mario-mgmn
commited on
Commit
•
2b00fc5
1
Parent(s):
73f2c09
Upload 12 files
Browse files- all_results.json +26 -0
- config.json +66 -0
- eval_results.json +15 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +14 -0
- trainer_state.json +108 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.9905438520216592,
|
4 |
+
"eval_f1": 0.9003506721215664,
|
5 |
+
"eval_loss": 0.04321206733584404,
|
6 |
+
"eval_mem_cpu_alloc_delta": 149028864,
|
7 |
+
"eval_mem_cpu_peaked_delta": 9793536,
|
8 |
+
"eval_mem_gpu_alloc_delta": 0,
|
9 |
+
"eval_mem_gpu_peaked_delta": 314081280,
|
10 |
+
"eval_precision": 0.8971173444627778,
|
11 |
+
"eval_recall": 0.9036073907517841,
|
12 |
+
"eval_runtime": 34.5441,
|
13 |
+
"eval_samples": 7550,
|
14 |
+
"eval_samples_per_second": 218.561,
|
15 |
+
"init_mem_cpu_alloc_delta": -68857856,
|
16 |
+
"init_mem_cpu_peaked_delta": 154255360,
|
17 |
+
"init_mem_gpu_alloc_delta": 497570816,
|
18 |
+
"init_mem_gpu_peaked_delta": 0,
|
19 |
+
"train_mem_cpu_alloc_delta": 2823634944,
|
20 |
+
"train_mem_cpu_peaked_delta": 164388864,
|
21 |
+
"train_mem_gpu_alloc_delta": 1508407296,
|
22 |
+
"train_mem_gpu_peaked_delta": 10039297024,
|
23 |
+
"train_runtime": 1076.7664,
|
24 |
+
"train_samples": 22648,
|
25 |
+
"train_samples_per_second": 3.288
|
26 |
+
}
|
config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base-bne",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"finetuning_task": "ner",
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.0,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "B-LOC",
|
16 |
+
"1": "B-ORG",
|
17 |
+
"2": "B-OTH",
|
18 |
+
"3": "B-PER",
|
19 |
+
"4": "E-LOC",
|
20 |
+
"5": "E-ORG",
|
21 |
+
"6": "E-OTH",
|
22 |
+
"7": "E-PER",
|
23 |
+
"8": "I-LOC",
|
24 |
+
"9": "I-ORG",
|
25 |
+
"10": "I-OTH",
|
26 |
+
"11": "I-PER",
|
27 |
+
"12": "O",
|
28 |
+
"13": "S-LOC",
|
29 |
+
"14": "S-ORG",
|
30 |
+
"15": "S-OTH",
|
31 |
+
"16": "S-PER"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
+
"label2id": {
|
36 |
+
"B-LOC": 0,
|
37 |
+
"B-ORG": 1,
|
38 |
+
"B-OTH": 2,
|
39 |
+
"B-PER": 3,
|
40 |
+
"E-LOC": 4,
|
41 |
+
"E-ORG": 5,
|
42 |
+
"E-OTH": 6,
|
43 |
+
"E-PER": 7,
|
44 |
+
"I-LOC": 8,
|
45 |
+
"I-ORG": 9,
|
46 |
+
"I-OTH": 10,
|
47 |
+
"I-PER": 11,
|
48 |
+
"O": 12,
|
49 |
+
"S-LOC": 13,
|
50 |
+
"S-ORG": 14,
|
51 |
+
"S-OTH": 15,
|
52 |
+
"S-PER": 16
|
53 |
+
|
54 |
+
},
|
55 |
+
"layer_norm_eps": 1e-05,
|
56 |
+
"max_position_embeddings": 514,
|
57 |
+
"model_type": "roberta",
|
58 |
+
"num_attention_heads": 12,
|
59 |
+
"num_hidden_layers": 12,
|
60 |
+
"pad_token_id": 1,
|
61 |
+
"position_embedding_type": "absolute",
|
62 |
+
"transformers_version": "4.6.1",
|
63 |
+
"type_vocab_size": 1,
|
64 |
+
"use_cache": true,
|
65 |
+
"vocab_size": 50262
|
66 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.9905438520216592,
|
4 |
+
"eval_f1": 0.9003506721215664,
|
5 |
+
"eval_loss": 0.04321206733584404,
|
6 |
+
"eval_mem_cpu_alloc_delta": 149028864,
|
7 |
+
"eval_mem_cpu_peaked_delta": 9793536,
|
8 |
+
"eval_mem_gpu_alloc_delta": 0,
|
9 |
+
"eval_mem_gpu_peaked_delta": 314081280,
|
10 |
+
"eval_precision": 0.8971173444627778,
|
11 |
+
"eval_recall": 0.9036073907517841,
|
12 |
+
"eval_runtime": 34.5441,
|
13 |
+
"eval_samples": 7550,
|
14 |
+
"eval_samples_per_second": 218.561
|
15 |
+
}
|
merges.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 sha256:2322a56610f6b0151e9380411b7ca1b8c5883e983a6dc1e4ecb1adf2cfcd6a66
|
3 |
+
size 496347953
|
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"}, "max_len": 512, "model_max_length": 512, "name_or_path": "roberta-base-bne", "special_tokens_map_file": null, "tokenizer_class": "RobertaTokenizer", "trim_offsets": true}
|
train_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"init_mem_cpu_alloc_delta": -68857856,
|
4 |
+
"init_mem_cpu_peaked_delta": 154255360,
|
5 |
+
"init_mem_gpu_alloc_delta": 497570816,
|
6 |
+
"init_mem_gpu_peaked_delta": 0,
|
7 |
+
"train_mem_cpu_alloc_delta": 2823634944,
|
8 |
+
"train_mem_cpu_peaked_delta": 164388864,
|
9 |
+
"train_mem_gpu_alloc_delta": 1508407296,
|
10 |
+
"train_mem_gpu_peaked_delta": 10039297024,
|
11 |
+
"train_runtime": 1076.7664,
|
12 |
+
"train_samples": 22648,
|
13 |
+
"train_samples_per_second": 3.288
|
14 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9003506721215664,
|
3 |
+
"best_model_checkpoint": "output/roberta-base-bne-capitel-iris-ner/iris_16_0.00005_07-17-23_22-27/checkpoint-3540",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 3540,
|
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": 4e-05,
|
13 |
+
"loss": 0.0969,
|
14 |
+
"step": 708
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.9882810956088692,
|
19 |
+
"eval_f1": 0.8684808352264488,
|
20 |
+
"eval_loss": 0.04088732972741127,
|
21 |
+
"eval_precision": 0.8588910133843213,
|
22 |
+
"eval_recall": 0.8782872226024049,
|
23 |
+
"eval_runtime": 34.6042,
|
24 |
+
"eval_samples_per_second": 218.182,
|
25 |
+
"step": 708
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"learning_rate": 3e-05,
|
30 |
+
"loss": 0.0253,
|
31 |
+
"step": 1416
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.9890666376823051,
|
36 |
+
"eval_f1": 0.8800116352353711,
|
37 |
+
"eval_loss": 0.03929711878299713,
|
38 |
+
"eval_precision": 0.8728601654164262,
|
39 |
+
"eval_recall": 0.8872812591651188,
|
40 |
+
"eval_runtime": 34.2725,
|
41 |
+
"eval_samples_per_second": 220.293,
|
42 |
+
"step": 1416
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"learning_rate": 2e-05,
|
47 |
+
"loss": 0.0117,
|
48 |
+
"step": 2124
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_accuracy": 0.9898768823366665,
|
53 |
+
"eval_f1": 0.892319680514294,
|
54 |
+
"eval_loss": 0.03888658434152603,
|
55 |
+
"eval_precision": 0.8890722049689441,
|
56 |
+
"eval_recall": 0.8955909668589305,
|
57 |
+
"eval_runtime": 34.6426,
|
58 |
+
"eval_samples_per_second": 217.94,
|
59 |
+
"step": 2124
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"learning_rate": 1e-05,
|
64 |
+
"loss": 0.0054,
|
65 |
+
"step": 2832
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"eval_accuracy": 0.9904549227303269,
|
70 |
+
"eval_f1": 0.8978559968885217,
|
71 |
+
"eval_loss": 0.040431126952171326,
|
72 |
+
"eval_precision": 0.893036750483559,
|
73 |
+
"eval_recall": 0.9027275393489099,
|
74 |
+
"eval_runtime": 34.4446,
|
75 |
+
"eval_samples_per_second": 219.192,
|
76 |
+
"step": 2832
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 5.0,
|
80 |
+
"learning_rate": 0.0,
|
81 |
+
"loss": 0.0026,
|
82 |
+
"step": 3540
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 5.0,
|
86 |
+
"eval_accuracy": 0.9905438520216592,
|
87 |
+
"eval_f1": 0.9003506721215664,
|
88 |
+
"eval_loss": 0.04321206733584404,
|
89 |
+
"eval_precision": 0.8971173444627778,
|
90 |
+
"eval_recall": 0.9036073907517841,
|
91 |
+
"eval_runtime": 34.2514,
|
92 |
+
"eval_samples_per_second": 220.429,
|
93 |
+
"step": 3540
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 5.0,
|
97 |
+
"step": 3540,
|
98 |
+
"total_flos": 0,
|
99 |
+
"train_runtime": 1076.7664,
|
100 |
+
"train_samples_per_second": 3.288
|
101 |
+
}
|
102 |
+
],
|
103 |
+
"max_steps": 3540,
|
104 |
+
"num_train_epochs": 5,
|
105 |
+
"total_flos": 0,
|
106 |
+
"trial_name": null,
|
107 |
+
"trial_params": null
|
108 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:372826fd22322afeabb836f01b27229bb024f143adf407e671ef9698d56f638d
|
3 |
+
size 2543
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|