End of training
Browse files- README.md +16 -39
- config.json +62 -82
- pytorch_model.bin +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 2.
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -37,51 +37,28 @@ More information needed
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
-
- learning_rate: 3.3e-
|
41 |
-
- train_batch_size:
|
42 |
-
- eval_batch_size:
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
-
|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
-
| 2.
|
62 |
-
| 2.2594 | 0.99 | 2200 | 2.3336 | 0.3387 |
|
63 |
-
| 2.229 | 1.08 | 2400 | 2.3446 | 0.3213 |
|
64 |
-
| 2.3017 | 1.17 | 2600 | 2.3362 | 0.3327 |
|
65 |
-
| 2.2405 | 1.26 | 2800 | 2.3299 | 0.335 |
|
66 |
-
| 2.3291 | 1.35 | 3000 | 2.3291 | 0.33 |
|
67 |
-
| 2.2518 | 1.43 | 3200 | 2.3363 | 0.3297 |
|
68 |
-
| 2.268 | 1.52 | 3400 | 2.3623 | 0.3187 |
|
69 |
-
| 2.3198 | 1.61 | 3600 | 2.3480 | 0.3277 |
|
70 |
-
| 2.1873 | 1.7 | 3800 | 2.3355 | 0.3293 |
|
71 |
-
| 2.2634 | 1.79 | 4000 | 2.3291 | 0.326 |
|
72 |
-
| 2.1011 | 1.88 | 4200 | 2.3345 | 0.333 |
|
73 |
-
| 2.1965 | 1.97 | 4400 | 2.3383 | 0.3293 |
|
74 |
-
| 2.2368 | 2.06 | 4600 | 2.3320 | 0.329 |
|
75 |
-
| 2.2226 | 2.15 | 4800 | 2.3453 | 0.3263 |
|
76 |
-
| 2.2354 | 2.24 | 5000 | 2.3372 | 0.33 |
|
77 |
-
| 2.2829 | 2.33 | 5200 | 2.3547 | 0.3223 |
|
78 |
-
| 2.1544 | 2.42 | 5400 | 2.3336 | 0.3287 |
|
79 |
-
| 2.2777 | 2.51 | 5600 | 2.3425 | 0.3283 |
|
80 |
-
| 2.0763 | 2.6 | 5800 | 2.3339 | 0.3307 |
|
81 |
-
| 2.2738 | 2.69 | 6000 | 2.3389 | 0.3293 |
|
82 |
-
| 2.1013 | 2.78 | 6200 | 2.3411 | 0.327 |
|
83 |
-
| 2.1058 | 2.87 | 6400 | 2.3357 | 0.332 |
|
84 |
-
| 2.1621 | 2.96 | 6600 | 2.3380 | 0.3293 |
|
85 |
|
86 |
|
87 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.5779
|
21 |
+
- Accuracy: 0.2597
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 3.3e-05
|
41 |
+
- train_batch_size: 20
|
42 |
+
- eval_batch_size: 10
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 1.0
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| No log | 0.09 | 200 | 2.6170 | 0.2412 |
|
53 |
+
| No log | 0.19 | 400 | 2.6193 | 0.2412 |
|
54 |
+
| No log | 0.28 | 600 | 2.6109 | 0.2519 |
|
55 |
+
| No log | 0.37 | 800 | 2.5937 | 0.2551 |
|
56 |
+
| No log | 0.47 | 1000 | 2.5840 | 0.2607 |
|
57 |
+
| No log | 0.56 | 1200 | 2.5814 | 0.2620 |
|
58 |
+
| No log | 0.66 | 1400 | 2.5889 | 0.2535 |
|
59 |
+
| No log | 0.75 | 1600 | 2.5779 | 0.2595 |
|
60 |
+
| No log | 0.84 | 1800 | 2.5752 | 0.2622 |
|
61 |
+
| 2.4849 | 0.94 | 2000 | 2.5779 | 0.2597 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
|
63 |
|
64 |
### Framework versions
|
config.json
CHANGED
@@ -9,91 +9,71 @@
|
|
9 |
"dropout": 0.1,
|
10 |
"hidden_dim": 3072,
|
11 |
"id2label": {
|
12 |
-
"0": "
|
13 |
-
"1": "
|
14 |
-
"2": "
|
15 |
-
"3": "
|
16 |
-
"4": "
|
17 |
-
"5": "
|
18 |
-
"6": "
|
19 |
-
"7": "
|
20 |
-
"8": "
|
21 |
-
"9": "
|
22 |
-
"10": "
|
23 |
-
"11": "
|
24 |
-
"12": "
|
25 |
-
"13": "
|
26 |
-
"14": "
|
27 |
-
"15": "
|
28 |
-
"16": "
|
29 |
-
"17": "
|
30 |
-
"18": "
|
31 |
-
"19": "
|
32 |
-
"20": "
|
33 |
-
"21": "
|
34 |
-
"22": "
|
35 |
-
"23": "
|
36 |
-
"24": "
|
37 |
-
"25": "
|
38 |
-
"26": "
|
39 |
-
"27": "
|
40 |
-
"28": "
|
41 |
-
"29": "
|
42 |
-
"30": "
|
43 |
-
"31": "Photographer",
|
44 |
-
"32": "Phyllis",
|
45 |
-
"33": "Roy",
|
46 |
-
"34": "Ryan",
|
47 |
-
"35": "Sadiq (IT guy)",
|
48 |
-
"36": "Second Cindy",
|
49 |
-
"37": "Stanley",
|
50 |
-
"38": "Toby",
|
51 |
-
"39": "Todd Packer",
|
52 |
-
"40": "Tony"
|
53 |
},
|
54 |
"initializer_range": 0.02,
|
55 |
"label2id": {
|
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 |
-
"Photographer": 31,
|
88 |
-
"Phyllis": 32,
|
89 |
-
"Roy": 33,
|
90 |
-
"Ryan": 34,
|
91 |
-
"Sadiq (IT guy)": 35,
|
92 |
-
"Second Cindy": 36,
|
93 |
-
"Stanley": 37,
|
94 |
-
"Toby": 38,
|
95 |
-
"Todd Packer": 39,
|
96 |
-
"Tony": 40
|
97 |
},
|
98 |
"max_position_embeddings": 512,
|
99 |
"model_type": "distilbert",
|
|
|
9 |
"dropout": 0.1,
|
10 |
"hidden_dim": 3072,
|
11 |
"id2label": {
|
12 |
+
"0": "Andy",
|
13 |
+
"1": "Angela",
|
14 |
+
"2": "Charles",
|
15 |
+
"3": "Clark",
|
16 |
+
"4": "Creed",
|
17 |
+
"5": "Darryl",
|
18 |
+
"6": "David",
|
19 |
+
"7": "David Wallace",
|
20 |
+
"8": "Deangelo",
|
21 |
+
"9": "Dwight",
|
22 |
+
"10": "Erin",
|
23 |
+
"11": "Gabe",
|
24 |
+
"12": "Holly",
|
25 |
+
"13": "Jan",
|
26 |
+
"14": "Jim",
|
27 |
+
"15": "Jo",
|
28 |
+
"16": "Karen",
|
29 |
+
"17": "Kelly",
|
30 |
+
"18": "Kevin",
|
31 |
+
"19": "Meredith",
|
32 |
+
"20": "Michael",
|
33 |
+
"21": "Nellie",
|
34 |
+
"22": "Oscar",
|
35 |
+
"23": "Pam",
|
36 |
+
"24": "Pete",
|
37 |
+
"25": "Phyllis",
|
38 |
+
"26": "Robert",
|
39 |
+
"27": "Roy",
|
40 |
+
"28": "Ryan",
|
41 |
+
"29": "Stanley",
|
42 |
+
"30": "Toby"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
},
|
44 |
"initializer_range": 0.02,
|
45 |
"label2id": {
|
46 |
+
"Andy": 0,
|
47 |
+
"Angela": 1,
|
48 |
+
"Charles": 2,
|
49 |
+
"Clark": 3,
|
50 |
+
"Creed": 4,
|
51 |
+
"Darryl": 5,
|
52 |
+
"David": 6,
|
53 |
+
"David Wallace": 7,
|
54 |
+
"Deangelo": 8,
|
55 |
+
"Dwight": 9,
|
56 |
+
"Erin": 10,
|
57 |
+
"Gabe": 11,
|
58 |
+
"Holly": 12,
|
59 |
+
"Jan": 13,
|
60 |
+
"Jim": 14,
|
61 |
+
"Jo": 15,
|
62 |
+
"Karen": 16,
|
63 |
+
"Kelly": 17,
|
64 |
+
"Kevin": 18,
|
65 |
+
"Meredith": 19,
|
66 |
+
"Michael": 20,
|
67 |
+
"Nellie": 21,
|
68 |
+
"Oscar": 22,
|
69 |
+
"Pam": 23,
|
70 |
+
"Pete": 24,
|
71 |
+
"Phyllis": 25,
|
72 |
+
"Robert": 26,
|
73 |
+
"Roy": 27,
|
74 |
+
"Ryan": 28,
|
75 |
+
"Stanley": 29,
|
76 |
+
"Toby": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
},
|
78 |
"max_position_embeddings": 512,
|
79 |
"model_type": "distilbert",
|
pytorch_model.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:c1fad4844e4cbb392ef4d15409f2d3caaf911c6cfc9cae9693780f4d0177eea9
|
3 |
+
size 267943341
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cc712bb79d6cd37b9b82ff868848d83639f4677e1d1eef5be7989eeafb38c23
|
3 |
size 4027
|