End of training
Browse files- README.md +42 -42
- config.json +3 -3
- generation_config.json +1 -1
- model.safetensors +2 -2
- runs/Mar24_14-32-40_6999fcd7abc0/events.out.tfevents.1711290761.6999fcd7abc0.344.0 +3 -0
- tokenizer.json +25 -23
- 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: 0.
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -44,51 +44,51 @@ The following hyperparameters were used during training:
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
-
| 2.
|
48 |
-
|
|
49 |
-
| 1.
|
50 |
-
| 1.
|
51 |
-
| 1.
|
52 |
-
| 0.
|
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.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
|
88 |
|
89 |
### Framework versions
|
90 |
|
91 |
-
- Transformers 4.
|
92 |
- Pytorch 2.2.1+cu121
|
93 |
- Datasets 2.18.0
|
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: 0.2167
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| 2.9708 | 1.0 | 6 | 2.2532 |
|
48 |
+
| 2.0334 | 2.0 | 12 | 1.7317 |
|
49 |
+
| 1.5636 | 3.0 | 18 | 1.3306 |
|
50 |
+
| 1.2228 | 4.0 | 24 | 1.1101 |
|
51 |
+
| 1.0587 | 5.0 | 30 | 0.9678 |
|
52 |
+
| 0.9399 | 6.0 | 36 | 0.8654 |
|
53 |
+
| 0.8269 | 7.0 | 42 | 0.7420 |
|
54 |
+
| 0.7354 | 8.0 | 48 | 0.6981 |
|
55 |
+
| 0.6841 | 9.0 | 54 | 0.6609 |
|
56 |
+
| 0.6499 | 10.0 | 60 | 0.6128 |
|
57 |
+
| 0.592 | 11.0 | 66 | 0.5730 |
|
58 |
+
| 0.5651 | 12.0 | 72 | 0.5324 |
|
59 |
+
| 0.53 | 13.0 | 78 | 0.5232 |
|
60 |
+
| 0.5087 | 14.0 | 84 | 0.5066 |
|
61 |
+
| 0.5052 | 15.0 | 90 | 0.4966 |
|
62 |
+
| 0.4933 | 16.0 | 96 | 0.4476 |
|
63 |
+
| 0.4622 | 17.0 | 102 | 0.4559 |
|
64 |
+
| 0.4604 | 18.0 | 108 | 0.4520 |
|
65 |
+
| 0.4386 | 19.0 | 114 | 0.4525 |
|
66 |
+
| 0.4453 | 20.0 | 120 | 0.4345 |
|
67 |
+
| 0.4293 | 21.0 | 126 | 0.3955 |
|
68 |
+
| 0.3904 | 22.0 | 132 | 0.3695 |
|
69 |
+
| 0.3793 | 23.0 | 138 | 0.3614 |
|
70 |
+
| 0.3648 | 24.0 | 144 | 0.3463 |
|
71 |
+
| 0.3471 | 25.0 | 150 | 0.3247 |
|
72 |
+
| 0.3391 | 26.0 | 156 | 0.3100 |
|
73 |
+
| 0.3084 | 27.0 | 162 | 0.2981 |
|
74 |
+
| 0.3188 | 28.0 | 168 | 0.2901 |
|
75 |
+
| 0.3074 | 29.0 | 174 | 0.2791 |
|
76 |
+
| 0.2847 | 30.0 | 180 | 0.2832 |
|
77 |
+
| 0.2832 | 31.0 | 186 | 0.2637 |
|
78 |
+
| 0.2762 | 32.0 | 192 | 0.2596 |
|
79 |
+
| 0.2928 | 33.0 | 198 | 0.2487 |
|
80 |
+
| 0.2759 | 34.0 | 204 | 0.2408 |
|
81 |
+
| 0.2634 | 35.0 | 210 | 0.2334 |
|
82 |
+
| 0.2585 | 36.0 | 216 | 0.2270 |
|
83 |
+
| 0.2444 | 37.0 | 222 | 0.2227 |
|
84 |
+
| 0.2394 | 38.0 | 228 | 0.2183 |
|
85 |
+
| 0.2376 | 39.0 | 234 | 0.2174 |
|
86 |
+
| 0.2394 | 40.0 | 240 | 0.2167 |
|
87 |
|
88 |
|
89 |
### Framework versions
|
90 |
|
91 |
+
- Transformers 4.38.2
|
92 |
- Pytorch 2.2.1+cu121
|
93 |
- Datasets 2.18.0
|
94 |
- Tokenizers 0.15.2
|
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": {
|
@@ -157,13 +157,13 @@
|
|
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,
|
164 |
"model_type": "encoder-decoder",
|
165 |
"pad_token_id": 3,
|
166 |
"torch_dtype": "float32",
|
167 |
-
"transformers_version": "4.
|
168 |
"unk_token_id": null
|
169 |
}
|
|
|
78 |
"typical_p": 1.0,
|
79 |
"use_bfloat16": false,
|
80 |
"use_cache": true,
|
81 |
+
"vocab_size": 53
|
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": 53
|
161 |
},
|
162 |
"eos_token_id": 0,
|
163 |
"is_encoder_decoder": true,
|
164 |
"model_type": "encoder-decoder",
|
165 |
"pad_token_id": 3,
|
166 |
"torch_dtype": "float32",
|
167 |
+
"transformers_version": "4.38.2",
|
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": "4.38.2"
|
7 |
}
|
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:fab7ebca07c1654775fe9566420c379fa893d378403fdf2efb22053f5e40528e
|
3 |
+
size 31207604
|
runs/Mar24_14-32-40_6999fcd7abc0/events.out.tfevents.1711290761.6999fcd7abc0.344.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:655d3e8ec7efbd55091af0cb0ac9f4cbe9559c2d2cefaa1373817fd42949c79f
|
3 |
+
size 27997
|
tokenizer.json
CHANGED
@@ -115,76 +115,78 @@
|
|
115 |
"=": 16,
|
116 |
"10": 17,
|
117 |
"99": 18,
|
118 |
-
"
|
119 |
-
"
|
120 |
"12": 21,
|
121 |
"97": 22,
|
122 |
"96": 23,
|
123 |
"13": 24,
|
124 |
"95": 25,
|
125 |
"14": 26,
|
126 |
-
"
|
127 |
-
"
|
128 |
"16": 29,
|
129 |
"93": 30,
|
130 |
-
"
|
131 |
-
"
|
132 |
"91": 33,
|
133 |
"18": 34,
|
134 |
-
"
|
135 |
-
"
|
136 |
-
"
|
137 |
-
"
|
138 |
-
"
|
139 |
-
"
|
140 |
"22": 41,
|
141 |
"87": 42,
|
142 |
-
"
|
143 |
-
"
|
144 |
"85": 45,
|
145 |
"24": 46,
|
146 |
"25": 47,
|
147 |
"84": 48,
|
148 |
"26": 49,
|
149 |
"83": 50,
|
150 |
-
"27": 51
|
|
|
151 |
},
|
152 |
"merges": [
|
153 |
"1 0",
|
154 |
"9 9",
|
155 |
-
"9 8",
|
156 |
"1 1",
|
|
|
157 |
"1 2",
|
158 |
"9 7",
|
159 |
"9 6",
|
160 |
"1 3",
|
161 |
"9 5",
|
162 |
"1 4",
|
163 |
-
"9 4",
|
164 |
"1 5",
|
|
|
165 |
"1 6",
|
166 |
"9 3",
|
167 |
-
"9 2",
|
168 |
"1 7",
|
|
|
169 |
"9 1",
|
170 |
"1 8",
|
171 |
-
"1 9",
|
172 |
"9 0",
|
173 |
-
"
|
174 |
"2 0",
|
175 |
-
"8
|
176 |
"2 1",
|
|
|
177 |
"2 2",
|
178 |
"8 7",
|
179 |
-
"2 3",
|
180 |
"8 6",
|
|
|
181 |
"8 5",
|
182 |
"2 4",
|
183 |
"2 5",
|
184 |
"8 4",
|
185 |
"2 6",
|
186 |
"8 3",
|
187 |
-
"2 7"
|
|
|
188 |
]
|
189 |
}
|
190 |
}
|
|
|
115 |
"=": 16,
|
116 |
"10": 17,
|
117 |
"99": 18,
|
118 |
+
"11": 19,
|
119 |
+
"98": 20,
|
120 |
"12": 21,
|
121 |
"97": 22,
|
122 |
"96": 23,
|
123 |
"13": 24,
|
124 |
"95": 25,
|
125 |
"14": 26,
|
126 |
+
"15": 27,
|
127 |
+
"94": 28,
|
128 |
"16": 29,
|
129 |
"93": 30,
|
130 |
+
"17": 31,
|
131 |
+
"92": 32,
|
132 |
"91": 33,
|
133 |
"18": 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 |
"85": 45,
|
145 |
"24": 46,
|
146 |
"25": 47,
|
147 |
"84": 48,
|
148 |
"26": 49,
|
149 |
"83": 50,
|
150 |
+
"27": 51,
|
151 |
+
"82": 52
|
152 |
},
|
153 |
"merges": [
|
154 |
"1 0",
|
155 |
"9 9",
|
|
|
156 |
"1 1",
|
157 |
+
"9 8",
|
158 |
"1 2",
|
159 |
"9 7",
|
160 |
"9 6",
|
161 |
"1 3",
|
162 |
"9 5",
|
163 |
"1 4",
|
|
|
164 |
"1 5",
|
165 |
+
"9 4",
|
166 |
"1 6",
|
167 |
"9 3",
|
|
|
168 |
"1 7",
|
169 |
+
"9 2",
|
170 |
"9 1",
|
171 |
"1 8",
|
|
|
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 |
"8 5",
|
183 |
"2 4",
|
184 |
"2 5",
|
185 |
"8 4",
|
186 |
"2 6",
|
187 |
"8 3",
|
188 |
+
"2 7",
|
189 |
+
"8 2"
|
190 |
]
|
191 |
}
|
192 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:160d6026e0184d20fa6b068e287f3fa90f6d2471cb2d32c45c963f3a6f69912f
|
3 |
size 5112
|