Model save
Browse files
Model/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4990a35b4c27cb32a45aad01a352f42bca9a08e3b563ed2f4199671355b42a98
|
3 |
+
size 1359228020
|
README.md
CHANGED
@@ -2,8 +2,6 @@
|
|
2 |
base_model: DeepPavlov/xlm-roberta-large-en-ru-mnli
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
metrics:
|
6 |
-
- accuracy
|
7 |
model-index:
|
8 |
- name: output
|
9 |
results: []
|
@@ -16,10 +14,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [DeepPavlov/xlm-roberta-large-en-ru-mnli](https://huggingface.co/DeepPavlov/xlm-roberta-large-en-ru-mnli) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
-
|
20 |
-
-
|
21 |
-
-
|
22 |
-
-
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -47,22 +50,6 @@ The following hyperparameters were used during training:
|
|
47 |
- lr_scheduler_warmup_ratio: 0.1
|
48 |
- num_epochs: 10
|
49 |
|
50 |
-
### Training results
|
51 |
-
|
52 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Mcc |
|
53 |
-
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:------:|
|
54 |
-
| 0.3994 | 1.0 | 1894 | 0.3931 | 0.8814 | 0.8622 | 0.8397 |
|
55 |
-
| 0.2659 | 2.0 | 3788 | 0.2872 | 0.9590 | 0.9560 | 0.9440 |
|
56 |
-
| 0.2262 | 3.0 | 5682 | 0.2528 | 0.9600 | 0.9566 | 0.9453 |
|
57 |
-
| 0.1514 | 4.0 | 7576 | 0.2465 | 0.9569 | 0.9567 | 0.9413 |
|
58 |
-
| 0.1319 | 5.0 | 9470 | 0.2808 | 0.9621 | 0.9617 | 0.9482 |
|
59 |
-
| 0.0649 | 6.0 | 11364 | 0.2656 | 0.9661 | 0.9656 | 0.9536 |
|
60 |
-
| 0.0513 | 7.0 | 13258 | 0.2716 | 0.9664 | 0.9662 | 0.9541 |
|
61 |
-
| 0.0159 | 8.0 | 15152 | 0.2948 | 0.9667 | 0.9665 | 0.9545 |
|
62 |
-
| 0.0121 | 9.0 | 17046 | 0.2972 | 0.9664 | 0.9662 | 0.9541 |
|
63 |
-
| 0.009 | 10.0 | 18940 | 0.3006 | 0.9677 | 0.9674 | 0.9558 |
|
64 |
-
|
65 |
-
|
66 |
### Framework versions
|
67 |
|
68 |
- Transformers 4.35.2
|
|
|
2 |
base_model: DeepPavlov/xlm-roberta-large-en-ru-mnli
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
model-index:
|
6 |
- name: output
|
7 |
results: []
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [DeepPavlov/xlm-roberta-large-en-ru-mnli](https://huggingface.co/DeepPavlov/xlm-roberta-large-en-ru-mnli) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- eval_loss: 0.2408
|
18 |
+
- eval_accuracy: 0.9691
|
19 |
+
- eval_f1-score: 0.9693
|
20 |
+
- eval_mcc: 0.9566
|
21 |
+
- eval_runtime: 78.6359
|
22 |
+
- eval_samples_per_second: 38.278
|
23 |
+
- eval_steps_per_second: 9.576
|
24 |
+
- epoch: 6.0
|
25 |
+
- step: 10536
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
50 |
- lr_scheduler_warmup_ratio: 0.1
|
51 |
- num_epochs: 10
|
52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
### Framework versions
|
54 |
|
55 |
- Transformers 4.35.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1359228020
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:121f9b898b5999c6ae59d43fc912e7899c2fd302998e33bd8df5c95151f976c8
|
3 |
size 1359228020
|
runs/Dec20_20-34-15_d0cb79e7e9f5/events.out.tfevents.1703104459.d0cb79e7e9f5.267.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39619a571b496d989e0475caca34bb14dc24097101345bfa1e66129f36286f0f
|
3 |
+
size 10715
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e8a119d661476f7e4ba025aff6087e3e3dd9c823ffef2cd1824e5c6680c02d1
|
3 |
size 4664
|