JamesMcMill
commited on
Commit
•
7633e49
1
Parent(s):
c230c6d
End of training
Browse files- README.md +58 -0
- added_tokens.json +3 -0
- bpe.codes +0 -0
- config.json +30 -0
- model.safetensors +3 -0
- runs/Mar07_09-56-26_RB-209A-27/events.out.tfevents.1709805387.RB-209A-27.4804.0 +3 -0
- runs/Mar07_09-56-26_RB-209A-27/events.out.tfevents.1709805652.RB-209A-27.4804.1 +3 -0
- runs/Mar07_10-09-26_RB-209A-27/events.out.tfevents.1709806167.RB-209A-27.11720.0 +3 -0
- runs/Mar07_10-09-26_RB-209A-27/events.out.tfevents.1709806264.RB-209A-27.11720.1 +3 -0
- runs/Mar07_10-22-19_RB-209A-27/events.out.tfevents.1709806939.RB-209A-27.16172.0 +3 -0
- runs/Mar07_10-22-19_RB-209A-27/events.out.tfevents.1709807045.RB-209A-27.16172.1 +3 -0
- runs/Mar07_10-26-34_RB-209A-27/events.out.tfevents.1709807194.RB-209A-27.14736.0 +3 -0
- runs/Mar07_10-26-34_RB-209A-27/events.out.tfevents.1709807291.RB-209A-27.14736.1 +3 -0
- runs/Mar07_10-29-26_RB-209A-27/events.out.tfevents.1709807367.RB-209A-27.13676.0 +3 -0
- runs/Mar07_10-29-26_RB-209A-27/events.out.tfevents.1709807462.RB-209A-27.13676.1 +3 -0
- runs/Mar07_10-33-30_RB-209A-27/events.out.tfevents.1709807610.RB-209A-27.5656.0 +3 -0
- runs/Mar07_10-33-30_RB-209A-27/events.out.tfevents.1709807703.RB-209A-27.5656.1 +3 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: finiteautomata/bertweet-base-sentiment-analysis
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- f1
|
8 |
+
model-index:
|
9 |
+
- name: finetuning-sentiment-model-1000-samples
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# finetuning-sentiment-model-1000-samples
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [finiteautomata/bertweet-base-sentiment-analysis](https://huggingface.co/finiteautomata/bertweet-base-sentiment-analysis) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0957
|
21 |
+
- Accuracy: {'accuracy': 0.995}
|
22 |
+
- F1: 0.9952
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 16
|
43 |
+
- eval_batch_size: 16
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 2
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- Transformers 4.38.2
|
56 |
+
- Pytorch 2.2.1+cpu
|
57 |
+
- Datasets 2.18.0
|
58 |
+
- Tokenizers 0.15.2
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<mask>": 64000
|
3 |
+
}
|
bpe.codes
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "finiteautomata/bertweet-base-sentiment-analysis",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 130,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"problem_type": "single_label_classification",
|
24 |
+
"tokenizer_class": "BertweetTokenizer",
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.38.2",
|
27 |
+
"type_vocab_size": 1,
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 64001
|
30 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dc89a56e4e905e74504bbe4be2102c95c0b451d32709a57cc1d8bf7c0f3cafc
|
3 |
+
size 539630168
|
runs/Mar07_09-56-26_RB-209A-27/events.out.tfevents.1709805387.RB-209A-27.4804.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d33ee58a975770bdcb99f6f24559beec1ebd93ec297253e9c082e8f0b7e745fd
|
3 |
+
size 5182
|
runs/Mar07_09-56-26_RB-209A-27/events.out.tfevents.1709805652.RB-209A-27.4804.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4c18cc760c161f0188ffb94e65b810ff42f56c8fb2320f7d188f655f867adcf
|
3 |
+
size 399
|
runs/Mar07_10-09-26_RB-209A-27/events.out.tfevents.1709806167.RB-209A-27.11720.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22978783764f51d34c25a2bf4aa4541369dd68672c92fd4090e4bdb83f7e2d84
|
3 |
+
size 5182
|
runs/Mar07_10-09-26_RB-209A-27/events.out.tfevents.1709806264.RB-209A-27.11720.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad939cb8ab812a9d2ef8520e1e6c06c996226380ab3dec1bb1a22ba4b59616ae
|
3 |
+
size 399
|
runs/Mar07_10-22-19_RB-209A-27/events.out.tfevents.1709806939.RB-209A-27.16172.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f276d0111faef0334bd2662f02b2fb52cea0ab431b90130c61c31191e7a5e31
|
3 |
+
size 5182
|
runs/Mar07_10-22-19_RB-209A-27/events.out.tfevents.1709807045.RB-209A-27.16172.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49badd12efbaedbc31973221340dd68925fb859364de2b004df489bce061fd57
|
3 |
+
size 399
|
runs/Mar07_10-26-34_RB-209A-27/events.out.tfevents.1709807194.RB-209A-27.14736.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bba7f0e52e4110d22ecb54ef0e1926abc40f3fb658d1b0b719a95946780f8f2
|
3 |
+
size 5182
|
runs/Mar07_10-26-34_RB-209A-27/events.out.tfevents.1709807291.RB-209A-27.14736.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fad7e471094421ad5f50a67d7a711369fcbce793960a44140de8b9e9d2b6c1b9
|
3 |
+
size 399
|
runs/Mar07_10-29-26_RB-209A-27/events.out.tfevents.1709807367.RB-209A-27.13676.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87452f121ee091566dafb8f86f8fc5653fe918c207b7b3f5083b734f3d9f64e9
|
3 |
+
size 5182
|
runs/Mar07_10-29-26_RB-209A-27/events.out.tfevents.1709807462.RB-209A-27.13676.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bcb5f9adfcdec3d16bfe3735af279831ca17db8bb59a12df5875e83b5d5e2ea
|
3 |
+
size 399
|
runs/Mar07_10-33-30_RB-209A-27/events.out.tfevents.1709807610.RB-209A-27.5656.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a63e98f5276e2566a0205b6ea3e60d159b851c205d3b3e9db4d621289373cd6
|
3 |
+
size 5182
|
runs/Mar07_10-33-30_RB-209A-27/events.out.tfevents.1709807703.RB-209A-27.5656.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:111db48fa82435431fb47ccad2d5a85c9ecc9789855db26e619dee891ec6403f
|
3 |
+
size 399
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"64000": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"ignore_mismatched_sizes": true,
|
49 |
+
"mask_token": "<mask>",
|
50 |
+
"model_max_length": 128,
|
51 |
+
"normalization": false,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "BertweetTokenizer",
|
55 |
+
"unk_token": "<unk>"
|
56 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e7aece840cad940caa75e759dc4b3b6dcd5c3d517e75c279dcafbf98fed3431
|
3 |
+
size 4984
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|