k011/startup-eligibility
Browse files- README.md +68 -0
- config.json +42 -0
- model.safetensors +3 -0
- runs/Jun16_07-30-17_236257c5c870/events.out.tfevents.1718523017.236257c5c870.405.0 +3 -0
- runs/Jun16_07-30-17_236257c5c870/events.out.tfevents.1718523577.236257c5c870.405.1 +3 -0
- special_tokens_map.json +15 -0
- spiece.model +3 -0
- tokenizer_config.json +58 -0
- trainer_state.json +56 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: albert/albert-base-v2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: startup-score
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# startup-score
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.7827
|
24 |
+
- Accuracy: 0.25
|
25 |
+
- F1: 0.3000
|
26 |
+
- Precision: 0.375
|
27 |
+
- Recall: 0.25
|
28 |
+
- Accuracy Label Eligible: 0.0
|
29 |
+
- Accuracy Label Not eligible: 0.3333
|
30 |
+
|
31 |
+
## Model description
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 2e-05
|
49 |
+
- train_batch_size: 16
|
50 |
+
- eval_batch_size: 16
|
51 |
+
- seed: 42
|
52 |
+
- gradient_accumulation_steps: 2
|
53 |
+
- total_train_batch_size: 32
|
54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
+
- lr_scheduler_type: linear
|
56 |
+
- lr_scheduler_warmup_steps: 500
|
57 |
+
- num_epochs: 3
|
58 |
+
|
59 |
+
### Training results
|
60 |
+
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.41.2
|
66 |
+
- Pytorch 2.3.0+cu121
|
67 |
+
- Datasets 2.20.0
|
68 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert/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 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "ELIGIBLE",
|
18 |
+
"1": "NOT ELIGIBLE"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"inner_group_num": 1,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"ELIGIBLE": 0,
|
25 |
+
"NOT ELIGIBLE": 1
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-12,
|
28 |
+
"max_position_embeddings": 512,
|
29 |
+
"model_type": "albert",
|
30 |
+
"net_structure_type": 0,
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_hidden_groups": 1,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"num_memory_blocks": 0,
|
35 |
+
"pad_token_id": 0,
|
36 |
+
"position_embedding_type": "absolute",
|
37 |
+
"problem_type": "single_label_classification",
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.41.2",
|
40 |
+
"type_vocab_size": 2,
|
41 |
+
"vocab_size": 30000
|
42 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35a26d4ab1066730f5384bbed08334fa8eabdefc70a4381de909b2bcdfbe35ee
|
3 |
+
size 46743912
|
runs/Jun16_07-30-17_236257c5c870/events.out.tfevents.1718523017.236257c5c870.405.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d1d045ce81fae84d00fdef909cdddb93540212ab3696aab0019fd8ed78c5c9b
|
3 |
+
size 5439
|
runs/Jun16_07-30-17_236257c5c870/events.out.tfevents.1718523577.236257c5c870.405.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:931f9540bd41870f9faaebcdc0916c11671d597a1349e30bf74dbfff4971e08c
|
3 |
+
size 687
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "[MASK]",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "[SEP]",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
|
3 |
+
size 760289
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<unk>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "[CLS]",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"eos_token": "[SEP]",
|
49 |
+
"keep_accents": false,
|
50 |
+
"mask_token": "[MASK]",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"remove_space": true,
|
54 |
+
"sep_token": "[SEP]",
|
55 |
+
"sp_model_kwargs": {},
|
56 |
+
"tokenizer_class": "AlbertTokenizer",
|
57 |
+
"unk_token": "<unk>"
|
58 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 9,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 3.0,
|
13 |
+
"step": 9,
|
14 |
+
"total_flos": 1963891858500.0,
|
15 |
+
"train_loss": 0.6781148910522461,
|
16 |
+
"train_runtime": 527.8082,
|
17 |
+
"train_samples_per_second": 0.483,
|
18 |
+
"train_steps_per_second": 0.017
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 3.0,
|
22 |
+
"eval_accuracy": 0.25,
|
23 |
+
"eval_accuracy_label_ELIGIBLE": 0.0,
|
24 |
+
"eval_accuracy_label_NOT ELIGIBLE": 0.3333333333333333,
|
25 |
+
"eval_f1": 0.30000000000000004,
|
26 |
+
"eval_loss": 0.7826551795005798,
|
27 |
+
"eval_precision": 0.375,
|
28 |
+
"eval_recall": 0.25,
|
29 |
+
"eval_runtime": 5.0134,
|
30 |
+
"eval_samples_per_second": 1.596,
|
31 |
+
"eval_steps_per_second": 0.199,
|
32 |
+
"step": 9
|
33 |
+
}
|
34 |
+
],
|
35 |
+
"logging_steps": 10,
|
36 |
+
"max_steps": 9,
|
37 |
+
"num_input_tokens_seen": 0,
|
38 |
+
"num_train_epochs": 3,
|
39 |
+
"save_steps": 1000,
|
40 |
+
"stateful_callbacks": {
|
41 |
+
"TrainerControl": {
|
42 |
+
"args": {
|
43 |
+
"should_epoch_stop": false,
|
44 |
+
"should_evaluate": false,
|
45 |
+
"should_log": false,
|
46 |
+
"should_save": false,
|
47 |
+
"should_training_stop": false
|
48 |
+
},
|
49 |
+
"attributes": {}
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"total_flos": 1963891858500.0,
|
53 |
+
"train_batch_size": 16,
|
54 |
+
"trial_name": null,
|
55 |
+
"trial_params": null
|
56 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ca13fdaf3a6472d8e75d8d7bf0cacf604df863ddd24a901cad946fbec0b8738
|
3 |
+
size 5048
|