avacaondata
commited on
Commit
•
fd5a13a
1
Parent(s):
724ca57
añadido modelo
Browse files- config.json +33 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +70 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/mnt/d/models_iberlef22/exist22/task1/models_es/best_ckpt_BSC-TeMU",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
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": 0.0,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"non-sexist": 0,
|
16 |
+
"sexist": 1
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"layer_norm_eps": 1e-05,
|
21 |
+
"max_position_embeddings": 514,
|
22 |
+
"model_type": "roberta",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 1,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"problem_type": "single_label_classification",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.16.2",
|
30 |
+
"type_vocab_size": 1,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 50262
|
33 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fc01a9de9b446ec5027b5bd05a01bb225b1fdcff7af0b125eb6cdce78f01ca1
|
3 |
+
size 997275421
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2215bea62f9eaadfdf1d71e80ab436a7f96e30bccf60c42cbb729812b5e522e1
|
3 |
+
size 498664877
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecdbdc2a33f0a08cf047e4ff85386859a003a820f081341260e37274c0a9d51b
|
3 |
+
size 14503
|
scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:981227375b8c6d2439b9fd2664e9cd784500649faa2e607c97ed38e07fc17be3
|
3 |
+
size 559
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3153fafd1e088f95801c8cf8796319c35d2c32bce11b7e5d5b7c2d59640953b7
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "trim_offsets": true, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "/mnt/d/models_iberlef22/exist22/task1/models_es/best_ckpt_BSC-TeMU", "do_lower_case": false, "max_length": 512, "tokenizer_class": "RobertaTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8825914161641272,
|
3 |
+
"best_model_checkpoint": "/mnt/d/models_iberlef22/exist22/task1/models_es/retrained_BSC-TeMU/checkpoint-322",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 483,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 5.2402087303147016e-05,
|
13 |
+
"loss": 0.3659,
|
14 |
+
"step": 161
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_f1-score": 0.8762599995046685,
|
19 |
+
"eval_loss": 0.32265210151672363,
|
20 |
+
"eval_precision": 0.8820436657141424,
|
21 |
+
"eval_recall": 0.874809413732048,
|
22 |
+
"eval_runtime": 0.7263,
|
23 |
+
"eval_samples_per_second": 786.163,
|
24 |
+
"eval_steps_per_second": 12.391,
|
25 |
+
"eval_support": 571,
|
26 |
+
"step": 161
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.0,
|
30 |
+
"learning_rate": 2.6201043651573508e-05,
|
31 |
+
"loss": 0.1328,
|
32 |
+
"step": 322
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_f1-score": 0.8825914161641272,
|
37 |
+
"eval_loss": 0.3923543691635132,
|
38 |
+
"eval_precision": 0.8826217642007116,
|
39 |
+
"eval_recall": 0.8834780149518001,
|
40 |
+
"eval_runtime": 0.7091,
|
41 |
+
"eval_samples_per_second": 805.279,
|
42 |
+
"eval_steps_per_second": 12.693,
|
43 |
+
"eval_support": 571,
|
44 |
+
"step": 322
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"learning_rate": 1.627394015625684e-07,
|
49 |
+
"loss": 0.026,
|
50 |
+
"step": 483
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 3.0,
|
54 |
+
"eval_f1-score": 0.8790866823182801,
|
55 |
+
"eval_loss": 0.5471494793891907,
|
56 |
+
"eval_precision": 0.8791191264875475,
|
57 |
+
"eval_recall": 0.8799675388550069,
|
58 |
+
"eval_runtime": 0.7205,
|
59 |
+
"eval_samples_per_second": 792.548,
|
60 |
+
"eval_steps_per_second": 12.492,
|
61 |
+
"eval_support": 571,
|
62 |
+
"step": 483
|
63 |
+
}
|
64 |
+
],
|
65 |
+
"max_steps": 483,
|
66 |
+
"num_train_epochs": 3,
|
67 |
+
"total_flos": 1012319785497600.0,
|
68 |
+
"trial_name": null,
|
69 |
+
"trial_params": null
|
70 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25c73720a9a4e208ae9e614a44c2e1a133427689348104387fa2f94334e52584
|
3 |
+
size 3055
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|