disk0dancer
commited on
End of training
Browse files
README.md
CHANGED
@@ -3,11 +3,6 @@ license: apache-2.0
|
|
3 |
base_model: ai-forever/ruBert-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
metrics:
|
7 |
-
- precision
|
8 |
-
- recall
|
9 |
-
- f1
|
10 |
-
- accuracy
|
11 |
model-index:
|
12 |
- name: ruBert-base-finetuned-pos
|
13 |
results: []
|
@@ -18,13 +13,18 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# ruBert-base-finetuned-pos
|
20 |
|
21 |
-
This model is a fine-tuned version of [ai-forever/ruBert-base](https://huggingface.co/ai-forever/ruBert-base) on
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
-
|
24 |
-
-
|
25 |
-
-
|
26 |
-
-
|
27 |
-
-
|
|
|
|
|
|
|
|
|
|
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -49,63 +49,7 @@ The following hyperparameters were used during training:
|
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
-
- num_epochs:
|
53 |
-
|
54 |
-
### Training results
|
55 |
-
|
56 |
-
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
-
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
-
| No log | 1.0 | 2 | 3.2246 | 0.0300 | 0.0160 | 0.0209 | 0.0062 |
|
59 |
-
| No log | 2.0 | 4 | 2.6688 | 0.0 | 0.0 | 0.0 | 0.0021 |
|
60 |
-
| No log | 3.0 | 6 | 2.1227 | 0.0 | 0.0 | 0.0 | 0.0021 |
|
61 |
-
| No log | 4.0 | 8 | 1.6906 | 0.0 | 0.0 | 0.0 | 0.0 |
|
62 |
-
| No log | 5.0 | 10 | 1.4171 | 0.0 | 0.0 | 0.0 | 0.0 |
|
63 |
-
| No log | 6.0 | 12 | 1.2636 | 0.0 | 0.0 | 0.0 | 0.0 |
|
64 |
-
| No log | 7.0 | 14 | 1.1762 | 0.0 | 0.0 | 0.0 | 0.0 |
|
65 |
-
| No log | 8.0 | 16 | 1.1150 | 0.0 | 0.0 | 0.0 | 0.0 |
|
66 |
-
| No log | 9.0 | 18 | 1.0601 | 0.0 | 0.0 | 0.0 | 0.0 |
|
67 |
-
| No log | 10.0 | 20 | 1.0094 | 0.0 | 0.0 | 0.0 | 0.0 |
|
68 |
-
| No log | 11.0 | 22 | 0.9662 | 0.0 | 0.0 | 0.0 | 0.0021 |
|
69 |
-
| No log | 12.0 | 24 | 0.9311 | 0.0 | 0.0 | 0.0 | 0.0124 |
|
70 |
-
| No log | 13.0 | 26 | 0.9011 | 0.0 | 0.0 | 0.0 | 0.0847 |
|
71 |
-
| No log | 14.0 | 28 | 0.8737 | 0.0 | 0.0 | 0.0 | 0.1921 |
|
72 |
-
| No log | 15.0 | 30 | 0.8476 | 0.0 | 0.0 | 0.0 | 0.2231 |
|
73 |
-
| No log | 16.0 | 32 | 0.8230 | 0.0 | 0.0 | 0.0 | 0.2335 |
|
74 |
-
| No log | 17.0 | 34 | 0.7996 | 0.5 | 0.0160 | 0.0310 | 0.25 |
|
75 |
-
| No log | 18.0 | 36 | 0.7772 | 0.5 | 0.0342 | 0.0641 | 0.2665 |
|
76 |
-
| No log | 19.0 | 38 | 0.7550 | 0.4630 | 0.0571 | 0.1016 | 0.2913 |
|
77 |
-
| No log | 20.0 | 40 | 0.7323 | 0.4706 | 0.0731 | 0.1265 | 0.3079 |
|
78 |
-
| No log | 21.0 | 42 | 0.7100 | 0.4333 | 0.0890 | 0.1477 | 0.3244 |
|
79 |
-
| No log | 22.0 | 44 | 0.6888 | 0.4122 | 0.1233 | 0.1898 | 0.3595 |
|
80 |
-
| No log | 23.0 | 46 | 0.6686 | 0.3778 | 0.1553 | 0.2201 | 0.3967 |
|
81 |
-
| No log | 24.0 | 48 | 0.6490 | 0.3972 | 0.1941 | 0.2607 | 0.4236 |
|
82 |
-
| No log | 25.0 | 50 | 0.6304 | 0.4149 | 0.2283 | 0.2946 | 0.4483 |
|
83 |
-
| No log | 26.0 | 52 | 0.6130 | 0.4504 | 0.2694 | 0.3371 | 0.4773 |
|
84 |
-
| No log | 27.0 | 54 | 0.5967 | 0.4593 | 0.2831 | 0.3503 | 0.4855 |
|
85 |
-
| No log | 28.0 | 56 | 0.5815 | 0.4657 | 0.2945 | 0.3608 | 0.4938 |
|
86 |
-
| No log | 29.0 | 58 | 0.5675 | 0.4842 | 0.3151 | 0.3817 | 0.5041 |
|
87 |
-
| No log | 30.0 | 60 | 0.5545 | 0.4916 | 0.3356 | 0.3989 | 0.5165 |
|
88 |
-
| No log | 31.0 | 62 | 0.5423 | 0.4967 | 0.3447 | 0.4070 | 0.5269 |
|
89 |
-
| No log | 32.0 | 64 | 0.5311 | 0.5016 | 0.3539 | 0.4150 | 0.5372 |
|
90 |
-
| No log | 33.0 | 66 | 0.5209 | 0.5016 | 0.3539 | 0.4150 | 0.5372 |
|
91 |
-
| No log | 34.0 | 68 | 0.5118 | 0.5063 | 0.3653 | 0.4244 | 0.5455 |
|
92 |
-
| No log | 35.0 | 70 | 0.5035 | 0.5140 | 0.3767 | 0.4348 | 0.5537 |
|
93 |
-
| No log | 36.0 | 72 | 0.4960 | 0.5105 | 0.3881 | 0.4410 | 0.5599 |
|
94 |
-
| No log | 37.0 | 74 | 0.4891 | 0.5208 | 0.3995 | 0.4522 | 0.5682 |
|
95 |
-
| No log | 38.0 | 76 | 0.4827 | 0.5249 | 0.4087 | 0.4596 | 0.5723 |
|
96 |
-
| No log | 39.0 | 78 | 0.4770 | 0.5407 | 0.4247 | 0.4757 | 0.5806 |
|
97 |
-
| No log | 40.0 | 80 | 0.4719 | 0.5473 | 0.4361 | 0.4854 | 0.5888 |
|
98 |
-
| No log | 41.0 | 82 | 0.4673 | 0.5568 | 0.4475 | 0.4962 | 0.5971 |
|
99 |
-
| No log | 42.0 | 84 | 0.4632 | 0.5581 | 0.4498 | 0.4981 | 0.5992 |
|
100 |
-
| No log | 43.0 | 86 | 0.4597 | 0.5682 | 0.4658 | 0.5119 | 0.6074 |
|
101 |
-
| No log | 44.0 | 88 | 0.4565 | 0.5754 | 0.4703 | 0.5176 | 0.6136 |
|
102 |
-
| No log | 45.0 | 90 | 0.4538 | 0.5766 | 0.4726 | 0.5194 | 0.6136 |
|
103 |
-
| No log | 46.0 | 92 | 0.4515 | 0.5810 | 0.4749 | 0.5226 | 0.6157 |
|
104 |
-
| No log | 47.0 | 94 | 0.4497 | 0.5845 | 0.4817 | 0.5282 | 0.6178 |
|
105 |
-
| No log | 48.0 | 96 | 0.4484 | 0.5918 | 0.4932 | 0.5380 | 0.6198 |
|
106 |
-
| No log | 49.0 | 98 | 0.4477 | 0.5918 | 0.4932 | 0.5380 | 0.6198 |
|
107 |
-
| No log | 50.0 | 100 | 0.4473 | 0.5945 | 0.4954 | 0.5405 | 0.6219 |
|
108 |
-
|
109 |
|
110 |
### Framework versions
|
111 |
|
|
|
3 |
base_model: ai-forever/ruBert-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
- name: ruBert-base-finetuned-pos
|
8 |
results: []
|
|
|
13 |
|
14 |
# ruBert-base-finetuned-pos
|
15 |
|
16 |
+
This model is a fine-tuned version of [ai-forever/ruBert-base](https://huggingface.co/ai-forever/ruBert-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- eval_loss: 0.0021
|
19 |
+
- eval_precision: 0.9995
|
20 |
+
- eval_recall: 0.9994
|
21 |
+
- eval_f1: 0.9995
|
22 |
+
- eval_accuracy: 0.9996
|
23 |
+
- eval_runtime: 39.8442
|
24 |
+
- eval_samples_per_second: 161.705
|
25 |
+
- eval_steps_per_second: 2.535
|
26 |
+
- epoch: 3.0
|
27 |
+
- step: 1059
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
49 |
- seed: 42
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
### Framework versions
|
55 |
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 711062560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f27c9d39236051dca997c77239ecc8d101cbc3e696637d6fa8421f36f9cf45c
|
3 |
size 711062560
|
runs/Mar15_13-26-29_af6d53f073f1/events.out.tfevents.1710509191.af6d53f073f1.1790.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64fb6c2264113ccbcaa09169458b72aeaecaeee627807ed73bbcffa1a2a2b521
|
3 |
+
size 9302
|
tmp-checkpoint-1059/config.json
ADDED
@@ -0,0 +1,147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ai-forever/ruBert-base",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "Not",
|
15 |
+
"2": "Abbr",
|
16 |
+
"3": "Adj",
|
17 |
+
"4": "Adv",
|
18 |
+
"5": "Adv/action_des\u0441",
|
19 |
+
"6": "Adv/action_time",
|
20 |
+
"7": "Adv/measure",
|
21 |
+
"8": "Adv/place",
|
22 |
+
"9": "Adv/emph",
|
23 |
+
"10": "Advt",
|
24 |
+
"11": "Advt1",
|
25 |
+
"12": "Aux",
|
26 |
+
"13": "Bracket",
|
27 |
+
"14": "Colon",
|
28 |
+
"15": "Comma",
|
29 |
+
"16": "Conj.comp",
|
30 |
+
"17": "Coord",
|
31 |
+
"18": "Dash",
|
32 |
+
"19": "Dot",
|
33 |
+
"20": "Ellipsis",
|
34 |
+
"21": "Fw",
|
35 |
+
"22": "Interj.",
|
36 |
+
"23": "Interrog.word",
|
37 |
+
"24": "Introduct",
|
38 |
+
"25": "Mark/excl",
|
39 |
+
"26": "Mark/quest",
|
40 |
+
"27": "Measure",
|
41 |
+
"28": "N",
|
42 |
+
"29": "Num",
|
43 |
+
"30": "Num/ordinal",
|
44 |
+
"31": "Part/dem",
|
45 |
+
"32": "Part/excl",
|
46 |
+
"33": "Part/limit",
|
47 |
+
"34": "Part/imp",
|
48 |
+
"35": "Part/intens",
|
49 |
+
"36": "Part/neg",
|
50 |
+
"37": "Part/quest",
|
51 |
+
"38": "Part/soft",
|
52 |
+
"39": "Prep",
|
53 |
+
"40": "Pron",
|
54 |
+
"41": "Pron/attr",
|
55 |
+
"42": "Pron/dem",
|
56 |
+
"43": "Pron/neg",
|
57 |
+
"44": "Pron/pos",
|
58 |
+
"45": "Pron/rel",
|
59 |
+
"46": "Particip/adj",
|
60 |
+
"47": "Particip/v",
|
61 |
+
"48": "Punct",
|
62 |
+
"49": "Quote",
|
63 |
+
"50": "Semicolon",
|
64 |
+
"51": "State",
|
65 |
+
"52": "Sub",
|
66 |
+
"53": "Vf",
|
67 |
+
"54": "Vinf",
|
68 |
+
"55": "Vm"
|
69 |
+
},
|
70 |
+
"initializer_range": 0.02,
|
71 |
+
"intermediate_size": 3072,
|
72 |
+
"label2id": {
|
73 |
+
"Abbr": 2,
|
74 |
+
"Adj": 3,
|
75 |
+
"Adv": 4,
|
76 |
+
"Adv/action_des\u0441": 5,
|
77 |
+
"Adv/action_time": 6,
|
78 |
+
"Adv/emph": 9,
|
79 |
+
"Adv/measure": 7,
|
80 |
+
"Adv/place": 8,
|
81 |
+
"Advt": 10,
|
82 |
+
"Advt1": 11,
|
83 |
+
"Aux": 12,
|
84 |
+
"Bracket": 13,
|
85 |
+
"Colon": 14,
|
86 |
+
"Comma": 15,
|
87 |
+
"Conj.comp": 16,
|
88 |
+
"Coord": 17,
|
89 |
+
"Dash": 18,
|
90 |
+
"Dot": 19,
|
91 |
+
"Ellipsis": 20,
|
92 |
+
"Fw": 21,
|
93 |
+
"Interj.": 22,
|
94 |
+
"Interrog.word": 23,
|
95 |
+
"Introduct": 24,
|
96 |
+
"Mark/excl": 25,
|
97 |
+
"Mark/quest": 26,
|
98 |
+
"Measure": 27,
|
99 |
+
"N": 28,
|
100 |
+
"Not": 1,
|
101 |
+
"Num": 29,
|
102 |
+
"Num/ordinal": 30,
|
103 |
+
"O": 0,
|
104 |
+
"Part/dem": 31,
|
105 |
+
"Part/excl": 32,
|
106 |
+
"Part/imp": 34,
|
107 |
+
"Part/intens": 35,
|
108 |
+
"Part/limit": 33,
|
109 |
+
"Part/neg": 36,
|
110 |
+
"Part/quest": 37,
|
111 |
+
"Part/soft": 38,
|
112 |
+
"Particip/adj": 46,
|
113 |
+
"Particip/v": 47,
|
114 |
+
"Prep": 39,
|
115 |
+
"Pron": 40,
|
116 |
+
"Pron/attr": 41,
|
117 |
+
"Pron/dem": 42,
|
118 |
+
"Pron/neg": 43,
|
119 |
+
"Pron/pos": 44,
|
120 |
+
"Pron/rel": 45,
|
121 |
+
"Punct": 48,
|
122 |
+
"Quote": 49,
|
123 |
+
"Semicolon": 50,
|
124 |
+
"State": 51,
|
125 |
+
"Sub": 52,
|
126 |
+
"Vf": 53,
|
127 |
+
"Vinf": 54,
|
128 |
+
"Vm": 55
|
129 |
+
},
|
130 |
+
"layer_norm_eps": 1e-12,
|
131 |
+
"max_position_embeddings": 512,
|
132 |
+
"model_type": "bert",
|
133 |
+
"num_attention_heads": 12,
|
134 |
+
"num_hidden_layers": 12,
|
135 |
+
"pad_token_id": 0,
|
136 |
+
"pooler_fc_size": 768,
|
137 |
+
"pooler_num_attention_heads": 12,
|
138 |
+
"pooler_num_fc_layers": 3,
|
139 |
+
"pooler_size_per_head": 128,
|
140 |
+
"pooler_type": "first_token_transform",
|
141 |
+
"position_embedding_type": "absolute",
|
142 |
+
"torch_dtype": "float32",
|
143 |
+
"transformers_version": "4.38.2",
|
144 |
+
"type_vocab_size": 2,
|
145 |
+
"use_cache": true,
|
146 |
+
"vocab_size": 120138
|
147 |
+
}
|
tmp-checkpoint-1059/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f27c9d39236051dca997c77239ecc8d101cbc3e696637d6fa8421f36f9cf45c
|
3 |
+
size 711062560
|
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 sha256:91e133dc65cfa7de7b6309e9d4ffa61691d54a4222c584940217dddb4b3f6a40
|
3 |
size 4920
|