José Antonio García Díaz
commited on
Commit
·
fd0be85
1
Parent(s):
d28792f
fixed tokenizer
Browse files- config.json +38 -38
- hyperparameters.csv +10 -10
- merges.txt +0 -0
- model.safetensors +1 -1
- optimizer.pt +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +51 -1
- tokenizer.json +0 -0
- tokenizer_config.json +58 -14
- trainer_state.json +49 -24
- training_args.bin +1 -1
- training_resume.json +2 -2
- vocab.json +0 -0
config.json
CHANGED
@@ -1,39 +1,39 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
|
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 |
+
"0": "negative",
|
16 |
+
"1": "neutral",
|
17 |
+
"2": "positive"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"negative": 0,
|
23 |
+
"neutral": 1,
|
24 |
+
"positive": 2
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-05,
|
27 |
+
"max_position_embeddings": 514,
|
28 |
+
"model_type": "roberta",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.46.2",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50262
|
39 |
+
}
|
hyperparameters.csv
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
objective,best,learning_rate,num_train_epochs,per_device_train_batch_size,warmup_steps,weight_decay,time_this_iter_s
|
2 |
-
0.
|
3 |
-
0.
|
4 |
-
0.
|
5 |
-
0.
|
6 |
-
0.
|
7 |
-
0.
|
8 |
-
0.
|
9 |
-
0.
|
10 |
-
0.
|
11 |
-
0.
|
|
|
1 |
objective,best,learning_rate,num_train_epochs,per_device_train_batch_size,warmup_steps,weight_decay,time_this_iter_s
|
2 |
+
0.6375283056594502,False,2.2682993818119634e-05,4,8,250,0.11257883483123868,62.295817613601685
|
3 |
+
0.6379352675229796,False,3.590880126653354e-05,3,16,1000,0.04950127542303912,57.21566104888916
|
4 |
+
0.6430101919356234,False,1.3305018813937754e-05,5,16,0,0.12477446104218509,57.07160472869873
|
5 |
+
0.5816271212668901,False,4.3719292103728615e-05,4,16,0,0.1691336373423109,58.25519013404846
|
6 |
+
0.6034066935437185,False,4.5066082606416965e-05,2,8,0,0.14557098270440524,63.2433078289032
|
7 |
+
0.565798317351568,False,4.5661870380314306e-05,5,8,250,0.2447905231269368,63.3815643787384
|
8 |
+
0.608610258345654,False,4.2309504791301604e-05,2,8,500,0.10748446501369772,63.30465888977051
|
9 |
+
0.6436338860188018,True,3.270513699172022e-05,4,16,0,0.07303439372733585,57.2542085647583
|
10 |
+
0.6128416978240078,False,4.0694553908891e-05,4,16,0,0.02683040797439604,58.1628360748291
|
11 |
+
0.6023919757272725,False,4.636122094405269e-05,1,8,1000,0.2126251167385789,64.2628378868103
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498606684
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8bcc165d8ed8e483102b09ac6474223640ad6efb6875e87067085d5b551dee3
|
3 |
size 498606684
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 997333242
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec9610175848862ca038e87ea85d878ec4a68aa555a0749b997bc68d78acff8e
|
3 |
size 997333242
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72eb625897e65592fa617f063dfc48812023fc6a9a3a4970bad58bf9ba8f479a
|
3 |
size 1064
|
special_tokens_map.json
CHANGED
@@ -1 +1,51 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,14 +1,58 @@
|
|
1 |
-
{
|
2 |
-
|
3 |
-
|
4 |
-
"
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
"
|
13 |
-
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
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 |
+
"4": {
|
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": false,
|
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 |
+
}
|
trainer_state.json
CHANGED
@@ -1,43 +1,68 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./results/run-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": true,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0029069767441860465,
|
13 |
-
"grad_norm": 1.
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 1.
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
-
"eval_f1": 0.
|
21 |
-
"eval_loss": 0.
|
22 |
-
"eval_runtime": 1.
|
23 |
-
"eval_samples_per_second":
|
24 |
-
"eval_steps_per_second":
|
25 |
"step": 344
|
26 |
},
|
27 |
{
|
28 |
"epoch": 2.0,
|
29 |
-
"eval_f1": 0.
|
30 |
-
"eval_loss": 0.
|
31 |
-
"eval_runtime":
|
32 |
-
"eval_samples_per_second":
|
33 |
-
"eval_steps_per_second":
|
34 |
"step": 688
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
}
|
36 |
],
|
37 |
"logging_steps": 1000,
|
38 |
-
"max_steps":
|
39 |
"num_input_tokens_seen": 0,
|
40 |
-
"num_train_epochs":
|
41 |
"save_steps": 500,
|
42 |
"stateful_callbacks": {
|
43 |
"TrainerControl": {
|
@@ -51,14 +76,14 @@
|
|
51 |
"attributes": {}
|
52 |
}
|
53 |
},
|
54 |
-
"total_flos":
|
55 |
"train_batch_size": 16,
|
56 |
"trial_name": null,
|
57 |
"trial_params": {
|
58 |
-
"learning_rate":
|
59 |
-
"num_train_epochs":
|
60 |
"per_device_train_batch_size": 16,
|
61 |
-
"warmup_steps":
|
62 |
-
"weight_decay": 0.
|
63 |
}
|
64 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8585572838783264,
|
3 |
+
"best_model_checkpoint": "./results/run-37598087/checkpoint-344",
|
4 |
+
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1376,
|
7 |
"is_hyper_param_search": true,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0029069767441860465,
|
13 |
+
"grad_norm": 1.1999566555023193,
|
14 |
+
"learning_rate": 3.2681368723557635e-05,
|
15 |
+
"loss": 1.0968,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
+
"eval_f1": 0.6239361242297824,
|
21 |
+
"eval_loss": 0.8585572838783264,
|
22 |
+
"eval_runtime": 1.1693,
|
23 |
+
"eval_samples_per_second": 1566.772,
|
24 |
+
"eval_steps_per_second": 195.846,
|
25 |
"step": 344
|
26 |
},
|
27 |
{
|
28 |
"epoch": 2.0,
|
29 |
+
"eval_f1": 0.6482640943501118,
|
30 |
+
"eval_loss": 0.9017149806022644,
|
31 |
+
"eval_runtime": 1.1788,
|
32 |
+
"eval_samples_per_second": 1554.158,
|
33 |
+
"eval_steps_per_second": 194.27,
|
34 |
"step": 688
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.9069767441860463,
|
38 |
+
"grad_norm": 10.886157989501953,
|
39 |
+
"learning_rate": 8.93686882913285e-06,
|
40 |
+
"loss": 0.5554,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_f1": 0.649741833511255,
|
46 |
+
"eval_loss": 1.2939248085021973,
|
47 |
+
"eval_runtime": 1.1859,
|
48 |
+
"eval_samples_per_second": 1544.754,
|
49 |
+
"eval_steps_per_second": 193.094,
|
50 |
+
"step": 1032
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_f1": 0.6436338860188018,
|
55 |
+
"eval_loss": 1.5838754177093506,
|
56 |
+
"eval_runtime": 1.1543,
|
57 |
+
"eval_samples_per_second": 1587.073,
|
58 |
+
"eval_steps_per_second": 198.384,
|
59 |
+
"step": 1376
|
60 |
}
|
61 |
],
|
62 |
"logging_steps": 1000,
|
63 |
+
"max_steps": 1376,
|
64 |
"num_input_tokens_seen": 0,
|
65 |
+
"num_train_epochs": 4,
|
66 |
"save_steps": 500,
|
67 |
"stateful_callbacks": {
|
68 |
"TrainerControl": {
|
|
|
76 |
"attributes": {}
|
77 |
}
|
78 |
},
|
79 |
+
"total_flos": 4202973734787072.0,
|
80 |
"train_batch_size": 16,
|
81 |
"trial_name": null,
|
82 |
"trial_params": {
|
83 |
+
"learning_rate": 3.270513699172022e-05,
|
84 |
+
"num_train_epochs": 4,
|
85 |
"per_device_train_batch_size": 16,
|
86 |
+
"warmup_steps": 0,
|
87 |
+
"weight_decay": 0.07303439372733585
|
88 |
}
|
89 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f91c32ad276d2e896aadd62adf8948a10e9ca13ebf58837f96206e3ee4b8fc14
|
3 |
size 5240
|
training_resume.json
CHANGED
@@ -19,10 +19,10 @@
|
|
19 |
"resources_per_trial": {
|
20 |
"gpu": 1
|
21 |
},
|
22 |
-
"run_id": "
|
23 |
"task": "",
|
24 |
"task_type": "classification",
|
25 |
-
"tokenizer_field": "
|
26 |
"tokenizer_model": "PlanTL-GOB-ES/roberta-base-bne",
|
27 |
"warmup_steps": 500,
|
28 |
"weight_decay": 0.01
|
|
|
19 |
"resources_per_trial": {
|
20 |
"gpu": 1
|
21 |
},
|
22 |
+
"run_id": "37598087",
|
23 |
"task": "",
|
24 |
"task_type": "classification",
|
25 |
+
"tokenizer_field": "tweet_clean_lowercase",
|
26 |
"tokenizer_model": "PlanTL-GOB-ES/roberta-base-bne",
|
27 |
"warmup_steps": 500,
|
28 |
"weight_decay": 0.01
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|