Commit
•
1fb5f36
1
Parent(s):
77084b9
add model
Browse files- .gitignore +1 -0
- README.md +73 -0
- all_results.json +16 -0
- config.json +41 -0
- eval_results.json +11 -0
- pytorch_model.bin +3 -0
- runs/Jul26_10-48-21_87e5b6406975/1627296525.161824/events.out.tfevents.1627296525.87e5b6406975.485.1 +3 -0
- runs/Jul26_10-48-21_87e5b6406975/events.out.tfevents.1627296525.87e5b6406975.485.0 +3 -0
- runs/Jul26_10-48-21_87e5b6406975/events.out.tfevents.1627297045.87e5b6406975.485.2 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +25 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- glue
|
9 |
+
metrics:
|
10 |
+
- spearmanr
|
11 |
+
model_index:
|
12 |
+
- name: stsb
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Text Classification
|
16 |
+
type: text-classification
|
17 |
+
dataset:
|
18 |
+
name: GLUE STSB
|
19 |
+
type: glue
|
20 |
+
args: stsb
|
21 |
+
metric:
|
22 |
+
name: Spearmanr
|
23 |
+
type: spearmanr
|
24 |
+
value: 0.9050744778895732
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# stsb
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE STSB dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.3978
|
35 |
+
- Pearson: 0.9090
|
36 |
+
- Spearmanr: 0.9051
|
37 |
+
- Combined Score: 0.9071
|
38 |
+
|
39 |
+
## Model description
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Intended uses & limitations
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training and evaluation data
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training procedure
|
52 |
+
|
53 |
+
### Training hyperparameters
|
54 |
+
|
55 |
+
The following hyperparameters were used during training:
|
56 |
+
- learning_rate: 3e-05
|
57 |
+
- train_batch_size: 64
|
58 |
+
- eval_batch_size: 8
|
59 |
+
- seed: 42
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- num_epochs: 4.0
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- Transformers 4.9.0
|
71 |
+
- Pytorch 1.9.0+cu102
|
72 |
+
- Datasets 1.10.2
|
73 |
+
- Tokenizers 0.10.3
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_combined_score": 0.9070512696741792,
|
4 |
+
"eval_loss": 0.3978178799152374,
|
5 |
+
"eval_pearson": 0.9090280614587851,
|
6 |
+
"eval_runtime": 13.6802,
|
7 |
+
"eval_samples": 1500,
|
8 |
+
"eval_samples_per_second": 109.648,
|
9 |
+
"eval_spearmanr": 0.9050744778895732,
|
10 |
+
"eval_steps_per_second": 13.743,
|
11 |
+
"train_loss": 0.43474773830837676,
|
12 |
+
"train_runtime": 506.7423,
|
13 |
+
"train_samples": 5749,
|
14 |
+
"train_samples_per_second": 45.38,
|
15 |
+
"train_steps_per_second": 0.71
|
16 |
+
}
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"finetuning_task": "stsb",
|
13 |
+
"gap_size": 0,
|
14 |
+
"hidden_act": "gelu_new",
|
15 |
+
"hidden_dropout_prob": 0,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"id2label": {
|
18 |
+
"0": "LABEL_0"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"inner_group_num": 1,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-12,
|
27 |
+
"max_position_embeddings": 512,
|
28 |
+
"model_type": "albert",
|
29 |
+
"net_structure_type": 0,
|
30 |
+
"num_attention_heads": 12,
|
31 |
+
"num_hidden_groups": 1,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"num_memory_blocks": 0,
|
34 |
+
"pad_token_id": 0,
|
35 |
+
"position_embedding_type": "absolute",
|
36 |
+
"problem_type": "regression",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.9.0",
|
39 |
+
"type_vocab_size": 2,
|
40 |
+
"vocab_size": 30000
|
41 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_combined_score": 0.9070512696741792,
|
4 |
+
"eval_loss": 0.3978178799152374,
|
5 |
+
"eval_pearson": 0.9090280614587851,
|
6 |
+
"eval_runtime": 13.6802,
|
7 |
+
"eval_samples": 1500,
|
8 |
+
"eval_samples_per_second": 109.648,
|
9 |
+
"eval_spearmanr": 0.9050744778895732,
|
10 |
+
"eval_steps_per_second": 13.743
|
11 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6fc22d84559cadd2b5bce10cc8caac94c27da6d99c529d76bf426f3179425fd
|
3 |
+
size 46752465
|
runs/Jul26_10-48-21_87e5b6406975/1627296525.161824/events.out.tfevents.1627296525.87e5b6406975.485.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:778b654c978867b2cb0d7a9c4a094ebe63ccaa4843767412b60b2d1d53b98784
|
3 |
+
size 4167
|
runs/Jul26_10-48-21_87e5b6406975/events.out.tfevents.1627296525.87e5b6406975.485.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cde7b06c86b4876bfd8bdc13d98596a6c5fbb3e0ec86ebbc8c57a4e997825d38
|
3 |
+
size 3548
|
runs/Jul26_10-48-21_87e5b6406975/events.out.tfevents.1627297045.87e5b6406975.485.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b52aabf9d844fae40928fec3984949d7fe04cc3ab4b022e11c0a6efedb66424
|
3 |
+
size 473
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"train_loss": 0.43474773830837676,
|
4 |
+
"train_runtime": 506.7423,
|
5 |
+
"train_samples": 5749,
|
6 |
+
"train_samples_per_second": 45.38,
|
7 |
+
"train_steps_per_second": 0.71
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 360,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 4.0,
|
12 |
+
"step": 360,
|
13 |
+
"total_flos": 137376605764608.0,
|
14 |
+
"train_loss": 0.43474773830837676,
|
15 |
+
"train_runtime": 506.7423,
|
16 |
+
"train_samples_per_second": 45.38,
|
17 |
+
"train_steps_per_second": 0.71
|
18 |
+
}
|
19 |
+
],
|
20 |
+
"max_steps": 360,
|
21 |
+
"num_train_epochs": 4,
|
22 |
+
"total_flos": 137376605764608.0,
|
23 |
+
"trial_name": null,
|
24 |
+
"trial_params": null
|
25 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c592deb26553180813296cece5490d0e30ccd681013f57a4a94259490592f22
|
3 |
+
size 2607
|