End of training
Browse files- README.md +11 -11
- config.json +5 -5
- generation_config.json +3 -3
- model.safetensors +2 -2
- runs/Feb28_13-26-30_3897ec21fae5/events.out.tfevents.1709126790.3897ec21fae5.17803.0 +3 -0
- runs/Feb28_13-28-13_3897ec21fae5/events.out.tfevents.1709126894.3897ec21fae5.18243.0 +3 -0
- tokenizer.json +106 -61
- tokenizer_config.json +36 -4
- 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 |
|
@@ -44,16 +44,16 @@ The following hyperparameters were used during training:
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
-
|
|
48 |
-
|
|
49 |
-
| 1.
|
50 |
-
| 1.
|
51 |
-
| 1.
|
52 |
-
| 1.
|
53 |
-
|
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
|
58 |
|
59 |
### 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: 0.8243
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
44 |
|
45 |
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| 2.8893 | 1.0 | 6 | 2.1271 |
|
48 |
+
| 1.9669 | 2.0 | 12 | 1.8233 |
|
49 |
+
| 1.6822 | 3.0 | 18 | 1.5134 |
|
50 |
+
| 1.3991 | 4.0 | 24 | 1.2639 |
|
51 |
+
| 1.1731 | 5.0 | 30 | 1.1030 |
|
52 |
+
| 1.0664 | 6.0 | 36 | 0.9758 |
|
53 |
+
| 0.9729 | 7.0 | 42 | 0.9245 |
|
54 |
+
| 0.9171 | 8.0 | 48 | 0.8696 |
|
55 |
+
| 0.8722 | 9.0 | 54 | 0.8384 |
|
56 |
+
| 0.8487 | 10.0 | 60 | 0.8243 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
config.json
CHANGED
@@ -78,9 +78,9 @@
|
|
78 |
"typical_p": 1.0,
|
79 |
"use_bfloat16": false,
|
80 |
"use_cache": true,
|
81 |
-
"vocab_size":
|
82 |
},
|
83 |
-
"decoder_start_token_id":
|
84 |
"encoder": {
|
85 |
"_name_or_path": "",
|
86 |
"add_cross_attention": false,
|
@@ -157,12 +157,12 @@
|
|
157 |
"typical_p": 1.0,
|
158 |
"use_bfloat16": false,
|
159 |
"use_cache": true,
|
160 |
-
"vocab_size":
|
161 |
},
|
162 |
-
"eos_token_id":
|
163 |
"is_encoder_decoder": true,
|
164 |
"model_type": "encoder-decoder",
|
165 |
-
"pad_token_id":
|
166 |
"torch_dtype": "float32",
|
167 |
"transformers_version": "4.37.2"
|
168 |
}
|
|
|
78 |
"typical_p": 1.0,
|
79 |
"use_bfloat16": false,
|
80 |
"use_cache": true,
|
81 |
+
"vocab_size": 56
|
82 |
},
|
83 |
+
"decoder_start_token_id": 1,
|
84 |
"encoder": {
|
85 |
"_name_or_path": "",
|
86 |
"add_cross_attention": false,
|
|
|
157 |
"typical_p": 1.0,
|
158 |
"use_bfloat16": false,
|
159 |
"use_cache": true,
|
160 |
+
"vocab_size": 56
|
161 |
},
|
162 |
+
"eos_token_id": 6,
|
163 |
"is_encoder_decoder": true,
|
164 |
"model_type": "encoder-decoder",
|
165 |
+
"pad_token_id": 3,
|
166 |
"torch_dtype": "float32",
|
167 |
"transformers_version": "4.37.2"
|
168 |
}
|
generation_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"decoder_start_token_id":
|
4 |
-
"eos_token_id":
|
5 |
-
"pad_token_id":
|
6 |
"transformers_version": "4.37.2"
|
7 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 1,
|
4 |
+
"eos_token_id": 6,
|
5 |
+
"pad_token_id": 3,
|
6 |
"transformers_version": "4.37.2"
|
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 sha256:3c786ce574c7b54427c775c1c401bc60b3a2a1bf4da9d34ebd224728b1d9fdb1
|
3 |
+
size 31213760
|
runs/Feb28_13-26-30_3897ec21fae5/events.out.tfevents.1709126790.3897ec21fae5.17803.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8918b9c98527482fb0ae44af3cc57d56c66e466f5fc8108c4c2b57a3b6988cb3
|
3 |
+
size 4184
|
runs/Feb28_13-28-13_3897ec21fae5/events.out.tfevents.1709126894.3897ec21fae5.18243.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f49d302e9b6efdd89a1ff829ad435c123743f3b816dcc97ded912b68c1e009e
|
3 |
+
size 12864
|
tokenizer.json
CHANGED
@@ -4,8 +4,8 @@
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
-
"id":
|
8 |
-
"content": "[
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
@@ -13,7 +13,7 @@
|
|
13 |
"special": true
|
14 |
},
|
15 |
{
|
16 |
-
"id":
|
17 |
"content": "[CLS]",
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
@@ -22,7 +22,43 @@
|
|
22 |
"special": true
|
23 |
},
|
24 |
{
|
25 |
-
"id":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
"content": "[EOS]",
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
@@ -40,86 +76,94 @@
|
|
40 |
"model": {
|
41 |
"type": "BPE",
|
42 |
"dropout": null,
|
43 |
-
"unk_token":
|
44 |
"continuing_subword_prefix": null,
|
45 |
"end_of_word_suffix": null,
|
46 |
"fuse_unk": false,
|
47 |
"byte_fallback": false,
|
48 |
"vocab": {
|
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 |
"merges": [
|
99 |
-
"1 0",
|
100 |
"9 9",
|
101 |
-
"1
|
102 |
"9 8",
|
|
|
103 |
"1 2",
|
104 |
"9 7",
|
105 |
-
"9 6",
|
106 |
"1 3",
|
107 |
-
"
|
108 |
"9 5",
|
109 |
-
"1
|
110 |
"9 4",
|
|
|
111 |
"1 6",
|
112 |
"9 3",
|
113 |
"1 7",
|
114 |
"9 2",
|
115 |
-
"1 8",
|
116 |
"9 1",
|
|
|
117 |
"1 9",
|
118 |
"9 0",
|
119 |
"2 0",
|
120 |
"8 9",
|
121 |
-
"8 8",
|
122 |
"2 1",
|
|
|
123 |
"2 2",
|
124 |
"8 7",
|
125 |
"2 3",
|
@@ -130,7 +174,8 @@
|
|
130 |
"2 5",
|
131 |
"2 6",
|
132 |
"8 3",
|
133 |
-
"2 7"
|
|
|
134 |
]
|
135 |
}
|
136 |
}
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "[UNK]",
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
|
|
13 |
"special": true
|
14 |
},
|
15 |
{
|
16 |
+
"id": 1,
|
17 |
"content": "[CLS]",
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
|
|
22 |
"special": true
|
23 |
},
|
24 |
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "[SEP]",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 3,
|
35 |
+
"content": "[PAD]",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 4,
|
44 |
+
"content": "[MASK]",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"id": 5,
|
53 |
+
"content": "[BOS]",
|
54 |
+
"single_word": false,
|
55 |
+
"lstrip": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"id": 6,
|
62 |
"content": "[EOS]",
|
63 |
"single_word": false,
|
64 |
"lstrip": false,
|
|
|
76 |
"model": {
|
77 |
"type": "BPE",
|
78 |
"dropout": null,
|
79 |
+
"unk_token": "[UNK]",
|
80 |
"continuing_subword_prefix": null,
|
81 |
"end_of_word_suffix": null,
|
82 |
"fuse_unk": false,
|
83 |
"byte_fallback": false,
|
84 |
"vocab": {
|
85 |
+
"[UNK]": 0,
|
86 |
+
"[CLS]": 1,
|
87 |
+
"[SEP]": 2,
|
88 |
+
"[PAD]": 3,
|
89 |
+
"[MASK]": 4,
|
90 |
+
"[BOS]": 5,
|
91 |
+
"[EOS]": 6,
|
92 |
+
"+": 7,
|
93 |
+
"-": 8,
|
94 |
+
"0": 9,
|
95 |
+
"1": 10,
|
96 |
+
"2": 11,
|
97 |
+
"3": 12,
|
98 |
+
"4": 13,
|
99 |
+
"5": 14,
|
100 |
+
"6": 15,
|
101 |
+
"7": 16,
|
102 |
+
"8": 17,
|
103 |
+
"9": 18,
|
104 |
+
"=": 19,
|
105 |
+
"99": 20,
|
106 |
+
"10": 21,
|
107 |
+
"98": 22,
|
108 |
+
"11": 23,
|
109 |
+
"12": 24,
|
110 |
+
"97": 25,
|
111 |
+
"13": 26,
|
112 |
+
"96": 27,
|
113 |
+
"95": 28,
|
114 |
+
"14": 29,
|
115 |
+
"94": 30,
|
116 |
+
"15": 31,
|
117 |
+
"16": 32,
|
118 |
+
"93": 33,
|
119 |
+
"17": 34,
|
120 |
+
"92": 35,
|
121 |
+
"91": 36,
|
122 |
+
"18": 37,
|
123 |
+
"19": 38,
|
124 |
+
"90": 39,
|
125 |
+
"20": 40,
|
126 |
+
"89": 41,
|
127 |
+
"21": 42,
|
128 |
+
"88": 43,
|
129 |
+
"22": 44,
|
130 |
+
"87": 45,
|
131 |
+
"23": 46,
|
132 |
+
"86": 47,
|
133 |
+
"24": 48,
|
134 |
+
"85": 49,
|
135 |
+
"84": 50,
|
136 |
+
"25": 51,
|
137 |
+
"26": 52,
|
138 |
+
"83": 53,
|
139 |
+
"27": 54,
|
140 |
+
"82": 55
|
141 |
},
|
142 |
"merges": [
|
|
|
143 |
"9 9",
|
144 |
+
"1 0",
|
145 |
"9 8",
|
146 |
+
"1 1",
|
147 |
"1 2",
|
148 |
"9 7",
|
|
|
149 |
"1 3",
|
150 |
+
"9 6",
|
151 |
"9 5",
|
152 |
+
"1 4",
|
153 |
"9 4",
|
154 |
+
"1 5",
|
155 |
"1 6",
|
156 |
"9 3",
|
157 |
"1 7",
|
158 |
"9 2",
|
|
|
159 |
"9 1",
|
160 |
+
"1 8",
|
161 |
"1 9",
|
162 |
"9 0",
|
163 |
"2 0",
|
164 |
"8 9",
|
|
|
165 |
"2 1",
|
166 |
+
"8 8",
|
167 |
"2 2",
|
168 |
"8 7",
|
169 |
"2 3",
|
|
|
174 |
"2 5",
|
175 |
"2 6",
|
176 |
"8 3",
|
177 |
+
"2 7",
|
178 |
+
"8 2"
|
179 |
]
|
180 |
}
|
181 |
}
|
tokenizer_config.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
-
"content": "[
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
"content": "[CLS]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
@@ -16,7 +16,39 @@
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"content": "[EOS]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[UNK]",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"1": {
|
12 |
"content": "[CLS]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[PAD]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "[BOS]",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
"content": "[EOS]",
|
53 |
"lstrip": false,
|
54 |
"normalized": false,
|
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 sha256:6659b0093eeff414bea7b0676fa26b8ced67d1bab20bc510776e16dcea6efb68
|
3 |
size 4920
|