|
121 |
"12": 22,
|
122 |
"13": 23,
|
123 |
"96": 24,
|
124 |
-
"
|
125 |
-
"
|
126 |
-
"
|
127 |
-
"
|
128 |
-
"
|
129 |
-
"
|
130 |
"17": 31,
|
131 |
"92": 32,
|
132 |
"18": 33,
|
133 |
"91": 34,
|
134 |
-
"
|
135 |
-
"
|
136 |
"20": 37,
|
137 |
"89": 38,
|
138 |
"21": 39,
|
139 |
"88": 40,
|
140 |
-
"
|
141 |
-
"
|
142 |
-
"
|
143 |
-
"
|
144 |
-
"
|
145 |
-
"
|
146 |
-
"
|
147 |
-
"
|
148 |
"26": 49,
|
149 |
"83": 50,
|
150 |
"27": 51,
|
151 |
"82": 52
|
152 |
},
|
153 |
"merges": [
|
154 |
-
"1 0",
|
155 |
"9 9",
|
156 |
-
"1
|
157 |
"9 8",
|
|
|
158 |
"9 7",
|
159 |
"1 2",
|
160 |
"1 3",
|
161 |
"9 6",
|
162 |
-
"1 4",
|
163 |
"9 5",
|
164 |
-
"1
|
165 |
"9 4",
|
166 |
-
"1
|
167 |
"9 3",
|
|
|
168 |
"1 7",
|
169 |
"9 2",
|
170 |
"1 8",
|
171 |
"9 1",
|
172 |
-
"1 9",
|
173 |
"9 0",
|
|
|
174 |
"2 0",
|
175 |
"8 9",
|
176 |
"2 1",
|
177 |
"8 8",
|
178 |
-
"8 7",
|
179 |
"2 2",
|
180 |
-
"
|
181 |
"8 6",
|
182 |
-
"
|
183 |
"2 4",
|
184 |
-
"
|
185 |
"8 4",
|
|
|
186 |
"2 6",
|
187 |
"8 3",
|
188 |
"2 7",
|
|
|
113 |
"8": 14,
|
114 |
"9": 15,
|
115 |
"=": 16,
|
116 |
+
"99": 17,
|
117 |
+
"10": 18,
|
118 |
+
"98": 19,
|
119 |
+
"11": 20,
|
120 |
"97": 21,
|
121 |
"12": 22,
|
122 |
"13": 23,
|
123 |
"96": 24,
|
124 |
+
"95": 25,
|
125 |
+
"14": 26,
|
126 |
+
"94": 27,
|
127 |
+
"15": 28,
|
128 |
+
"93": 29,
|
129 |
+
"16": 30,
|
130 |
"17": 31,
|
131 |
"92": 32,
|
132 |
"18": 33,
|
133 |
"91": 34,
|
134 |
+
"90": 35,
|
135 |
+
"19": 36,
|
136 |
"20": 37,
|
137 |
"89": 38,
|
138 |
"21": 39,
|
139 |
"88": 40,
|
140 |
+
"22": 41,
|
141 |
+
"87": 42,
|
142 |
+
"86": 43,
|
143 |
+
"23": 44,
|
144 |
+
"24": 45,
|
145 |
+
"85": 46,
|
146 |
+
"84": 47,
|
147 |
+
"25": 48,
|
148 |
"26": 49,
|
149 |
"83": 50,
|
150 |
"27": 51,
|
151 |
"82": 52
|
152 |
},
|
153 |
"merges": [
|
|
|
154 |
"9 9",
|
155 |
+
"1 0",
|
156 |
"9 8",
|
157 |
+
"1 1",
|
158 |
"9 7",
|
159 |
"1 2",
|
160 |
"1 3",
|
161 |
"9 6",
|
|
|
162 |
"9 5",
|
163 |
+
"1 4",
|
164 |
"9 4",
|
165 |
+
"1 5",
|
166 |
"9 3",
|
167 |
+
"1 6",
|
168 |
"1 7",
|
169 |
"9 2",
|
170 |
"1 8",
|
171 |
"9 1",
|
|
|
172 |
"9 0",
|
173 |
+
"1 9",
|
174 |
"2 0",
|
175 |
"8 9",
|
176 |
"2 1",
|
177 |
"8 8",
|
|
|
178 |
"2 2",
|
179 |
+
"8 7",
|
180 |
"8 6",
|
181 |
+
"2 3",
|
182 |
"2 4",
|
183 |
+
"8 5",
|
184 |
"8 4",
|
185 |
+
"2 5",
|
186 |
"2 6",
|
187 |
"8 3",
|
188 |
"2 7",
|
training_args.bin
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 sha256:9b65476e169e5915d0d98245574cb840abef742cd27134fa31a767c9d1641c6e
|
3 |
+
size 5112
|