Rodrigo1771
commited on
Commit
β’
0f6759c
1
Parent(s):
10a928e
End of training
Browse files- README.md +63 -0
- all_results.json +19 -0
- config.json +51 -0
- eval_results.json +11 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- predict_results.json +10 -0
- predictions.txt +0 -0
- special_tokens_map.json +51 -0
- tb/events.out.tfevents.1715608825.c331905616cf.2224.0 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- train.log +357 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
|
4 |
+
tags:
|
5 |
+
- token-classification
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- Rodrigo1771/multi-train-drugtemist-dev-ner
|
9 |
+
model-index:
|
10 |
+
- name: output
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# output
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the Rodrigo1771/multi-train-drugtemist-dev-ner dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- eval_loss: 2.4031
|
22 |
+
- eval_precision: 0.0004
|
23 |
+
- eval_recall: 0.0386
|
24 |
+
- eval_f1: 0.0007
|
25 |
+
- eval_accuracy: 0.0028
|
26 |
+
- eval_runtime: 16.7962
|
27 |
+
- eval_samples_per_second: 405.27
|
28 |
+
- eval_steps_per_second: 50.666
|
29 |
+
- step: 0
|
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: 5e-05
|
49 |
+
- train_batch_size: 4
|
50 |
+
- eval_batch_size: 8
|
51 |
+
- seed: 42
|
52 |
+
- gradient_accumulation_steps: 4
|
53 |
+
- total_train_batch_size: 16
|
54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
+
- lr_scheduler_type: linear
|
56 |
+
- num_epochs: 10.0
|
57 |
+
|
58 |
+
### Framework versions
|
59 |
+
|
60 |
+
- Transformers 4.40.2
|
61 |
+
- Pytorch 2.2.1+cu121
|
62 |
+
- Datasets 2.19.1
|
63 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_accuracy": 0.002835545241707918,
|
3 |
+
"eval_f1": 0.0006942779922141681,
|
4 |
+
"eval_loss": 2.4030845165252686,
|
5 |
+
"eval_precision": 0.00035028898841544273,
|
6 |
+
"eval_recall": 0.03860294117647059,
|
7 |
+
"eval_runtime": 16.7962,
|
8 |
+
"eval_samples": 6807,
|
9 |
+
"eval_samples_per_second": 405.27,
|
10 |
+
"eval_steps_per_second": 50.666,
|
11 |
+
"predict_accuracy": 0.002835545241707918,
|
12 |
+
"predict_f1": 0.0006942779922141681,
|
13 |
+
"predict_loss": 2.4030845165252686,
|
14 |
+
"predict_precision": 0.00035028898841544273,
|
15 |
+
"predict_recall": 0.03860294117647059,
|
16 |
+
"predict_runtime": 16.0715,
|
17 |
+
"predict_samples_per_second": 423.545,
|
18 |
+
"predict_steps_per_second": 52.951
|
19 |
+
}
|
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"finetuning_task": "ner",
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "O",
|
17 |
+
"1": "B-ENFERMEDAD",
|
18 |
+
"2": "I-ENFERMEDAD",
|
19 |
+
"3": "B-PROCEDIMIENTO",
|
20 |
+
"4": "I-PROCEDIMIENTO",
|
21 |
+
"5": "B-SINTOMA",
|
22 |
+
"6": "I-SINTOMA",
|
23 |
+
"7": "B-FARMACO",
|
24 |
+
"8": "I-FARMACO"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 3072,
|
28 |
+
"label2id": {
|
29 |
+
"B-ENFERMEDAD": 1,
|
30 |
+
"B-FARMACO": 7,
|
31 |
+
"B-PROCEDIMIENTO": 3,
|
32 |
+
"B-SINTOMA": 5,
|
33 |
+
"I-ENFERMEDAD": 2,
|
34 |
+
"I-FARMACO": 8,
|
35 |
+
"I-PROCEDIMIENTO": 4,
|
36 |
+
"I-SINTOMA": 6,
|
37 |
+
"O": 0
|
38 |
+
},
|
39 |
+
"layer_norm_eps": 1e-05,
|
40 |
+
"max_position_embeddings": 514,
|
41 |
+
"model_type": "roberta",
|
42 |
+
"num_attention_heads": 12,
|
43 |
+
"num_hidden_layers": 12,
|
44 |
+
"pad_token_id": 1,
|
45 |
+
"position_embedding_type": "absolute",
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.40.2",
|
48 |
+
"type_vocab_size": 1,
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 50262
|
51 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_accuracy": 0.002835545241707918,
|
3 |
+
"eval_f1": 0.0006942779922141681,
|
4 |
+
"eval_loss": 2.4030845165252686,
|
5 |
+
"eval_precision": 0.00035028898841544273,
|
6 |
+
"eval_recall": 0.03860294117647059,
|
7 |
+
"eval_runtime": 16.7962,
|
8 |
+
"eval_samples": 6807,
|
9 |
+
"eval_samples_per_second": 405.27,
|
10 |
+
"eval_steps_per_second": 50.666
|
11 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cb8f27d656928c021399304ae37e82d147c80df5386c804b66e664424a60fee
|
3 |
+
size 496262556
|
predict_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"predict_accuracy": 0.002835545241707918,
|
3 |
+
"predict_f1": 0.0006942779922141681,
|
4 |
+
"predict_loss": 2.4030845165252686,
|
5 |
+
"predict_precision": 0.00035028898841544273,
|
6 |
+
"predict_recall": 0.03860294117647059,
|
7 |
+
"predict_runtime": 16.0715,
|
8 |
+
"predict_samples_per_second": 423.545,
|
9 |
+
"predict_steps_per_second": 52.951
|
10 |
+
}
|
predictions.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tb/events.out.tfevents.1715608825.c331905616cf.2224.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6b43bba93fcdae059a879a573e39c04184713f463eaf8c074aa07d771faa37e
|
3 |
+
size 486
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50261": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"max_len": 512,
|
52 |
+
"model_max_length": 512,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": "<unk>"
|
58 |
+
}
|
train.log
ADDED
@@ -0,0 +1,357 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
0 |
0%| | 0/851 [00:00<?, ?it/s]
|
1 |
1%| | 6/851 [00:00<00:14, 56.79it/s]
|
2 |
2%|β | 14/851 [00:00<00:12, 66.67it/s]
|
3 |
2%|β | 21/851 [00:00<00:12, 67.60it/s]
|
4 |
3%|β | 29/851 [00:00<00:11, 71.18it/s]
|
5 |
4%|β | 37/851 [00:00<00:11, 72.27it/s]
|
6 |
5%|β | 45/851 [00:00<00:10, 73.94it/s]
|
7 |
6%|β | 53/851 [00:00<00:10, 75.21it/s]
|
8 |
7%|β | 62/851 [00:00<00:10, 76.83it/s]
|
9 |
8%|β | 70/851 [00:00<00:10, 72.77it/s]
|
10 |
9%|β | 78/851 [00:01<00:10, 73.82it/s]
|
11 |
10%|β | 86/851 [00:01<00:10, 72.92it/s]
|
12 |
11%|β | 94/851 [00:01<00:10, 71.23it/s]
|
13 |
12%|ββ | 102/851 [00:01<00:10, 72.43it/s]
|
14 |
13%|ββ | 110/851 [00:01<00:10, 71.56it/s]
|
15 |
14%|ββ | 118/851 [00:01<00:10, 72.68it/s]
|
16 |
15%|ββ | 126/851 [00:01<00:10, 69.25it/s]
|
17 |
16%|ββ | 134/851 [00:01<00:10, 69.92it/s]
|
18 |
17%|ββ | 142/851 [00:01<00:10, 70.22it/s]
|
19 |
18%|ββ | 150/851 [00:02<00:10, 68.89it/s]
|
20 |
19%|ββ | 158/851 [00:02<00:09, 71.66it/s]
|
21 |
20%|ββ | 166/851 [00:02<00:09, 72.84it/s]
|
22 |
20%|ββ | 174/851 [00:02<00:09, 73.78it/s]
|
23 |
21%|βββ | 182/851 [00:02<00:08, 74.73it/s]
|
24 |
22%|βββ | 191/851 [00:02<00:08, 75.91it/s]
|
25 |
24%|βββ | 200/851 [00:02<00:08, 77.69it/s]
|
26 |
24%|βββ | 208/851 [00:02<00:08, 74.46it/s]
|
27 |
25%|βββ | 216/851 [00:02<00:08, 73.02it/s]
|
28 |
26%|βββ | 224/851 [00:03<00:08, 73.31it/s]
|
29 |
27%|βββ | 233/851 [00:03<00:08, 75.80it/s]
|
30 |
28%|βββ | 241/851 [00:03<00:08, 70.34it/s]
|
31 |
29%|βββ | 249/851 [00:03<00:08, 70.90it/s]
|
32 |
30%|βββ | 258/851 [00:03<00:07, 74.54it/s]
|
33 |
31%|ββββ | 267/851 [00:03<00:07, 74.56it/s]
|
34 |
32%|ββββ | 275/851 [00:03<00:07, 75.23it/s]
|
35 |
33%|ββββ | 284/851 [00:03<00:07, 77.16it/s]
|
36 |
34%|ββββ | 292/851 [00:03<00:07, 75.36it/s]
|
37 |
35%|ββββ | 300/851 [00:04<00:07, 76.48it/s]
|
38 |
36%|ββββ | 309/851 [00:04<00:06, 78.03it/s]
|
39 |
37%|ββββ | 317/851 [00:04<00:07, 73.84it/s]
|
40 |
38%|ββββ | 325/851 [00:04<00:07, 74.16it/s]
|
41 |
39%|ββββ | 333/851 [00:04<00:07, 73.48it/s]
|
42 |
40%|ββββ | 341/851 [00:04<00:06, 75.03it/s]
|
43 |
41%|ββββ | 349/851 [00:04<00:06, 75.15it/s]
|
44 |
42%|βββββ | 357/851 [00:04<00:06, 71.25it/s]
|
45 |
43%|βββββ | 365/851 [00:04<00:06, 73.08it/s]
|
46 |
44%|βββββ | 373/851 [00:05<00:06, 71.71it/s]
|
47 |
45%|βββββ | 381/851 [00:05<00:06, 69.65it/s]
|
48 |
46%|βββββ | 389/851 [00:05<00:06, 72.30it/s]
|
49 |
47%|βββββ | 397/851 [00:05<00:06, 72.22it/s]
|
50 |
48%|βββββ | 405/851 [00:05<00:06, 67.45it/s]
|
51 |
49%|βββββ | 413/851 [00:05<00:06, 68.89it/s]
|
52 |
49%|βββββ | 421/851 [00:05<00:05, 71.75it/s]
|
53 |
50%|βββββ | 429/851 [00:05<00:06, 70.29it/s]
|
54 |
51%|ββββββ | 437/851 [00:06<00:05, 72.84it/s]
|
55 |
52%|ββββββ | 445/851 [00:06<00:05, 73.81it/s]
|
56 |
53%|ββββββ | 453/851 [00:06<00:05, 74.50it/s]
|
57 |
54%|ββββββ | 461/851 [00:06<00:05, 72.92it/s]
|
58 |
55%|ββββββ | 469/851 [00:06<00:05, 70.51it/s]
|
59 |
56%|ββββββ | 477/851 [00:06<00:05, 65.80it/s]
|
60 |
57%|ββββββ | 484/851 [00:06<00:05, 65.68it/s]
|
61 |
58%|ββββββ | 492/851 [00:06<00:05, 69.27it/s]
|
62 |
59%|ββββββ | 501/851 [00:06<00:04, 73.42it/s]
|
63 |
60%|ββββββ | 509/851 [00:07<00:04, 72.53it/s]
|
64 |
61%|ββββββ | 517/851 [00:07<00:04, 74.04it/s]
|
65 |
62%|βββββββ | 525/851 [00:07<00:04, 69.50it/s]
|
66 |
63%|βββββββ | 533/851 [00:07<00:04, 70.76it/s]
|
67 |
64%|βββββββ | 541/851 [00:07<00:04, 72.75it/s]
|
68 |
65%|βββββββ | 549/851 [00:07<00:04, 70.77it/s]
|
69 |
65%|βββββββ | 557/851 [00:07<00:04, 72.93it/s]
|
70 |
67%|βββββββ | 566/851 [00:07<00:03, 75.96it/s]
|
71 |
67%|βββββββ | 574/851 [00:07<00:03, 75.68it/s]
|
72 |
68%|βββββββ | 582/851 [00:08<00:03, 73.54it/s]
|
73 |
69%|βββββββ | 590/851 [00:08<00:03, 70.20it/s]
|
74 |
70%|βββββββ | 598/851 [00:08<00:03, 71.00it/s]
|
75 |
71%|βββββββ | 606/851 [00:08<00:03, 69.47it/s]
|
76 |
72%|ββββββββ | 613/851 [00:08<00:03, 67.88it/s]
|
77 |
73%|ββββββββ | 620/851 [00:08<00:03, 68.06it/s]
|
78 |
74%|ββββββββ | 627/851 [00:08<00:03, 67.97it/s]
|
79 |
75%|ββββββββ | 635/851 [00:08<00:03, 68.41it/s]
|
80 |
75%|ββββββββ | 642/851 [00:08<00:03, 63.33it/s]
|
81 |
76%|ββββββββ | 650/851 [00:09<00:02, 67.25it/s]
|
82 |
77%|ββββββββ | 658/851 [00:09<00:02, 69.51it/s]
|
83 |
78%|ββββββββ | 666/851 [00:09<00:02, 70.79it/s]
|
84 |
79%|ββββββββ | 674/851 [00:09<00:02, 70.05it/s]
|
85 |
80%|ββββββββ | 682/851 [00:09<00:02, 71.60it/s]
|
86 |
81%|ββββββββ | 691/851 [00:09<00:02, 74.53it/s]
|
87 |
82%|βββββββββ | 699/851 [00:09<00:02, 74.50it/s]
|
88 |
83%|βββββββββ | 708/851 [00:09<00:01, 76.84it/s]
|
89 |
84%|βββββββββ | 716/851 [00:09<00:01, 74.99it/s]
|
90 |
85%|βββββββββ | 724/851 [00:10<00:01, 75.33it/s]
|
91 |
86%|βββββββββ | 732/851 [00:10<00:01, 76.41it/s]
|
92 |
87%|βββββββββ | 740/851 [00:10<00:01, 76.60it/s]
|
93 |
88%|βββββββββ | 748/851 [00:10<00:01, 76.14it/s]
|
94 |
89%|βββββββββ | 756/851 [00:10<00:01, 75.65it/s]
|
95 |
90%|βββββββββ | 764/851 [00:10<00:01, 76.38it/s]
|
96 |
91%|βββββββββ | 772/851 [00:10<00:01, 71.78it/s]
|
97 |
92%|ββββββββββ| 780/851 [00:10<00:01, 69.90it/s]
|
98 |
93%|ββββββββββ| 788/851 [00:10<00:00, 70.05it/s]
|
99 |
94%|ββββββββββ| 796/851 [00:11<00:00, 70.92it/s]
|
100 |
94%|ββββββββββ| 804/851 [00:11<00:00, 73.14it/s]
|
101 |
95%|ββββββββββ| 812/851 [00:11<00:00, 71.35it/s]
|
102 |
96%|ββββββββββ| 820/851 [00:11<00:00, 72.32it/s]
|
103 |
97%|ββββββββββ| 828/851 [00:11<00:00, 73.57it/s]
|
104 |
98%|ββββββββββ| 836/851 [00:11<00:00, 73.25it/s]
|
105 |
99%|ββββββββββ| 844/851 [00:11<00:00, 70.06it/s]/usr/local/lib/python3.10/dist-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
106 |
0%| | 0/851 [00:00<?, ?it/s]
|
107 |
1%| | 10/851 [00:00<00:09, 91.44it/s]
|
108 |
2%|β | 20/851 [00:00<00:10, 80.05it/s]
|
109 |
3%|β | 29/851 [00:00<00:10, 76.91it/s]
|
110 |
4%|β | 37/851 [00:00<00:10, 76.11it/s]
|
111 |
5%|β | 45/851 [00:00<00:10, 76.81it/s]
|
112 |
6%|β | 53/851 [00:00<00:10, 77.42it/s]
|
113 |
7%|β | 62/851 [00:00<00:10, 78.22it/s]
|
114 |
8%|β | 70/851 [00:00<00:10, 73.17it/s]
|
115 |
9%|β | 78/851 [00:01<00:10, 74.14it/s]
|
116 |
10%|β | 86/851 [00:01<00:10, 74.47it/s]
|
117 |
11%|β | 94/851 [00:01<00:10, 71.54it/s]
|
118 |
12%|ββ | 102/851 [00:01<00:10, 72.66it/s]
|
119 |
13%|ββ | 110/851 [00:01<00:10, 71.47it/s]
|
120 |
14%|ββ | 118/851 [00:01<00:10, 72.13it/s]
|
121 |
15%|ββ | 126/851 [00:01<00:10, 69.31it/s]
|
122 |
16%|ββ | 134/851 [00:01<00:10, 69.99it/s]
|
123 |
17%|ββ | 142/851 [00:01<00:10, 70.34it/s]
|
124 |
18%|ββ | 150/851 [00:02<00:10, 69.10it/s]
|
125 |
19%|ββ | 159/851 [00:02<00:09, 73.31it/s]
|
126 |
20%|ββ | 167/851 [00:02<00:09, 73.76it/s]
|
127 |
21%|ββ | 175/851 [00:02<00:09, 74.62it/s]
|
128 |
22%|βββ | 183/851 [00:02<00:08, 75.28it/s]
|
129 |
22%|βββ | 191/851 [00:02<00:08, 75.29it/s]
|
130 |
24%|βββ | 200/851 [00:02<00:08, 77.19it/s]
|
131 |
24%|βββ | 208/851 [00:02<00:08, 74.09it/s]
|
132 |
25%|βββ | 216/851 [00:02<00:08, 72.43it/s]
|
133 |
26%|βββ | 224/851 [00:03<00:08, 72.43it/s]
|
134 |
27%|βββ | 232/851 [00:03<00:08, 74.47it/s]
|
135 |
28%|βββ | 240/851 [00:03<00:08, 72.23it/s]
|
136 |
29%|βββ | 248/851 [00:03<00:08, 70.30it/s]
|
137 |
30%|βββ | 257/851 [00:03<00:08, 74.22it/s]
|
138 |
31%|ββββ | 266/851 [00:03<00:07, 76.38it/s]
|
139 |
32%|ββββ | 274/851 [00:03<00:07, 73.69it/s]
|
140 |
33%|ββββ | 283/851 [00:03<00:07, 75.70it/s]
|
141 |
34%|ββββ | 291/851 [00:03<00:07, 74.53it/s]
|
142 |
35%|ββββ | 299/851 [00:04<00:07, 75.95it/s]
|
143 |
36%|ββββ | 308/851 [00:04<00:06, 77.72it/s]
|
144 |
37%|ββββ | 316/851 [00:04<00:07, 73.39it/s]
|
145 |
38%|ββββ | 324/851 [00:04<00:07, 74.25it/s]
|
146 |
39%|ββββ | 332/851 [00:04<00:07, 73.40it/s]
|
147 |
40%|ββββ | 340/851 [00:04<00:06, 74.69it/s]
|
148 |
41%|ββββ | 348/851 [00:04<00:06, 74.45it/s]
|
149 |
42%|βββββ | 356/851 [00:04<00:06, 71.61it/s]
|
150 |
43%|βββββ | 364/851 [00:04<00:06, 71.59it/s]
|
151 |
44%|βββββ | 372/851 [00:05<00:06, 71.39it/s]
|
152 |
45%|βββββ | 380/851 [00:05<00:06, 68.82it/s]
|
153 |
46%|βββββ | 388/851 [00:05<00:06, 71.34it/s]
|
154 |
47%|βββββ | 396/851 [00:05<00:06, 71.74it/s]
|
155 |
47%|βββββ | 404/851 [00:05<00:06, 67.34it/s]
|
156 |
48%|βββββ | 411/851 [00:05<00:06, 67.07it/s]
|
157 |
49%|βββββ | 419/851 [00:05<00:06, 70.05it/s]
|
158 |
50%|βββββ | 427/851 [00:05<00:06, 68.22it/s]
|
159 |
51%|βββββ | 435/851 [00:05<00:05, 71.05it/s]
|
160 |
52%|ββββββ | 443/851 [00:06<00:05, 73.07it/s]
|
161 |
53%|ββββββ | 451/851 [00:06<00:05, 73.76it/s]
|
162 |
54%|ββββββ | 459/851 [00:06<00:05, 74.30it/s]
|
163 |
55%|ββββββ | 467/851 [00:06<00:05, 69.53it/s]
|
164 |
56%|ββββββ | 475/851 [00:06<00:05, 64.31it/s]
|
165 |
57%|ββββββ | 482/851 [00:06<00:05, 65.00it/s]
|
166 |
57%|ββββββ | 489/851 [00:06<00:05, 66.01it/s]
|
167 |
59%|ββββββ | 498/851 [00:06<00:04, 70.87it/s]
|
168 |
59%|ββββββ | 506/851 [00:06<00:04, 72.82it/s]
|
169 |
60%|ββββββ | 514/851 [00:07<00:04, 72.54it/s]
|
170 |
61%|βββββββ | 522/851 [00:07<00:04, 69.41it/s]
|
171 |
62%|βββββββ | 530/851 [00:07<00:04, 69.19it/s]
|
172 |
63%|βββββββ | 538/851 [00:07<00:04, 71.41it/s]
|
173 |
64%|βββββββ | 546/851 [00:07<00:04, 72.09it/s]
|
174 |
65%|βββββββ | 554/851 [00:07<00:04, 70.07it/s]
|
175 |
66%|βββββββ | 562/851 [00:07<00:04, 72.16it/s]
|
176 |
67%|βββββββ | 570/851 [00:07<00:03, 73.41it/s]
|
177 |
68%|βββββββ | 578/851 [00:07<00:03, 71.89it/s]
|
178 |
69%|βββββββ | 586/851 [00:08<00:03, 70.00it/s]
|
179 |
70%|βββββββ | 594/851 [00:08<00:03, 70.61it/s]
|
180 |
71%|βββββββ | 602/851 [00:08<00:03, 71.04it/s]
|
181 |
72%|ββββββββ | 610/851 [00:08<00:03, 70.41it/s]
|
182 |
73%|ββββββββ | 618/851 [00:08<00:03, 66.31it/s]
|
183 |
74%|ββββββββ | 626/851 [00:08<00:03, 66.58it/s]
|
184 |
74%|ββββββββ | 633/851 [00:08<00:03, 67.17it/s]
|
185 |
75%|ββββββββ | 640/851 [00:08<00:03, 67.05it/s]
|
186 |
76%|ββββββββ | 647/851 [00:09<00:03, 65.37it/s]
|
187 |
77%|ββββββββ | 655/851 [00:09<00:02, 68.38it/s]
|
188 |
78%|ββββββββ | 663/851 [00:09<00:02, 69.14it/s]
|
189 |
79%|ββββββββ | 671/851 [00:09<00:02, 69.12it/s]
|
190 |
80%|ββββββββ | 679/851 [00:09<00:02, 69.97it/s]
|
191 |
81%|ββββββββ | 687/851 [00:09<00:02, 70.94it/s]
|
192 |
82%|βββββββββ | 695/851 [00:09<00:02, 72.48it/s]
|
193 |
83%|βββββββββ | 703/851 [00:09<00:02, 73.26it/s]
|
194 |
84%|βββββββββ | 711/851 [00:09<00:01, 74.87it/s]
|
195 |
84%|βββββββββ | 719/851 [00:09<00:01, 73.29it/s]
|
196 |
85%|βββββββββ | 727/851 [00:10<00:01, 74.62it/s]
|
197 |
86%|βββββββββ | 735/851 [00:10<00:01, 75.28it/s]
|
198 |
87%|βββββββββ | 743/851 [00:10<00:01, 74.64it/s]
|
199 |
88%|βββββββββ | 751/851 [00:10<00:01, 73.98it/s]
|
200 |
89%|βββββββββ | 759/851 [00:10<00:01, 74.89it/s]
|
201 |
90%|βββββββββ | 767/851 [00:10<00:01, 70.39it/s]
|
202 |
91%|βββββββββ | 775/851 [00:10<00:01, 69.17it/s]
|
203 |
92%|ββββββββββ| 782/851 [00:10<00:01, 68.09it/s]
|
204 |
93%|ββββββββββ| 790/851 [00:10<00:00, 69.33it/s]
|
205 |
94%|ββββββββββ| 798/851 [00:11<00:00, 70.49it/s]
|
206 |
95%|ββββββββββ| 806/851 [00:11<00:00, 72.99it/s]
|
207 |
96%|ββββββββββ| 814/851 [00:11<00:00, 70.07it/s]
|
208 |
97%|ββββββββββ| 822/851 [00:11<00:00, 71.14it/s]
|
209 |
98%|ββββββββββ| 830/851 [00:11<00:00, 71.12it/s]
|
210 |
98%|ββββββββββ| 838/851 [00:11<00:00, 71.03it/s]
|
211 |
99%|ββββββββββ| 846/851 [00:11<00:00, 66.90it/s]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2024-05-13 13:59:44.191151: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
|
2 |
+
2024-05-13 13:59:44.191275: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
|
3 |
+
2024-05-13 13:59:44.193141: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
|
4 |
+
2024-05-13 13:59:45.319933: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
|
5 |
+
05/13/2024 13:59:47 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
|
6 |
+
05/13/2024 13:59:47 - INFO - __main__ - Training/evaluation parameters TrainingArguments(
|
7 |
+
_n_gpu=1,
|
8 |
+
accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None},
|
9 |
+
adafactor=False,
|
10 |
+
adam_beta1=0.9,
|
11 |
+
adam_beta2=0.999,
|
12 |
+
adam_epsilon=1e-08,
|
13 |
+
auto_find_batch_size=False,
|
14 |
+
bf16=False,
|
15 |
+
bf16_full_eval=False,
|
16 |
+
data_seed=None,
|
17 |
+
dataloader_drop_last=False,
|
18 |
+
dataloader_num_workers=0,
|
19 |
+
dataloader_persistent_workers=False,
|
20 |
+
dataloader_pin_memory=True,
|
21 |
+
dataloader_prefetch_factor=None,
|
22 |
+
ddp_backend=None,
|
23 |
+
ddp_broadcast_buffers=None,
|
24 |
+
ddp_bucket_cap_mb=None,
|
25 |
+
ddp_find_unused_parameters=None,
|
26 |
+
ddp_timeout=1800,
|
27 |
+
debug=[],
|
28 |
+
deepspeed=None,
|
29 |
+
disable_tqdm=False,
|
30 |
+
dispatch_batches=None,
|
31 |
+
do_eval=True,
|
32 |
+
do_predict=True,
|
33 |
+
do_train=False,
|
34 |
+
eval_accumulation_steps=None,
|
35 |
+
eval_delay=0,
|
36 |
+
eval_do_concat_batches=True,
|
37 |
+
eval_steps=None,
|
38 |
+
evaluation_strategy=epoch,
|
39 |
+
fp16=False,
|
40 |
+
fp16_backend=auto,
|
41 |
+
fp16_full_eval=False,
|
42 |
+
fp16_opt_level=O1,
|
43 |
+
fsdp=[],
|
44 |
+
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
|
45 |
+
fsdp_min_num_params=0,
|
46 |
+
fsdp_transformer_layer_cls_to_wrap=None,
|
47 |
+
full_determinism=False,
|
48 |
+
gradient_accumulation_steps=4,
|
49 |
+
gradient_checkpointing=False,
|
50 |
+
gradient_checkpointing_kwargs=None,
|
51 |
+
greater_is_better=True,
|
52 |
+
group_by_length=False,
|
53 |
+
half_precision_backend=auto,
|
54 |
+
hub_always_push=False,
|
55 |
+
hub_model_id=None,
|
56 |
+
hub_private_repo=False,
|
57 |
+
hub_strategy=every_save,
|
58 |
+
hub_token=<HUB_TOKEN>,
|
59 |
+
ignore_data_skip=False,
|
60 |
+
include_inputs_for_metrics=False,
|
61 |
+
include_num_input_tokens_seen=False,
|
62 |
+
include_tokens_per_second=False,
|
63 |
+
jit_mode_eval=False,
|
64 |
+
label_names=None,
|
65 |
+
label_smoothing_factor=0.0,
|
66 |
+
learning_rate=5e-05,
|
67 |
+
length_column_name=length,
|
68 |
+
load_best_model_at_end=True,
|
69 |
+
local_rank=0,
|
70 |
+
log_level=passive,
|
71 |
+
log_level_replica=warning,
|
72 |
+
log_on_each_node=True,
|
73 |
+
logging_dir=/content/dissertation/scripts/ner/output/tb,
|
74 |
+
logging_first_step=False,
|
75 |
+
logging_nan_inf_filter=True,
|
76 |
+
logging_steps=500,
|
77 |
+
logging_strategy=steps,
|
78 |
+
lr_scheduler_kwargs={},
|
79 |
+
lr_scheduler_type=linear,
|
80 |
+
max_grad_norm=1.0,
|
81 |
+
max_steps=-1,
|
82 |
+
metric_for_best_model=f1,
|
83 |
+
mp_parameters=,
|
84 |
+
neftune_noise_alpha=None,
|
85 |
+
no_cuda=False,
|
86 |
+
num_train_epochs=10.0,
|
87 |
+
optim=adamw_torch,
|
88 |
+
optim_args=None,
|
89 |
+
optim_target_modules=None,
|
90 |
+
output_dir=/content/dissertation/scripts/ner/output,
|
91 |
+
overwrite_output_dir=True,
|
92 |
+
past_index=-1,
|
93 |
+
per_device_eval_batch_size=8,
|
94 |
+
per_device_train_batch_size=4,
|
95 |
+
prediction_loss_only=False,
|
96 |
+
push_to_hub=True,
|
97 |
+
push_to_hub_model_id=None,
|
98 |
+
push_to_hub_organization=None,
|
99 |
+
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
|
100 |
+
ray_scope=last,
|
101 |
+
remove_unused_columns=True,
|
102 |
+
report_to=['tensorboard'],
|
103 |
+
resume_from_checkpoint=None,
|
104 |
+
run_name=/content/dissertation/scripts/ner/output,
|
105 |
+
save_on_each_node=False,
|
106 |
+
save_only_model=False,
|
107 |
+
save_safetensors=True,
|
108 |
+
save_steps=500,
|
109 |
+
save_strategy=epoch,
|
110 |
+
save_total_limit=None,
|
111 |
+
seed=42,
|
112 |
+
skip_memory_metrics=True,
|
113 |
+
split_batches=None,
|
114 |
+
tf32=None,
|
115 |
+
torch_compile=False,
|
116 |
+
torch_compile_backend=None,
|
117 |
+
torch_compile_mode=None,
|
118 |
+
torchdynamo=None,
|
119 |
+
tpu_metrics_debug=False,
|
120 |
+
tpu_num_cores=None,
|
121 |
+
use_cpu=False,
|
122 |
+
use_ipex=False,
|
123 |
+
use_legacy_prediction_loop=False,
|
124 |
+
use_mps_device=False,
|
125 |
+
warmup_ratio=0.0,
|
126 |
+
warmup_steps=0,
|
127 |
+
weight_decay=0.0,
|
128 |
+
)
|
129 |
+
/usr/local/lib/python3.10/dist-packages/datasets/load.py:1486: FutureWarning: The repository for Rodrigo1771/multi-train-drugtemist-dev-ner contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/Rodrigo1771/multi-train-drugtemist-dev-ner
|
130 |
+
You can avoid this message in future by passing the argument `trust_remote_code=True`.
|
131 |
+
Passing `trust_remote_code=True` will be mandatory to load this dataset from the next major release of `datasets`.
|
132 |
+
warnings.warn(
|
133 |
+
|
134 |
+
|
135 |
+
|
136 |
+
|
137 |
+
|
138 |
+
|
139 |
+
|
140 |
+
/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
|
141 |
+
warnings.warn(
|
142 |
+
[INFO|configuration_utils.py:726] 2024-05-13 13:59:59,622 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
|
143 |
+
[INFO|configuration_utils.py:789] 2024-05-13 13:59:59,630 >> Model config RobertaConfig {
|
144 |
+
"_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
|
145 |
+
"architectures": [
|
146 |
+
"RobertaForMaskedLM"
|
147 |
+
],
|
148 |
+
"attention_probs_dropout_prob": 0.1,
|
149 |
+
"bos_token_id": 0,
|
150 |
+
"classifier_dropout": null,
|
151 |
+
"eos_token_id": 2,
|
152 |
+
"finetuning_task": "ner",
|
153 |
+
"gradient_checkpointing": false,
|
154 |
+
"hidden_act": "gelu",
|
155 |
+
"hidden_dropout_prob": 0.1,
|
156 |
+
"hidden_size": 768,
|
157 |
+
"id2label": {
|
158 |
+
"0": "O",
|
159 |
+
"1": "B-ENFERMEDAD",
|
160 |
+
"2": "I-ENFERMEDAD",
|
161 |
+
"3": "B-PROCEDIMIENTO",
|
162 |
+
"4": "I-PROCEDIMIENTO",
|
163 |
+
"5": "B-SINTOMA",
|
164 |
+
"6": "I-SINTOMA",
|
165 |
+
"7": "B-FARMACO",
|
166 |
+
"8": "I-FARMACO"
|
167 |
+
},
|
168 |
+
"initializer_range": 0.02,
|
169 |
+
"intermediate_size": 3072,
|
170 |
+
"label2id": {
|
171 |
+
"B-ENFERMEDAD": 1,
|
172 |
+
"B-FARMACO": 7,
|
173 |
+
"B-PROCEDIMIENTO": 3,
|
174 |
+
"B-SINTOMA": 5,
|
175 |
+
"I-ENFERMEDAD": 2,
|
176 |
+
"I-FARMACO": 8,
|
177 |
+
"I-PROCEDIMIENTO": 4,
|
178 |
+
"I-SINTOMA": 6,
|
179 |
+
"O": 0
|
180 |
+
},
|
181 |
+
"layer_norm_eps": 1e-05,
|
182 |
+
"max_position_embeddings": 514,
|
183 |
+
"model_type": "roberta",
|
184 |
+
"num_attention_heads": 12,
|
185 |
+
"num_hidden_layers": 12,
|
186 |
+
"pad_token_id": 1,
|
187 |
+
"position_embedding_type": "absolute",
|
188 |
+
"transformers_version": "4.40.2",
|
189 |
+
"type_vocab_size": 1,
|
190 |
+
"use_cache": true,
|
191 |
+
"vocab_size": 50262
|
192 |
+
}
|
193 |
+
|
194 |
+
[INFO|configuration_utils.py:726] 2024-05-13 13:59:59,860 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
|
195 |
+
[INFO|configuration_utils.py:789] 2024-05-13 13:59:59,860 >> Model config RobertaConfig {
|
196 |
+
"_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
|
197 |
+
"architectures": [
|
198 |
+
"RobertaForMaskedLM"
|
199 |
+
],
|
200 |
+
"attention_probs_dropout_prob": 0.1,
|
201 |
+
"bos_token_id": 0,
|
202 |
+
"classifier_dropout": null,
|
203 |
+
"eos_token_id": 2,
|
204 |
+
"gradient_checkpointing": false,
|
205 |
+
"hidden_act": "gelu",
|
206 |
+
"hidden_dropout_prob": 0.1,
|
207 |
+
"hidden_size": 768,
|
208 |
+
"initializer_range": 0.02,
|
209 |
+
"intermediate_size": 3072,
|
210 |
+
"layer_norm_eps": 1e-05,
|
211 |
+
"max_position_embeddings": 514,
|
212 |
+
"model_type": "roberta",
|
213 |
+
"num_attention_heads": 12,
|
214 |
+
"num_hidden_layers": 12,
|
215 |
+
"pad_token_id": 1,
|
216 |
+
"position_embedding_type": "absolute",
|
217 |
+
"transformers_version": "4.40.2",
|
218 |
+
"type_vocab_size": 1,
|
219 |
+
"use_cache": true,
|
220 |
+
"vocab_size": 50262
|
221 |
+
}
|
222 |
+
|
223 |
+
[INFO|tokenization_utils_base.py:2087] 2024-05-13 14:00:01,284 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/vocab.json
|
224 |
+
[INFO|tokenization_utils_base.py:2087] 2024-05-13 14:00:01,284 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/merges.txt
|
225 |
+
[INFO|tokenization_utils_base.py:2087] 2024-05-13 14:00:01,284 >> loading file tokenizer.json from cache at None
|
226 |
+
[INFO|tokenization_utils_base.py:2087] 2024-05-13 14:00:01,284 >> loading file added_tokens.json from cache at None
|
227 |
+
[INFO|tokenization_utils_base.py:2087] 2024-05-13 14:00:01,284 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/special_tokens_map.json
|
228 |
+
[INFO|tokenization_utils_base.py:2087] 2024-05-13 14:00:01,284 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/tokenizer_config.json
|
229 |
+
[INFO|configuration_utils.py:726] 2024-05-13 14:00:01,284 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
|
230 |
+
[INFO|configuration_utils.py:789] 2024-05-13 14:00:01,285 >> Model config RobertaConfig {
|
231 |
+
"_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
|
232 |
+
"architectures": [
|
233 |
+
"RobertaForMaskedLM"
|
234 |
+
],
|
235 |
+
"attention_probs_dropout_prob": 0.1,
|
236 |
+
"bos_token_id": 0,
|
237 |
+
"classifier_dropout": null,
|
238 |
+
"eos_token_id": 2,
|
239 |
+
"gradient_checkpointing": false,
|
240 |
+
"hidden_act": "gelu",
|
241 |
+
"hidden_dropout_prob": 0.1,
|
242 |
+
"hidden_size": 768,
|
243 |
+
"initializer_range": 0.02,
|
244 |
+
"intermediate_size": 3072,
|
245 |
+
"layer_norm_eps": 1e-05,
|
246 |
+
"max_position_embeddings": 514,
|
247 |
+
"model_type": "roberta",
|
248 |
+
"num_attention_heads": 12,
|
249 |
+
"num_hidden_layers": 12,
|
250 |
+
"pad_token_id": 1,
|
251 |
+
"position_embedding_type": "absolute",
|
252 |
+
"transformers_version": "4.40.2",
|
253 |
+
"type_vocab_size": 1,
|
254 |
+
"use_cache": true,
|
255 |
+
"vocab_size": 50262
|
256 |
+
}
|
257 |
+
|
258 |
+
[INFO|configuration_utils.py:726] 2024-05-13 14:00:01,385 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/config.json
|
259 |
+
[INFO|configuration_utils.py:789] 2024-05-13 14:00:01,386 >> Model config RobertaConfig {
|
260 |
+
"_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
|
261 |
+
"architectures": [
|
262 |
+
"RobertaForMaskedLM"
|
263 |
+
],
|
264 |
+
"attention_probs_dropout_prob": 0.1,
|
265 |
+
"bos_token_id": 0,
|
266 |
+
"classifier_dropout": null,
|
267 |
+
"eos_token_id": 2,
|
268 |
+
"gradient_checkpointing": false,
|
269 |
+
"hidden_act": "gelu",
|
270 |
+
"hidden_dropout_prob": 0.1,
|
271 |
+
"hidden_size": 768,
|
272 |
+
"initializer_range": 0.02,
|
273 |
+
"intermediate_size": 3072,
|
274 |
+
"layer_norm_eps": 1e-05,
|
275 |
+
"max_position_embeddings": 514,
|
276 |
+
"model_type": "roberta",
|
277 |
+
"num_attention_heads": 12,
|
278 |
+
"num_hidden_layers": 12,
|
279 |
+
"pad_token_id": 1,
|
280 |
+
"position_embedding_type": "absolute",
|
281 |
+
"transformers_version": "4.40.2",
|
282 |
+
"type_vocab_size": 1,
|
283 |
+
"use_cache": true,
|
284 |
+
"vocab_size": 50262
|
285 |
+
}
|
286 |
+
|
287 |
+
[INFO|modeling_utils.py:3429] 2024-05-13 14:00:06,524 >> loading weights file pytorch_model.bin from cache at /root/.cache/huggingface/hub/models--PlanTL-GOB-ES--bsc-bio-ehr-es/snapshots/1e543adb2d21f19d85a89305eebdbd64ab656b99/pytorch_model.bin
|
288 |
+
[INFO|modeling_utils.py:4160] 2024-05-13 14:00:06,768 >> Some weights of the model checkpoint at PlanTL-GOB-ES/bsc-bio-ehr-es were not used when initializing RobertaForTokenClassification: ['lm_head.bias', 'lm_head.decoder.bias', 'lm_head.decoder.weight', 'lm_head.dense.bias', 'lm_head.dense.weight', 'lm_head.layer_norm.bias', 'lm_head.layer_norm.weight']
|
289 |
+
- This IS expected if you are initializing RobertaForTokenClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
|
290 |
+
- This IS NOT expected if you are initializing RobertaForTokenClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
|
291 |
+
[WARNING|modeling_utils.py:4172] 2024-05-13 14:00:06,768 >> Some weights of RobertaForTokenClassification were not initialized from the model checkpoint at PlanTL-GOB-ES/bsc-bio-ehr-es and are newly initialized: ['classifier.bias', 'classifier.weight']
|
292 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
293 |
+
|
294 |
+
|
295 |
+
/content/dissertation/scripts/ner/run_ner.py:397: FutureWarning: load_metric is deprecated and will be removed in the next major version of datasets. Use 'evaluate.load' instead, from the new library π€ Evaluate: https://huggingface.co/docs/evaluate
|
296 |
+
metric = load_metric("seqeval")
|
297 |
+
/usr/local/lib/python3.10/dist-packages/datasets/load.py:759: FutureWarning: The repository for seqeval contains custom code which must be executed to correctly load the metric. You can inspect the repository content at https://raw.githubusercontent.com/huggingface/datasets/2.19.1/metrics/seqeval/seqeval.py
|
298 |
+
You can avoid this message in future by passing the argument `trust_remote_code=True`.
|
299 |
+
Passing `trust_remote_code=True` will be mandatory to load this metric from the next major release of `datasets`.
|
300 |
+
warnings.warn(
|
301 |
+
|
302 |
+
05/13/2024 14:00:09 - INFO - __main__ - *** Evaluate ***
|
303 |
+
[INFO|trainer.py:786] 2024-05-13 14:00:09,048 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, id, ner_tags. If tokens, id, ner_tags are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message.
|
304 |
+
[INFO|trainer.py:3614] 2024-05-13 14:00:09,055 >> ***** Running Evaluation *****
|
305 |
+
[INFO|trainer.py:3616] 2024-05-13 14:00:09,055 >> Num examples = 6807
|
306 |
+
[INFO|trainer.py:3619] 2024-05-13 14:00:09,055 >> Batch size = 8
|
307 |
+
|
308 |
0%| | 0/851 [00:00<?, ?it/s]
|
309 |
1%| | 6/851 [00:00<00:14, 56.79it/s]
|
310 |
2%|β | 14/851 [00:00<00:12, 66.67it/s]
|
311 |
2%|β | 21/851 [00:00<00:12, 67.60it/s]
|
312 |
3%|β | 29/851 [00:00<00:11, 71.18it/s]
|
313 |
4%|β | 37/851 [00:00<00:11, 72.27it/s]
|
314 |
5%|β | 45/851 [00:00<00:10, 73.94it/s]
|
315 |
6%|β | 53/851 [00:00<00:10, 75.21it/s]
|
316 |
7%|β | 62/851 [00:00<00:10, 76.83it/s]
|
317 |
8%|β | 70/851 [00:00<00:10, 72.77it/s]
|
318 |
9%|β | 78/851 [00:01<00:10, 73.82it/s]
|
319 |
10%|β | 86/851 [00:01<00:10, 72.92it/s]
|
320 |
11%|β | 94/851 [00:01<00:10, 71.23it/s]
|
321 |
12%|ββ | 102/851 [00:01<00:10, 72.43it/s]
|
322 |
13%|ββ | 110/851 [00:01<00:10, 71.56it/s]
|
323 |
14%|ββ | 118/851 [00:01<00:10, 72.68it/s]
|
324 |
15%|ββ | 126/851 [00:01<00:10, 69.25it/s]
|
325 |
16%|ββ | 134/851 [00:01<00:10, 69.92it/s]
|
326 |
17%|ββ | 142/851 [00:01<00:10, 70.22it/s]
|
327 |
18%|ββ | 150/851 [00:02<00:10, 68.89it/s]
|
328 |
19%|ββ | 158/851 [00:02<00:09, 71.66it/s]
|
329 |
20%|ββ | 166/851 [00:02<00:09, 72.84it/s]
|
330 |
20%|ββ | 174/851 [00:02<00:09, 73.78it/s]
|
331 |
21%|βββ | 182/851 [00:02<00:08, 74.73it/s]
|
332 |
22%|βββ | 191/851 [00:02<00:08, 75.91it/s]
|
333 |
24%|βββ | 200/851 [00:02<00:08, 77.69it/s]
|
334 |
24%|βββ | 208/851 [00:02<00:08, 74.46it/s]
|
335 |
25%|βββ | 216/851 [00:02<00:08, 73.02it/s]
|
336 |
26%|βββ | 224/851 [00:03<00:08, 73.31it/s]
|
337 |
27%|βββ | 233/851 [00:03<00:08, 75.80it/s]
|
338 |
28%|βββ | 241/851 [00:03<00:08, 70.34it/s]
|
339 |
29%|βββ | 249/851 [00:03<00:08, 70.90it/s]
|
340 |
30%|βββ | 258/851 [00:03<00:07, 74.54it/s]
|
341 |
31%|ββββ | 267/851 [00:03<00:07, 74.56it/s]
|
342 |
32%|ββββ | 275/851 [00:03<00:07, 75.23it/s]
|
343 |
33%|ββββ | 284/851 [00:03<00:07, 77.16it/s]
|
344 |
34%|ββββ | 292/851 [00:03<00:07, 75.36it/s]
|
345 |
35%|ββββ | 300/851 [00:04<00:07, 76.48it/s]
|
346 |
36%|ββββ | 309/851 [00:04<00:06, 78.03it/s]
|
347 |
37%|ββββ | 317/851 [00:04<00:07, 73.84it/s]
|
348 |
38%|ββββ | 325/851 [00:04<00:07, 74.16it/s]
|
349 |
39%|ββββ | 333/851 [00:04<00:07, 73.48it/s]
|
350 |
40%|ββββ | 341/851 [00:04<00:06, 75.03it/s]
|
351 |
41%|ββββ | 349/851 [00:04<00:06, 75.15it/s]
|
352 |
42%|βββββ | 357/851 [00:04<00:06, 71.25it/s]
|
353 |
43%|βββββ | 365/851 [00:04<00:06, 73.08it/s]
|
354 |
44%|βββββ | 373/851 [00:05<00:06, 71.71it/s]
|
355 |
45%|βββββ | 381/851 [00:05<00:06, 69.65it/s]
|
356 |
46%|βββββ | 389/851 [00:05<00:06, 72.30it/s]
|
357 |
47%|βββββ | 397/851 [00:05<00:06, 72.22it/s]
|
358 |
48%|βββββ | 405/851 [00:05<00:06, 67.45it/s]
|
359 |
49%|βββββ | 413/851 [00:05<00:06, 68.89it/s]
|
360 |
49%|βββββ | 421/851 [00:05<00:05, 71.75it/s]
|
361 |
50%|βββββ | 429/851 [00:05<00:06, 70.29it/s]
|
362 |
51%|ββββββ | 437/851 [00:06<00:05, 72.84it/s]
|
363 |
52%|ββββββ | 445/851 [00:06<00:05, 73.81it/s]
|
364 |
53%|ββββββ | 453/851 [00:06<00:05, 74.50it/s]
|
365 |
54%|ββββββ | 461/851 [00:06<00:05, 72.92it/s]
|
366 |
55%|ββββββ | 469/851 [00:06<00:05, 70.51it/s]
|
367 |
56%|ββββββ | 477/851 [00:06<00:05, 65.80it/s]
|
368 |
57%|ββββββ | 484/851 [00:06<00:05, 65.68it/s]
|
369 |
58%|ββββββ | 492/851 [00:06<00:05, 69.27it/s]
|
370 |
59%|ββββββ | 501/851 [00:06<00:04, 73.42it/s]
|
371 |
60%|ββββββ | 509/851 [00:07<00:04, 72.53it/s]
|
372 |
61%|ββββββ | 517/851 [00:07<00:04, 74.04it/s]
|
373 |
62%|βββββββ | 525/851 [00:07<00:04, 69.50it/s]
|
374 |
63%|βββββββ | 533/851 [00:07<00:04, 70.76it/s]
|
375 |
64%|βββββββ | 541/851 [00:07<00:04, 72.75it/s]
|
376 |
65%|βββββββ | 549/851 [00:07<00:04, 70.77it/s]
|
377 |
65%|βββββββ | 557/851 [00:07<00:04, 72.93it/s]
|
378 |
67%|βββββββ | 566/851 [00:07<00:03, 75.96it/s]
|
379 |
67%|βββββββ | 574/851 [00:07<00:03, 75.68it/s]
|
380 |
68%|βββββββ | 582/851 [00:08<00:03, 73.54it/s]
|
381 |
69%|βββββββ | 590/851 [00:08<00:03, 70.20it/s]
|
382 |
70%|βββββββ | 598/851 [00:08<00:03, 71.00it/s]
|
383 |
71%|βββββββ | 606/851 [00:08<00:03, 69.47it/s]
|
384 |
72%|ββββββββ | 613/851 [00:08<00:03, 67.88it/s]
|
385 |
73%|ββββββββ | 620/851 [00:08<00:03, 68.06it/s]
|
386 |
74%|ββββββββ | 627/851 [00:08<00:03, 67.97it/s]
|
387 |
75%|ββββββββ | 635/851 [00:08<00:03, 68.41it/s]
|
388 |
75%|ββββββββ | 642/851 [00:08<00:03, 63.33it/s]
|
389 |
76%|ββββββββ | 650/851 [00:09<00:02, 67.25it/s]
|
390 |
77%|ββββββββ | 658/851 [00:09<00:02, 69.51it/s]
|
391 |
78%|ββββββββ | 666/851 [00:09<00:02, 70.79it/s]
|
392 |
79%|ββββββββ | 674/851 [00:09<00:02, 70.05it/s]
|
393 |
80%|ββββββββ | 682/851 [00:09<00:02, 71.60it/s]
|
394 |
81%|ββββββββ | 691/851 [00:09<00:02, 74.53it/s]
|
395 |
82%|βββββββββ | 699/851 [00:09<00:02, 74.50it/s]
|
396 |
83%|βββββββββ | 708/851 [00:09<00:01, 76.84it/s]
|
397 |
84%|βββββββββ | 716/851 [00:09<00:01, 74.99it/s]
|
398 |
85%|βββββββββ | 724/851 [00:10<00:01, 75.33it/s]
|
399 |
86%|βββββββββ | 732/851 [00:10<00:01, 76.41it/s]
|
400 |
87%|βββββββββ | 740/851 [00:10<00:01, 76.60it/s]
|
401 |
88%|βββββββββ | 748/851 [00:10<00:01, 76.14it/s]
|
402 |
89%|βββββββββ | 756/851 [00:10<00:01, 75.65it/s]
|
403 |
90%|βββββββββ | 764/851 [00:10<00:01, 76.38it/s]
|
404 |
91%|βββββββββ | 772/851 [00:10<00:01, 71.78it/s]
|
405 |
92%|ββββββββββ| 780/851 [00:10<00:01, 69.90it/s]
|
406 |
93%|ββββββββββ| 788/851 [00:10<00:00, 70.05it/s]
|
407 |
94%|ββββββββββ| 796/851 [00:11<00:00, 70.92it/s]
|
408 |
94%|ββββββββββ| 804/851 [00:11<00:00, 73.14it/s]
|
409 |
95%|ββββββββββ| 812/851 [00:11<00:00, 71.35it/s]
|
410 |
96%|ββββββββββ| 820/851 [00:11<00:00, 72.32it/s]
|
411 |
97%|ββββββββββ| 828/851 [00:11<00:00, 73.57it/s]
|
412 |
98%|ββββββββββ| 836/851 [00:11<00:00, 73.25it/s]
|
413 |
99%|ββββββββββ| 844/851 [00:11<00:00, 70.06it/s]/usr/local/lib/python3.10/dist-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.
|
414 |
+
_warn_prf(average, modifier, msg_start, len(result))
|
415 |
+
|
416 |
+
***** eval metrics *****
|
417 |
+
eval_accuracy = 0.0028
|
418 |
+
eval_f1 = 0.0007
|
419 |
+
eval_loss = 2.4031
|
420 |
+
eval_precision = 0.0004
|
421 |
+
eval_recall = 0.0386
|
422 |
+
eval_runtime = 0:00:16.79
|
423 |
+
eval_samples = 6807
|
424 |
+
eval_samples_per_second = 405.27
|
425 |
+
eval_steps_per_second = 50.666
|
426 |
+
05/13/2024 14:00:25 - INFO - __main__ - *** Predict ***
|
427 |
+
[INFO|trainer.py:786] 2024-05-13 14:00:25,855 >> The following columns in the test set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: tokens, id, ner_tags. If tokens, id, ner_tags are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message.
|
428 |
+
[INFO|trainer.py:3614] 2024-05-13 14:00:25,857 >> ***** Running Prediction *****
|
429 |
+
[INFO|trainer.py:3616] 2024-05-13 14:00:25,857 >> Num examples = 6807
|
430 |
+
[INFO|trainer.py:3619] 2024-05-13 14:00:25,857 >> Batch size = 8
|
431 |
+
|
432 |
0%| | 0/851 [00:00<?, ?it/s]
|
433 |
1%| | 10/851 [00:00<00:09, 91.44it/s]
|
434 |
2%|β | 20/851 [00:00<00:10, 80.05it/s]
|
435 |
3%|β | 29/851 [00:00<00:10, 76.91it/s]
|
436 |
4%|β | 37/851 [00:00<00:10, 76.11it/s]
|
437 |
5%|β | 45/851 [00:00<00:10, 76.81it/s]
|
438 |
6%|β | 53/851 [00:00<00:10, 77.42it/s]
|
439 |
7%|β | 62/851 [00:00<00:10, 78.22it/s]
|
440 |
8%|β | 70/851 [00:00<00:10, 73.17it/s]
|
441 |
9%|β | 78/851 [00:01<00:10, 74.14it/s]
|
442 |
10%|β | 86/851 [00:01<00:10, 74.47it/s]
|
443 |
11%|β | 94/851 [00:01<00:10, 71.54it/s]
|
444 |
12%|ββ | 102/851 [00:01<00:10, 72.66it/s]
|
445 |
13%|ββ | 110/851 [00:01<00:10, 71.47it/s]
|
446 |
14%|ββ | 118/851 [00:01<00:10, 72.13it/s]
|
447 |
15%|ββ | 126/851 [00:01<00:10, 69.31it/s]
|
448 |
16%|ββ | 134/851 [00:01<00:10, 69.99it/s]
|
449 |
17%|ββ | 142/851 [00:01<00:10, 70.34it/s]
|
450 |
18%|ββ | 150/851 [00:02<00:10, 69.10it/s]
|
451 |
19%|ββ | 159/851 [00:02<00:09, 73.31it/s]
|
452 |
20%|ββ | 167/851 [00:02<00:09, 73.76it/s]
|
453 |
21%|ββ | 175/851 [00:02<00:09, 74.62it/s]
|
454 |
22%|βββ | 183/851 [00:02<00:08, 75.28it/s]
|
455 |
22%|βββ | 191/851 [00:02<00:08, 75.29it/s]
|
456 |
24%|βββ | 200/851 [00:02<00:08, 77.19it/s]
|
457 |
24%|βββ | 208/851 [00:02<00:08, 74.09it/s]
|
458 |
25%|βββ | 216/851 [00:02<00:08, 72.43it/s]
|
459 |
26%|βββ | 224/851 [00:03<00:08, 72.43it/s]
|
460 |
27%|βββ | 232/851 [00:03<00:08, 74.47it/s]
|
461 |
28%|βββ | 240/851 [00:03<00:08, 72.23it/s]
|
462 |
29%|βββ | 248/851 [00:03<00:08, 70.30it/s]
|
463 |
30%|βββ | 257/851 [00:03<00:08, 74.22it/s]
|
464 |
31%|ββββ | 266/851 [00:03<00:07, 76.38it/s]
|
465 |
32%|ββββ | 274/851 [00:03<00:07, 73.69it/s]
|
466 |
33%|ββββ | 283/851 [00:03<00:07, 75.70it/s]
|
467 |
34%|ββββ | 291/851 [00:03<00:07, 74.53it/s]
|
468 |
35%|ββββ | 299/851 [00:04<00:07, 75.95it/s]
|
469 |
36%|ββββ | 308/851 [00:04<00:06, 77.72it/s]
|
470 |
37%|ββββ | 316/851 [00:04<00:07, 73.39it/s]
|
471 |
38%|ββββ | 324/851 [00:04<00:07, 74.25it/s]
|
472 |
39%|ββββ | 332/851 [00:04<00:07, 73.40it/s]
|
473 |
40%|ββββ | 340/851 [00:04<00:06, 74.69it/s]
|
474 |
41%|ββββ | 348/851 [00:04<00:06, 74.45it/s]
|
475 |
42%|βββββ | 356/851 [00:04<00:06, 71.61it/s]
|
476 |
43%|βββββ | 364/851 [00:04<00:06, 71.59it/s]
|
477 |
44%|βββββ | 372/851 [00:05<00:06, 71.39it/s]
|
478 |
45%|βββββ | 380/851 [00:05<00:06, 68.82it/s]
|
479 |
46%|βββββ | 388/851 [00:05<00:06, 71.34it/s]
|
480 |
47%|βββββ | 396/851 [00:05<00:06, 71.74it/s]
|
481 |
47%|βββββ | 404/851 [00:05<00:06, 67.34it/s]
|
482 |
48%|βββββ | 411/851 [00:05<00:06, 67.07it/s]
|
483 |
49%|βββββ | 419/851 [00:05<00:06, 70.05it/s]
|
484 |
50%|βββββ | 427/851 [00:05<00:06, 68.22it/s]
|
485 |
51%|βββββ | 435/851 [00:05<00:05, 71.05it/s]
|
486 |
52%|ββββββ | 443/851 [00:06<00:05, 73.07it/s]
|
487 |
53%|ββββββ | 451/851 [00:06<00:05, 73.76it/s]
|
488 |
54%|ββββββ | 459/851 [00:06<00:05, 74.30it/s]
|
489 |
55%|ββββββ | 467/851 [00:06<00:05, 69.53it/s]
|
490 |
56%|ββββββ | 475/851 [00:06<00:05, 64.31it/s]
|
491 |
57%|ββββββ | 482/851 [00:06<00:05, 65.00it/s]
|
492 |
57%|ββββββ | 489/851 [00:06<00:05, 66.01it/s]
|
493 |
59%|ββββββ | 498/851 [00:06<00:04, 70.87it/s]
|
494 |
59%|ββββββ | 506/851 [00:06<00:04, 72.82it/s]
|
495 |
60%|ββββββ | 514/851 [00:07<00:04, 72.54it/s]
|
496 |
61%|βββββββ | 522/851 [00:07<00:04, 69.41it/s]
|
497 |
62%|βββββββ | 530/851 [00:07<00:04, 69.19it/s]
|
498 |
63%|βββββββ | 538/851 [00:07<00:04, 71.41it/s]
|
499 |
64%|βββββββ | 546/851 [00:07<00:04, 72.09it/s]
|
500 |
65%|βββββββ | 554/851 [00:07<00:04, 70.07it/s]
|
501 |
66%|βββββββ | 562/851 [00:07<00:04, 72.16it/s]
|
502 |
67%|βββββββ | 570/851 [00:07<00:03, 73.41it/s]
|
503 |
68%|βββββββ | 578/851 [00:07<00:03, 71.89it/s]
|
504 |
69%|βββββββ | 586/851 [00:08<00:03, 70.00it/s]
|
505 |
70%|βββββββ | 594/851 [00:08<00:03, 70.61it/s]
|
506 |
71%|βββββββ | 602/851 [00:08<00:03, 71.04it/s]
|
507 |
72%|ββββββββ | 610/851 [00:08<00:03, 70.41it/s]
|
508 |
73%|ββββββββ | 618/851 [00:08<00:03, 66.31it/s]
|
509 |
74%|ββββββββ | 626/851 [00:08<00:03, 66.58it/s]
|
510 |
74%|ββββββββ | 633/851 [00:08<00:03, 67.17it/s]
|
511 |
75%|ββββββββ | 640/851 [00:08<00:03, 67.05it/s]
|
512 |
76%|ββββββββ | 647/851 [00:09<00:03, 65.37it/s]
|
513 |
77%|ββββββββ | 655/851 [00:09<00:02, 68.38it/s]
|
514 |
78%|ββββββββ | 663/851 [00:09<00:02, 69.14it/s]
|
515 |
79%|ββββββββ | 671/851 [00:09<00:02, 69.12it/s]
|
516 |
80%|ββββββββ | 679/851 [00:09<00:02, 69.97it/s]
|
517 |
81%|ββββββββ | 687/851 [00:09<00:02, 70.94it/s]
|
518 |
82%|βββββββββ | 695/851 [00:09<00:02, 72.48it/s]
|
519 |
83%|βββββββββ | 703/851 [00:09<00:02, 73.26it/s]
|
520 |
84%|βββββββββ | 711/851 [00:09<00:01, 74.87it/s]
|
521 |
84%|βββββββββ | 719/851 [00:09<00:01, 73.29it/s]
|
522 |
85%|βββββββββ | 727/851 [00:10<00:01, 74.62it/s]
|
523 |
86%|βββββββββ | 735/851 [00:10<00:01, 75.28it/s]
|
524 |
87%|βββββββββ | 743/851 [00:10<00:01, 74.64it/s]
|
525 |
88%|βββββββββ | 751/851 [00:10<00:01, 73.98it/s]
|
526 |
89%|βββββββββ | 759/851 [00:10<00:01, 74.89it/s]
|
527 |
90%|βββββββββ | 767/851 [00:10<00:01, 70.39it/s]
|
528 |
91%|βββββββββ | 775/851 [00:10<00:01, 69.17it/s]
|
529 |
92%|ββββββββββ| 782/851 [00:10<00:01, 68.09it/s]
|
530 |
93%|ββββββββββ| 790/851 [00:10<00:00, 69.33it/s]
|
531 |
94%|ββββββββββ| 798/851 [00:11<00:00, 70.49it/s]
|
532 |
95%|ββββββββββ| 806/851 [00:11<00:00, 72.99it/s]
|
533 |
96%|ββββββββββ| 814/851 [00:11<00:00, 70.07it/s]
|
534 |
97%|ββββββββββ| 822/851 [00:11<00:00, 71.14it/s]
|
535 |
98%|ββββββββββ| 830/851 [00:11<00:00, 71.12it/s]
|
536 |
98%|ββββββββββ| 838/851 [00:11<00:00, 71.03it/s]
|
537 |
99%|ββββββββββ| 846/851 [00:11<00:00, 66.90it/s]
|
538 |
+
[INFO|trainer.py:3305] 2024-05-13 14:00:42,250 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
|
539 |
+
[INFO|configuration_utils.py:471] 2024-05-13 14:00:42,251 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
|
540 |
+
[INFO|modeling_utils.py:2590] 2024-05-13 14:00:43,185 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
|
541 |
+
[INFO|tokenization_utils_base.py:2488] 2024-05-13 14:00:43,186 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
|
542 |
+
[INFO|tokenization_utils_base.py:2497] 2024-05-13 14:00:43,186 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
|
543 |
+
[INFO|modelcard.py:450] 2024-05-13 14:00:43,335 >> Dropping the following result as it does not have all the necessary fields:
|
544 |
+
{'task': {'name': 'Token Classification', 'type': 'token-classification'}, 'dataset': {'name': 'Rodrigo1771/multi-train-drugtemist-dev-ner', 'type': 'Rodrigo1771/multi-train-drugtemist-dev-ner', 'config': 'MultiTrainDrugTEMISTDevNER', 'split': 'validation', 'args': 'MultiTrainDrugTEMISTDevNER'}}
|
545 |
+
***** predict metrics *****
|
546 |
+
predict_accuracy = 0.0028
|
547 |
+
predict_f1 = 0.0007
|
548 |
+
predict_loss = 2.4031
|
549 |
+
predict_precision = 0.0004
|
550 |
+
predict_recall = 0.0386
|
551 |
+
predict_runtime = 0:00:16.07
|
552 |
+
predict_samples_per_second = 423.545
|
553 |
+
predict_steps_per_second = 52.951
|
554 |
+
|
555 |
+
|
556 |
+
|
557 |
+
|
558 |
+
|
559 |
+
|
560 |
+
|
561 |
+
|
562 |
+
|
563 |
+
|
564 |
+
|
565 |
+
|
566 |
+
|
567 |
+
|
568 |
+
|
569 |
+
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18cce49dc172023921a8c234d2d643afeaa0b4f8f209fd2e1d76d267cbbe3c95
|
3 |
+
size 5048
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|