salbatarni
commited on
Commit
•
f438ff1
1
Parent(s):
a5edf0a
Training in progress, step 65
Browse files- README.md +90 -0
- config.json +33 -0
- model.safetensors +3 -0
- runs/Aug22_09-38-15_4a91f28c1eab/events.out.tfevents.1724319507.4a91f28c1eab.34.0 +3 -0
- runs/Aug22_09-43-32_4a91f28c1eab/events.out.tfevents.1724319813.4a91f28c1eab.34.1 +3 -0
- runs/Aug22_09-48-51_4a91f28c1eab/events.out.tfevents.1724320132.4a91f28c1eab.34.2 +3 -0
- runs/Aug22_09-54-11_4a91f28c1eab/events.out.tfevents.1724320452.4a91f28c1eab.34.3 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google-bert/bert-base-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: bert_baseline_prompt_adherence_task3_fold2
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# bert_baseline_prompt_adherence_task3_fold2
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.3817
|
19 |
+
- Qwk: 0.6470
|
20 |
+
- Mse: 0.3818
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 2e-05
|
40 |
+
- train_batch_size: 16
|
41 |
+
- eval_batch_size: 16
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 1
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
|
50 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|
|
51 |
+
| No log | 0.0308 | 2 | 1.5377 | 0.0 | 1.5385 |
|
52 |
+
| No log | 0.0615 | 4 | 0.9550 | 0.1039 | 0.9553 |
|
53 |
+
| No log | 0.0923 | 6 | 0.7286 | 0.1294 | 0.7283 |
|
54 |
+
| No log | 0.1231 | 8 | 0.6242 | 0.0252 | 0.6236 |
|
55 |
+
| No log | 0.1538 | 10 | 0.6104 | 0.0252 | 0.6097 |
|
56 |
+
| No log | 0.1846 | 12 | 0.5825 | 0.0638 | 0.5819 |
|
57 |
+
| No log | 0.2154 | 14 | 0.5472 | 0.0709 | 0.5466 |
|
58 |
+
| No log | 0.2462 | 16 | 0.4973 | 0.1150 | 0.4968 |
|
59 |
+
| No log | 0.2769 | 18 | 0.4732 | 0.3908 | 0.4728 |
|
60 |
+
| No log | 0.3077 | 20 | 0.4665 | 0.5935 | 0.4662 |
|
61 |
+
| No log | 0.3385 | 22 | 0.4304 | 0.5976 | 0.4304 |
|
62 |
+
| No log | 0.3692 | 24 | 0.4506 | 0.5795 | 0.4507 |
|
63 |
+
| No log | 0.4 | 26 | 0.4830 | 0.5936 | 0.4830 |
|
64 |
+
| No log | 0.4308 | 28 | 0.5284 | 0.4334 | 0.5284 |
|
65 |
+
| No log | 0.4615 | 30 | 0.5470 | 0.4239 | 0.5469 |
|
66 |
+
| No log | 0.4923 | 32 | 0.5238 | 0.4711 | 0.5238 |
|
67 |
+
| No log | 0.5231 | 34 | 0.4764 | 0.5446 | 0.4766 |
|
68 |
+
| No log | 0.5538 | 36 | 0.4393 | 0.4824 | 0.4396 |
|
69 |
+
| No log | 0.5846 | 38 | 0.4326 | 0.4425 | 0.4329 |
|
70 |
+
| No log | 0.6154 | 40 | 0.4139 | 0.4814 | 0.4142 |
|
71 |
+
| No log | 0.6462 | 42 | 0.4079 | 0.5310 | 0.4081 |
|
72 |
+
| No log | 0.6769 | 44 | 0.4149 | 0.6150 | 0.4150 |
|
73 |
+
| No log | 0.7077 | 46 | 0.4218 | 0.6348 | 0.4218 |
|
74 |
+
| No log | 0.7385 | 48 | 0.4259 | 0.6583 | 0.4259 |
|
75 |
+
| No log | 0.7692 | 50 | 0.4150 | 0.6611 | 0.4151 |
|
76 |
+
| No log | 0.8 | 52 | 0.3977 | 0.6481 | 0.3977 |
|
77 |
+
| No log | 0.8308 | 54 | 0.3910 | 0.6396 | 0.3911 |
|
78 |
+
| No log | 0.8615 | 56 | 0.3892 | 0.6415 | 0.3892 |
|
79 |
+
| No log | 0.8923 | 58 | 0.3830 | 0.6405 | 0.3830 |
|
80 |
+
| No log | 0.9231 | 60 | 0.3792 | 0.6359 | 0.3792 |
|
81 |
+
| No log | 0.9538 | 62 | 0.3794 | 0.6359 | 0.3794 |
|
82 |
+
| No log | 0.9846 | 64 | 0.3817 | 0.6470 | 0.3818 |
|
83 |
+
|
84 |
+
|
85 |
+
### Framework versions
|
86 |
+
|
87 |
+
- Transformers 4.42.3
|
88 |
+
- Pytorch 2.1.2
|
89 |
+
- Datasets 2.20.0
|
90 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
+
},
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "bert",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"problem_type": "regression",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.42.3",
|
30 |
+
"type_vocab_size": 2,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 28996
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b8095c26e120287a196522e7fbb868cee839e200be5c58849f89f9bf69d0d4
|
3 |
+
size 433267692
|
runs/Aug22_09-38-15_4a91f28c1eab/events.out.tfevents.1724319507.4a91f28c1eab.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d780bca46640f487aaace997a9e534dc47ca582c785247bfe137b5a6b54f293a
|
3 |
+
size 16732
|
runs/Aug22_09-43-32_4a91f28c1eab/events.out.tfevents.1724319813.4a91f28c1eab.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba6e318c2d084abab07a0ce487d4a1a40a69a47c6b752f31635fd14904a10757
|
3 |
+
size 16732
|
runs/Aug22_09-48-51_4a91f28c1eab/events.out.tfevents.1724320132.4a91f28c1eab.34.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14cf319845c27eda78d0ad082f4fb4af2b09bd98647668d789c7c6b808747f61
|
3 |
+
size 16732
|
runs/Aug22_09-54-11_4a91f28c1eab/events.out.tfevents.1724320452.4a91f28c1eab.34.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b08a55fc3e6d524231001e78e5bcf8a111111b247ff8521853a2be3d560c4d2b
|
3 |
+
size 16732
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76080e477b3cdf7c7bf25f32855b52b3aec91fde1612ead22ccc822cc9784db3
|
3 |
+
size 5176
|