francisco-perez-sorrosal
commited on
Commit
·
b0e7b7c
1
Parent(s):
f1be92c
End of training
Browse files- last-checkpoint/config.json +0 -35
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/pytorch_model.bin +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/scheduler.pt +0 -3
- last-checkpoint/special_tokens_map.json +0 -7
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +0 -17
- last-checkpoint/trainer_state.json +0 -88
- last-checkpoint/training_args.bin +0 -3
- last-checkpoint/vocab.txt +0 -0
- pytorch_model.bin +1 -1
last-checkpoint/config.json
DELETED
@@ -1,35 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
-
"activation": "gelu",
|
4 |
-
"architectures": [
|
5 |
-
"DistilBertForSequenceClassification"
|
6 |
-
],
|
7 |
-
"attention_dropout": 0.1,
|
8 |
-
"dim": 768,
|
9 |
-
"dropout": 0.1,
|
10 |
-
"hidden_dim": 3072,
|
11 |
-
"id2label": {
|
12 |
-
"0": "P",
|
13 |
-
"1": "NEU",
|
14 |
-
"2": "N"
|
15 |
-
},
|
16 |
-
"initializer_range": 0.02,
|
17 |
-
"label2id": {
|
18 |
-
"N": 2,
|
19 |
-
"NEU": 1,
|
20 |
-
"P": 0
|
21 |
-
},
|
22 |
-
"max_position_embeddings": 512,
|
23 |
-
"model_type": "distilbert",
|
24 |
-
"n_heads": 12,
|
25 |
-
"n_layers": 6,
|
26 |
-
"pad_token_id": 0,
|
27 |
-
"problem_type": "single_label_classification",
|
28 |
-
"qa_dropout": 0.1,
|
29 |
-
"seq_classif_dropout": 0.2,
|
30 |
-
"sinusoidal_pos_embds": false,
|
31 |
-
"tie_weights_": true,
|
32 |
-
"torch_dtype": "float32",
|
33 |
-
"transformers_version": "4.26.0",
|
34 |
-
"vocab_size": 30522
|
35 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:b5502ebe2c01891a59e636849cf3785199bff10785e38e3d11ec4786541a92c6
|
3 |
-
size 535704261
|
|
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:ef883db0b7fbb86966cdc7dbc53c9cb6b08ceef5b149ac358bb03630cb601139
|
3 |
-
size 267857197
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7bb41029a85b616a7e387ded9d40018428571ef301b994fb1bdfd0fb89b8aa19
|
3 |
-
size 13553
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:00146e06824988c619d6727106a07dfdd073664c96ecfc34b06f27eb7332be3d
|
3 |
-
size 627
|
|
|
|
|
|
|
|
last-checkpoint/special_tokens_map.json
DELETED
@@ -1,7 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": "[CLS]",
|
3 |
-
"mask_token": "[MASK]",
|
4 |
-
"pad_token": "[PAD]",
|
5 |
-
"sep_token": "[SEP]",
|
6 |
-
"unk_token": "[UNK]"
|
7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer_config.json
DELETED
@@ -1,17 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": "[CLS]",
|
3 |
-
"do_lower_case": true,
|
4 |
-
"mask_token": "[MASK]",
|
5 |
-
"max_length": 72,
|
6 |
-
"model_max_length": 512,
|
7 |
-
"name_or_path": "distilbert-base-uncased",
|
8 |
-
"pad_token": "[PAD]",
|
9 |
-
"padding": "max_length",
|
10 |
-
"sep_token": "[SEP]",
|
11 |
-
"special_tokens_map_file": null,
|
12 |
-
"strip_accents": null,
|
13 |
-
"tokenize_chinese_chars": true,
|
14 |
-
"tokenizer_class": "DistilBertTokenizer",
|
15 |
-
"truncation": true,
|
16 |
-
"unk_token": "[UNK]"
|
17 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
@@ -1,88 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 0.561526731484265,
|
3 |
-
"best_model_checkpoint": "/Users/fperez/dev/data/spanishclassfier_exp/distilbert-base-uncased-finetuned-with-spanish-tweets-clf-cleaned-ds/ep_4-lr_5e-5-msl_72-bs_8/checkpoint-1629",
|
4 |
-
"epoch": 4.0,
|
5 |
-
"global_step": 2172,
|
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": 3.7500000000000003e-05,
|
13 |
-
"loss": 1.0683,
|
14 |
-
"step": 543
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 1.0,
|
18 |
-
"eval_accuracy": 0.4996544574982723,
|
19 |
-
"eval_f1": 0.4041403679871358,
|
20 |
-
"eval_loss": 1.001932144165039,
|
21 |
-
"eval_precision": 0.4723824092574092,
|
22 |
-
"eval_recall": 0.4488085460318594,
|
23 |
-
"eval_runtime": 71.6143,
|
24 |
-
"eval_samples_per_second": 20.205,
|
25 |
-
"eval_steps_per_second": 0.642,
|
26 |
-
"step": 543
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 2.0,
|
30 |
-
"learning_rate": 2.5e-05,
|
31 |
-
"loss": 0.9372,
|
32 |
-
"step": 1086
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 2.0,
|
36 |
-
"eval_accuracy": 0.5425017277125086,
|
37 |
-
"eval_f1": 0.514327101402141,
|
38 |
-
"eval_loss": 0.9395344257354736,
|
39 |
-
"eval_precision": 0.5479505155677658,
|
40 |
-
"eval_recall": 0.5122633831192213,
|
41 |
-
"eval_runtime": 76.1257,
|
42 |
-
"eval_samples_per_second": 19.008,
|
43 |
-
"eval_steps_per_second": 0.604,
|
44 |
-
"step": 1086
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 3.0,
|
48 |
-
"learning_rate": 1.25e-05,
|
49 |
-
"loss": 0.7283,
|
50 |
-
"step": 1629
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 3.0,
|
54 |
-
"eval_accuracy": 0.5632342778161714,
|
55 |
-
"eval_f1": 0.561526731484265,
|
56 |
-
"eval_loss": 0.967441737651825,
|
57 |
-
"eval_precision": 0.5658121229492835,
|
58 |
-
"eval_recall": 0.5586787297506143,
|
59 |
-
"eval_runtime": 65.1455,
|
60 |
-
"eval_samples_per_second": 22.212,
|
61 |
-
"eval_steps_per_second": 0.706,
|
62 |
-
"step": 1629
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 4.0,
|
66 |
-
"learning_rate": 0.0,
|
67 |
-
"loss": 0.5127,
|
68 |
-
"step": 2172
|
69 |
-
},
|
70 |
-
{
|
71 |
-
"epoch": 4.0,
|
72 |
-
"eval_accuracy": 0.5556323427781618,
|
73 |
-
"eval_f1": 0.5577964748279268,
|
74 |
-
"eval_loss": 1.122901201248169,
|
75 |
-
"eval_precision": 0.5682169161320979,
|
76 |
-
"eval_recall": 0.5539741666889855,
|
77 |
-
"eval_runtime": 45.2266,
|
78 |
-
"eval_samples_per_second": 31.994,
|
79 |
-
"eval_steps_per_second": 1.017,
|
80 |
-
"step": 2172
|
81 |
-
}
|
82 |
-
],
|
83 |
-
"max_steps": 2172,
|
84 |
-
"num_train_epochs": 4,
|
85 |
-
"total_flos": 323391804099840.0,
|
86 |
-
"trial_name": null,
|
87 |
-
"trial_params": null
|
88 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:9ad2ddb2c068d7006d3a5d324b65430898e3027d46d3633fb90be19fb8699704
|
3 |
-
size 3835
|
|
|
|
|
|
|
|
last-checkpoint/vocab.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267857197
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6c1879d9fbed0cdd591c460cea11305fe72986c79e18c3a715fb48b4d016b5b
|
3 |
size 267857197
|