ciebson commited on
Commit
e68e058
·
verified ·
1 Parent(s): 08e37f9

End of training

Browse files
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: 1.5023
17
 
18
  ## Model description
19
 
@@ -44,46 +44,46 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | 3.3775 | 1.0 | 6 | 2.7529 |
48
- | 2.3702 | 2.0 | 12 | 2.1325 |
49
- | 1.8843 | 3.0 | 18 | 1.6965 |
50
- | 1.6497 | 4.0 | 24 | 1.6655 |
51
- | 1.6067 | 5.0 | 30 | 1.7142 |
52
- | 1.5987 | 6.0 | 36 | 1.5422 |
53
- | 1.5515 | 7.0 | 42 | 1.5353 |
54
- | 1.5423 | 8.0 | 48 | 1.5221 |
55
- | 1.5279 | 9.0 | 54 | 1.5173 |
56
- | 1.5394 | 10.0 | 60 | 1.5206 |
57
- | 1.5298 | 11.0 | 66 | 1.5216 |
58
- | 1.5003 | 12.0 | 72 | 1.5170 |
59
- | 1.5462 | 13.0 | 78 | 1.5142 |
60
- | 1.5107 | 14.0 | 84 | 1.5157 |
61
- | 1.5059 | 15.0 | 90 | 1.5077 |
62
- | 1.5442 | 16.0 | 96 | 1.5069 |
63
- | 1.548 | 17.0 | 102 | 1.5080 |
64
- | 1.5427 | 18.0 | 108 | 1.5058 |
65
- | 1.5231 | 19.0 | 114 | 1.5261 |
66
- | 1.5349 | 20.0 | 120 | 1.5155 |
67
- | 1.5127 | 21.0 | 126 | 1.5145 |
68
- | 1.5436 | 22.0 | 132 | 1.5114 |
69
- | 1.5478 | 23.0 | 138 | 1.5145 |
70
- | 1.5041 | 24.0 | 144 | 1.5112 |
71
- | 1.4968 | 25.0 | 150 | 1.5114 |
72
- | 1.5202 | 26.0 | 156 | 1.5111 |
73
- | 1.5004 | 27.0 | 162 | 1.5104 |
74
- | 1.5004 | 28.0 | 168 | 1.5025 |
75
- | 1.502 | 29.0 | 174 | 1.5034 |
76
- | 1.5044 | 30.0 | 180 | 1.5057 |
77
- | 1.5234 | 31.0 | 186 | 1.5072 |
78
- | 1.5266 | 32.0 | 192 | 1.5074 |
79
- | 1.5209 | 33.0 | 198 | 1.5071 |
80
- | 1.502 | 34.0 | 204 | 1.5054 |
81
- | 1.5408 | 35.0 | 210 | 1.5056 |
82
- | 1.4966 | 36.0 | 216 | 1.5058 |
83
- | 1.5492 | 37.0 | 222 | 1.5049 |
84
- | 1.4984 | 38.0 | 228 | 1.5034 |
85
- | 1.5358 | 39.0 | 234 | 1.5030 |
86
- | 1.5127 | 40.0 | 240 | 1.5023 |
87
 
88
 
89
  ### 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: 0.2014
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 2.947 | 1.0 | 6 | 2.2690 |
48
+ | 2.0301 | 2.0 | 12 | 1.7402 |
49
+ | 1.5419 | 3.0 | 18 | 1.2929 |
50
+ | 1.2143 | 4.0 | 24 | 1.0901 |
51
+ | 1.0259 | 5.0 | 30 | 0.9702 |
52
+ | 0.9007 | 6.0 | 36 | 0.8471 |
53
+ | 0.7925 | 7.0 | 42 | 0.8145 |
54
+ | 0.7608 | 8.0 | 48 | 0.7531 |
55
+ | 0.7152 | 9.0 | 54 | 0.6772 |
56
+ | 0.6579 | 10.0 | 60 | 0.6378 |
57
+ | 0.6218 | 11.0 | 66 | 0.5797 |
58
+ | 0.5697 | 12.0 | 72 | 0.5534 |
59
+ | 0.5604 | 13.0 | 78 | 0.5225 |
60
+ | 0.5172 | 14.0 | 84 | 0.4961 |
61
+ | 0.4936 | 15.0 | 90 | 0.4773 |
62
+ | 0.4897 | 16.0 | 96 | 0.5122 |
63
+ | 0.499 | 17.0 | 102 | 0.4710 |
64
+ | 0.4578 | 18.0 | 108 | 0.4763 |
65
+ | 0.4455 | 19.0 | 114 | 0.4437 |
66
+ | 0.4382 | 20.0 | 120 | 0.4259 |
67
+ | 0.407 | 21.0 | 126 | 0.4043 |
68
+ | 0.3937 | 22.0 | 132 | 0.3824 |
69
+ | 0.3753 | 23.0 | 138 | 0.3754 |
70
+ | 0.3795 | 24.0 | 144 | 0.3496 |
71
+ | 0.3553 | 25.0 | 150 | 0.3459 |
72
+ | 0.3454 | 26.0 | 156 | 0.3359 |
73
+ | 0.3391 | 27.0 | 162 | 0.3221 |
74
+ | 0.3182 | 28.0 | 168 | 0.3027 |
75
+ | 0.3087 | 29.0 | 174 | 0.2958 |
76
+ | 0.288 | 30.0 | 180 | 0.2732 |
77
+ | 0.288 | 31.0 | 186 | 0.2607 |
78
+ | 0.2705 | 32.0 | 192 | 0.2444 |
79
+ | 0.2637 | 33.0 | 198 | 0.2393 |
80
+ | 0.2507 | 34.0 | 204 | 0.2264 |
81
+ | 0.2331 | 35.0 | 210 | 0.2193 |
82
+ | 0.2292 | 36.0 | 216 | 0.2118 |
83
+ | 0.2238 | 37.0 | 222 | 0.2089 |
84
+ | 0.2252 | 38.0 | 228 | 0.2051 |
85
+ | 0.2131 | 39.0 | 234 | 0.2043 |
86
+ | 0.2168 | 40.0 | 240 | 0.2014 |
87
 
88
 
89
  ### 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": 52
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": 52
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": 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,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:053134c68c277780219beb08c9c486e66a49b595e60f51b99ef57f737bf26e2f
3
- size 31205552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1718e7b86e2847840f6c60a23032d116ce48f66e5c61b46aed03617e0ddab03
3
+ size 31207604
runs/Mar04_13-53-42_d8c8da50ec4e/events.out.tfevents.1709560423.d8c8da50ec4e.409.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a170ff15555aa9829e2ace14a3cccfc58276e1b70d9d46fbfaeb703c8f8c8c4d
3
+ size 27997
tokenizer.json CHANGED
@@ -112,50 +112,51 @@
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
- "99": 16,
116
  "10": 17,
117
- "11": 18,
118
- "98": 19,
119
- "97": 20,
120
  "12": 21,
121
- "13": 22,
122
- "96": 23,
123
- "95": 24,
124
- "14": 25,
125
- "15": 26,
126
- "94": 27,
127
- "16": 28,
128
- "93": 29,
129
- "92": 30,
130
  "17": 31,
131
- "18": 32,
132
- "91": 33,
133
- "19": 34,
134
- "90": 35,
135
- "20": 36,
136
- "89": 37,
137
- "21": 38,
138
  "88": 39,
139
- "22": 40,
140
- "87": 41,
141
- "86": 42,
142
  "23": 43,
143
- "24": 44,
144
- "85": 45,
145
- "25": 46,
146
  "84": 47,
147
- "26": 48,
148
- "83": 49,
149
- "27": 50,
150
- "82": 51
 
151
  },
152
  "merges": [
153
- "9 9",
154
  "1 0",
 
155
  "1 1",
156
  "9 8",
157
- "9 7",
158
  "1 2",
 
159
  "1 3",
160
  "9 6",
161
  "9 5",
@@ -164,24 +165,24 @@
164
  "9 4",
165
  "1 6",
166
  "9 3",
167
- "9 2",
168
  "1 7",
 
169
  "1 8",
170
  "9 1",
171
  "1 9",
172
  "9 0",
173
  "2 0",
174
  "8 9",
175
- "2 1",
176
  "8 8",
 
177
  "2 2",
178
  "8 7",
179
- "8 6",
180
  "2 3",
 
181
  "2 4",
182
  "8 5",
183
- "2 5",
184
  "8 4",
 
185
  "2 6",
186
  "8 3",
187
  "2 7",
 
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
+ "=": 16,
116
  "10": 17,
117
+ "99": 18,
118
+ "11": 19,
119
+ "98": 20,
120
  "12": 21,
121
+ "97": 22,
122
+ "13": 23,
123
+ "96": 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
+ "18": 33,
133
+ "91": 34,
134
+ "19": 35,
135
+ "90": 36,
136
+ "20": 37,
137
+ "89": 38,
138
  "88": 39,
139
+ "21": 40,
140
+ "22": 41,
141
+ "87": 42,
142
  "23": 43,
143
+ "86": 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
  "1 0",
155
+ "9 9",
156
  "1 1",
157
  "9 8",
 
158
  "1 2",
159
+ "9 7",
160
  "1 3",
161
  "9 6",
162
  "9 5",
 
165
  "9 4",
166
  "1 6",
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
  "8 8",
177
+ "2 1",
178
  "2 2",
179
  "8 7",
 
180
  "2 3",
181
+ "8 6",
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 sha256:6de4df87d5fdcfb087440d5eafcae498fa1c8c454f47a2cb6dc311a85eb3b1c0
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7ad0845eaad54b53a1cc4f9a14b90eecd2370ffb4954a8c0a67c31b5e464ae
3
  size 5112