francisco-perez-sorrosal commited on
Commit
b4950af
1 Parent(s): 1766ad1

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-multilingual-cased",
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
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "qa_dropout": 0.1,
30
+ "seq_classif_dropout": 0.2,
31
+ "sinusoidal_pos_embds": false,
32
+ "tie_weights_": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.26.0",
35
+ "vocab_size": 119547
36
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-multilingual-cased",
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
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "qa_dropout": 0.1,
30
+ "seq_classif_dropout": 0.2,
31
+ "sinusoidal_pos_embds": false,
32
+ "tie_weights_": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.26.0",
35
+ "vocab_size": 119547
36
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad68f7020fff1f0e243cd60c4876b9b73a07dc14b05ed632c69825ddaa58a970
3
+ size 1082673861
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bdd6b78f974013bce1aec4f94a2b191b8dafb462c6b9faddae16a4f17560312
3
+ size 541341997
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c217c8da9b1f3f90a790bb2b05f111d916ff143daa3cf19ad27dd02007dcd0c
3
+ size 13553
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2c4f9cae00d2f2dce1381a30f6b5f4854a75960078ce7c852274fe3c646a95
3
+ size 627
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
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 ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
5
+ "max_length": 72,
6
+ "model_max_length": 512,
7
+ "name_or_path": "distilbert-base-multilingual-cased",
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 ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4949397774870696,
3
+ "best_model_checkpoint": "/Users/fperez/dev/data/spanishclassfier_exp/distilbert-base-multilingual-cased-finetuned-with-spanish-tweets-clf-cleaned-ds/ep_4-lr_5e-5-msl_72-bs_8/checkpoint-543",
4
+ "epoch": 1.0,
5
+ "global_step": 543,
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": 1.018,
14
+ "step": 543
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.5535590877677954,
19
+ "eval_f1": 0.4949397774870696,
20
+ "eval_loss": 0.942139744758606,
21
+ "eval_precision": 0.5346677326820676,
22
+ "eval_recall": 0.5146316846159721,
23
+ "eval_runtime": 80.7708,
24
+ "eval_samples_per_second": 17.915,
25
+ "eval_steps_per_second": 0.57,
26
+ "step": 543
27
+ }
28
+ ],
29
+ "max_steps": 2172,
30
+ "num_train_epochs": 4,
31
+ "total_flos": 80847951024960.0,
32
+ "trial_name": null,
33
+ "trial_params": null
34
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547db2c34b063e23ee11f17e4bff5def40cf9fa9cf46e3e436df969a7238cc1c
3
+ size 3835
last-checkpoint/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bdd6b78f974013bce1aec4f94a2b191b8dafb462c6b9faddae16a4f17560312
3
+ size 541341997
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
5
+ "max_length": 72,
6
+ "model_max_length": 512,
7
+ "name_or_path": "distilbert-base-multilingual-cased",
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547db2c34b063e23ee11f17e4bff5def40cf9fa9cf46e3e436df969a7238cc1c
3
+ size 3835
vocab.txt ADDED
The diff for this file is too large to render. See raw diff