chizhik
commited on
Commit
·
6dbacd6
1
Parent(s):
a3fb507
initial commit
Browse files- config.json +65 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- trainer_state.json +382 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./Models/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": "LABEL_0",
|
16 |
+
"1": "LABEL_1",
|
17 |
+
"2": "LABEL_2",
|
18 |
+
"3": "LABEL_3",
|
19 |
+
"4": "LABEL_4",
|
20 |
+
"5": "LABEL_5",
|
21 |
+
"6": "LABEL_6",
|
22 |
+
"7": "LABEL_7",
|
23 |
+
"8": "LABEL_8",
|
24 |
+
"9": "LABEL_9",
|
25 |
+
"10": "LABEL_10",
|
26 |
+
"11": "LABEL_11",
|
27 |
+
"12": "LABEL_12",
|
28 |
+
"13": "LABEL_13",
|
29 |
+
"14": "LABEL_14",
|
30 |
+
"15": "LABEL_15"
|
31 |
+
},
|
32 |
+
"initializer_range": 0.02,
|
33 |
+
"intermediate_size": 3072,
|
34 |
+
"label2id": {
|
35 |
+
"LABEL_0": 0,
|
36 |
+
"LABEL_1": 1,
|
37 |
+
"LABEL_10": 10,
|
38 |
+
"LABEL_11": 11,
|
39 |
+
"LABEL_12": 12,
|
40 |
+
"LABEL_13": 13,
|
41 |
+
"LABEL_14": 14,
|
42 |
+
"LABEL_15": 15,
|
43 |
+
"LABEL_2": 2,
|
44 |
+
"LABEL_3": 3,
|
45 |
+
"LABEL_4": 4,
|
46 |
+
"LABEL_5": 5,
|
47 |
+
"LABEL_6": 6,
|
48 |
+
"LABEL_7": 7,
|
49 |
+
"LABEL_8": 8,
|
50 |
+
"LABEL_9": 9
|
51 |
+
},
|
52 |
+
"layer_norm_eps": 1e-05,
|
53 |
+
"max_position_embeddings": 514,
|
54 |
+
"model_type": "roberta",
|
55 |
+
"num_attention_heads": 12,
|
56 |
+
"num_hidden_layers": 12,
|
57 |
+
"pad_token_id": 1,
|
58 |
+
"position_embedding_type": "absolute",
|
59 |
+
"problem_type": "multi_label_classification",
|
60 |
+
"torch_dtype": "float32",
|
61 |
+
"transformers_version": "4.24.0",
|
62 |
+
"type_vocab_size": 1,
|
63 |
+
"use_cache": true,
|
64 |
+
"vocab_size": 50262
|
65 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa17b658ff6291efbf0919babd01f5eec92da9643b39758cdaa3b6db9476e1db
|
3 |
+
size 997361565
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41adba97b7f678cbf4f5086d500f1346c7fa47d372988e0f0b6d5a52361a1d50
|
3 |
+
size 498694189
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a9d4831f96a909c7446a40c7bdd8e8f202f41f3fc50a85bbf9b303cfdfcd011
|
3 |
+
size 14567
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c73139dd76e847347cf52b339302ca357b5775c05b771f462b21d2da0fdbee2
|
3 |
+
size 623
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"cls_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"eos_token": {
|
20 |
+
"__type": "AddedToken",
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"errors": "replace",
|
28 |
+
"mask_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "<mask>",
|
31 |
+
"lstrip": true,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"max_len": 512,
|
37 |
+
"name_or_path": "Models/roberta-base-bne",
|
38 |
+
"pad_token": {
|
39 |
+
"__type": "AddedToken",
|
40 |
+
"content": "<pad>",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": true,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"sep_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "</s>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"special_tokens_map_file": null,
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": {
|
58 |
+
"__type": "AddedToken",
|
59 |
+
"content": "<unk>",
|
60 |
+
"lstrip": false,
|
61 |
+
"normalized": true,
|
62 |
+
"rstrip": false,
|
63 |
+
"single_word": false
|
64 |
+
}
|
65 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,382 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6491296227815271,
|
3 |
+
"best_model_checkpoint": "./CARES/checkpoints/roberta-stratified/run-0/checkpoint-3266",
|
4 |
+
"epoch": 23.163120567375888,
|
5 |
+
"global_step": 3266,
|
6 |
+
"is_hyper_param_search": true,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.01,
|
12 |
+
"eval_loss": 0.3462072014808655,
|
13 |
+
"eval_macro_f1": 0.0007381889763779527,
|
14 |
+
"eval_macro_precision": 0.0625,
|
15 |
+
"eval_macro_recall": 0.0003712871287128713,
|
16 |
+
"eval_micro_f1": 0.0039447731755424065,
|
17 |
+
"eval_micro_precision": 1.0,
|
18 |
+
"eval_micro_recall": 0.001976284584980237,
|
19 |
+
"eval_runtime": 2.8803,
|
20 |
+
"eval_samples_per_second": 337.116,
|
21 |
+
"eval_steps_per_second": 10.763,
|
22 |
+
"step": 142
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.01,
|
26 |
+
"eval_loss": 0.26299169659614563,
|
27 |
+
"eval_macro_f1": 0.03133608815426997,
|
28 |
+
"eval_macro_precision": 0.051470588235294115,
|
29 |
+
"eval_macro_recall": 0.022524752475247524,
|
30 |
+
"eval_micro_f1": 0.20931569867740082,
|
31 |
+
"eval_micro_precision": 0.8235294117647058,
|
32 |
+
"eval_micro_recall": 0.11989459815546773,
|
33 |
+
"eval_runtime": 2.7712,
|
34 |
+
"eval_samples_per_second": 350.396,
|
35 |
+
"eval_steps_per_second": 11.187,
|
36 |
+
"step": 284
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.02,
|
40 |
+
"eval_loss": 0.2253277599811554,
|
41 |
+
"eval_macro_f1": 0.06167745523885891,
|
42 |
+
"eval_macro_precision": 0.16397973284200829,
|
43 |
+
"eval_macro_recall": 0.06444494429328504,
|
44 |
+
"eval_micro_f1": 0.43727272727272726,
|
45 |
+
"eval_micro_precision": 0.7052785923753666,
|
46 |
+
"eval_micro_recall": 0.3168642951251647,
|
47 |
+
"eval_runtime": 2.7754,
|
48 |
+
"eval_samples_per_second": 349.86,
|
49 |
+
"eval_steps_per_second": 11.17,
|
50 |
+
"step": 426
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 3.55,
|
54 |
+
"learning_rate": 1.858287403029302e-05,
|
55 |
+
"loss": 0.3344,
|
56 |
+
"step": 500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.03,
|
60 |
+
"eval_loss": 0.19568884372711182,
|
61 |
+
"eval_macro_f1": 0.19533405609363325,
|
62 |
+
"eval_macro_precision": 0.3105566636324695,
|
63 |
+
"eval_macro_recall": 0.1838257881936085,
|
64 |
+
"eval_micro_f1": 0.6221161495624502,
|
65 |
+
"eval_micro_precision": 0.785140562248996,
|
66 |
+
"eval_micro_recall": 0.5151515151515151,
|
67 |
+
"eval_runtime": 2.775,
|
68 |
+
"eval_samples_per_second": 349.909,
|
69 |
+
"eval_steps_per_second": 11.171,
|
70 |
+
"step": 568
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 5.04,
|
74 |
+
"eval_loss": 0.16411657631397247,
|
75 |
+
"eval_macro_f1": 0.2724936969098707,
|
76 |
+
"eval_macro_precision": 0.3798299682715689,
|
77 |
+
"eval_macro_recall": 0.24456296636870606,
|
78 |
+
"eval_micro_f1": 0.6832491255343957,
|
79 |
+
"eval_micro_precision": 0.833175355450237,
|
80 |
+
"eval_micro_recall": 0.5790513833992095,
|
81 |
+
"eval_runtime": 2.7735,
|
82 |
+
"eval_samples_per_second": 350.097,
|
83 |
+
"eval_steps_per_second": 11.177,
|
84 |
+
"step": 710
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.04,
|
88 |
+
"eval_loss": 0.15434952080249786,
|
89 |
+
"eval_macro_f1": 0.33512731711181853,
|
90 |
+
"eval_macro_precision": 0.42023284164245034,
|
91 |
+
"eval_macro_recall": 0.31527094611085327,
|
92 |
+
"eval_micro_f1": 0.7207672445592034,
|
93 |
+
"eval_micro_precision": 0.8189438390611903,
|
94 |
+
"eval_micro_recall": 0.6436100131752306,
|
95 |
+
"eval_runtime": 2.7765,
|
96 |
+
"eval_samples_per_second": 349.72,
|
97 |
+
"eval_steps_per_second": 11.165,
|
98 |
+
"step": 852
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.05,
|
102 |
+
"eval_loss": 0.14012500643730164,
|
103 |
+
"eval_macro_f1": 0.3798067714294707,
|
104 |
+
"eval_macro_precision": 0.5469114307081249,
|
105 |
+
"eval_macro_recall": 0.3317304014614234,
|
106 |
+
"eval_micro_f1": 0.7399624765478424,
|
107 |
+
"eval_micro_precision": 0.8596338273757629,
|
108 |
+
"eval_micro_recall": 0.6495388669301713,
|
109 |
+
"eval_runtime": 2.774,
|
110 |
+
"eval_samples_per_second": 350.033,
|
111 |
+
"eval_steps_per_second": 11.175,
|
112 |
+
"step": 994
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 7.09,
|
116 |
+
"learning_rate": 3.0452387239092086e-05,
|
117 |
+
"loss": 0.1403,
|
118 |
+
"step": 1000
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 8.06,
|
122 |
+
"eval_loss": 0.1425222009420395,
|
123 |
+
"eval_macro_f1": 0.4279380705267567,
|
124 |
+
"eval_macro_precision": 0.603624913309443,
|
125 |
+
"eval_macro_recall": 0.3703454980587147,
|
126 |
+
"eval_micro_f1": 0.7544954128440367,
|
127 |
+
"eval_micro_precision": 0.851698425849213,
|
128 |
+
"eval_micro_recall": 0.6772068511198946,
|
129 |
+
"eval_runtime": 2.7729,
|
130 |
+
"eval_samples_per_second": 350.179,
|
131 |
+
"eval_steps_per_second": 11.18,
|
132 |
+
"step": 1136
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 9.06,
|
136 |
+
"eval_loss": 0.12965930998325348,
|
137 |
+
"eval_macro_f1": 0.516908938978679,
|
138 |
+
"eval_macro_precision": 0.6952135806026781,
|
139 |
+
"eval_macro_recall": 0.4441065897269686,
|
140 |
+
"eval_micro_f1": 0.7703488372093023,
|
141 |
+
"eval_micro_precision": 0.8589951377633711,
|
142 |
+
"eval_micro_recall": 0.6982872200263505,
|
143 |
+
"eval_runtime": 2.7725,
|
144 |
+
"eval_samples_per_second": 350.226,
|
145 |
+
"eval_steps_per_second": 11.181,
|
146 |
+
"step": 1278
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 10.07,
|
150 |
+
"eval_loss": 0.12852537631988525,
|
151 |
+
"eval_macro_f1": 0.5388984906238257,
|
152 |
+
"eval_macro_precision": 0.7130990451123878,
|
153 |
+
"eval_macro_recall": 0.4711434333008039,
|
154 |
+
"eval_micro_f1": 0.7730547550432276,
|
155 |
+
"eval_micro_precision": 0.8529411764705882,
|
156 |
+
"eval_micro_recall": 0.7068511198945981,
|
157 |
+
"eval_runtime": 2.7737,
|
158 |
+
"eval_samples_per_second": 350.077,
|
159 |
+
"eval_steps_per_second": 11.176,
|
160 |
+
"step": 1420
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 10.64,
|
164 |
+
"learning_rate": 2.929008238263819e-05,
|
165 |
+
"loss": 0.0558,
|
166 |
+
"step": 1500
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 11.08,
|
170 |
+
"eval_loss": 0.13507980108261108,
|
171 |
+
"eval_macro_f1": 0.5653547754610186,
|
172 |
+
"eval_macro_precision": 0.697025101599949,
|
173 |
+
"eval_macro_recall": 0.49809191604893205,
|
174 |
+
"eval_micro_f1": 0.7797808412866738,
|
175 |
+
"eval_micro_precision": 0.8413424866514111,
|
176 |
+
"eval_micro_recall": 0.7266139657444005,
|
177 |
+
"eval_runtime": 2.7736,
|
178 |
+
"eval_samples_per_second": 350.083,
|
179 |
+
"eval_steps_per_second": 11.177,
|
180 |
+
"step": 1562
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 12.09,
|
184 |
+
"eval_loss": 0.1355280876159668,
|
185 |
+
"eval_macro_f1": 0.5794821565833095,
|
186 |
+
"eval_macro_precision": 0.6818697605893614,
|
187 |
+
"eval_macro_recall": 0.5236900724860433,
|
188 |
+
"eval_micro_f1": 0.7849877236057524,
|
189 |
+
"eval_micro_precision": 0.8394598649662416,
|
190 |
+
"eval_micro_recall": 0.7371541501976284,
|
191 |
+
"eval_runtime": 2.7759,
|
192 |
+
"eval_samples_per_second": 349.801,
|
193 |
+
"eval_steps_per_second": 11.168,
|
194 |
+
"step": 1704
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 13.09,
|
198 |
+
"eval_loss": 0.13659390807151794,
|
199 |
+
"eval_macro_f1": 0.5891915194817472,
|
200 |
+
"eval_macro_precision": 0.69343533514632,
|
201 |
+
"eval_macro_recall": 0.5302292848265341,
|
202 |
+
"eval_micro_f1": 0.7858642407277815,
|
203 |
+
"eval_micro_precision": 0.8380597014925373,
|
204 |
+
"eval_micro_recall": 0.7397891963109354,
|
205 |
+
"eval_runtime": 2.7739,
|
206 |
+
"eval_samples_per_second": 350.043,
|
207 |
+
"eval_steps_per_second": 11.175,
|
208 |
+
"step": 1846
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 14.1,
|
212 |
+
"eval_loss": 0.13488434255123138,
|
213 |
+
"eval_macro_f1": 0.5900914578255574,
|
214 |
+
"eval_macro_precision": 0.6881746937300715,
|
215 |
+
"eval_macro_recall": 0.5327336547593478,
|
216 |
+
"eval_micro_f1": 0.7906326459279972,
|
217 |
+
"eval_micro_precision": 0.842144452717796,
|
218 |
+
"eval_micro_recall": 0.7450592885375494,
|
219 |
+
"eval_runtime": 2.772,
|
220 |
+
"eval_samples_per_second": 350.292,
|
221 |
+
"eval_steps_per_second": 11.183,
|
222 |
+
"step": 1988
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 14.18,
|
226 |
+
"learning_rate": 2.8127777526184293e-05,
|
227 |
+
"loss": 0.0229,
|
228 |
+
"step": 2000
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 15.11,
|
232 |
+
"eval_loss": 0.14160068333148956,
|
233 |
+
"eval_macro_f1": 0.5920064296505824,
|
234 |
+
"eval_macro_precision": 0.6848089552512611,
|
235 |
+
"eval_macro_recall": 0.5382146732964487,
|
236 |
+
"eval_micro_f1": 0.7904066736183525,
|
237 |
+
"eval_micro_precision": 0.8366445916114791,
|
238 |
+
"eval_micro_recall": 0.7490118577075099,
|
239 |
+
"eval_runtime": 2.7738,
|
240 |
+
"eval_samples_per_second": 350.061,
|
241 |
+
"eval_steps_per_second": 11.176,
|
242 |
+
"step": 2130
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 16.11,
|
246 |
+
"eval_loss": 0.14674818515777588,
|
247 |
+
"eval_macro_f1": 0.5928173166365653,
|
248 |
+
"eval_macro_precision": 0.6894481117094009,
|
249 |
+
"eval_macro_recall": 0.5355030217646541,
|
250 |
+
"eval_micro_f1": 0.7838118298166724,
|
251 |
+
"eval_micro_precision": 0.8252002913328478,
|
252 |
+
"eval_micro_recall": 0.7463768115942029,
|
253 |
+
"eval_runtime": 2.7753,
|
254 |
+
"eval_samples_per_second": 349.871,
|
255 |
+
"eval_steps_per_second": 11.17,
|
256 |
+
"step": 2272
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 17.12,
|
260 |
+
"eval_loss": 0.15975715219974518,
|
261 |
+
"eval_macro_f1": 0.6260279452973108,
|
262 |
+
"eval_macro_precision": 0.7038398537082291,
|
263 |
+
"eval_macro_recall": 0.5866152515992036,
|
264 |
+
"eval_micro_f1": 0.7704974271012006,
|
265 |
+
"eval_micro_precision": 0.80386542591267,
|
266 |
+
"eval_micro_recall": 0.7397891963109354,
|
267 |
+
"eval_runtime": 2.773,
|
268 |
+
"eval_samples_per_second": 350.168,
|
269 |
+
"eval_steps_per_second": 11.179,
|
270 |
+
"step": 2414
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 17.73,
|
274 |
+
"learning_rate": 2.6965472669730396e-05,
|
275 |
+
"loss": 0.0137,
|
276 |
+
"step": 2500
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 18.13,
|
280 |
+
"eval_loss": 0.15081025660037994,
|
281 |
+
"eval_macro_f1": 0.6271302596876451,
|
282 |
+
"eval_macro_precision": 0.7314709578369518,
|
283 |
+
"eval_macro_recall": 0.5704921787075566,
|
284 |
+
"eval_micro_f1": 0.7809989521480964,
|
285 |
+
"eval_micro_precision": 0.8312267657992565,
|
286 |
+
"eval_micro_recall": 0.7364953886693018,
|
287 |
+
"eval_runtime": 2.7721,
|
288 |
+
"eval_samples_per_second": 350.282,
|
289 |
+
"eval_steps_per_second": 11.183,
|
290 |
+
"step": 2556
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 19.13,
|
294 |
+
"eval_loss": 0.14972703158855438,
|
295 |
+
"eval_macro_f1": 0.5953077373311189,
|
296 |
+
"eval_macro_precision": 0.6771131830689183,
|
297 |
+
"eval_macro_recall": 0.5419002355296083,
|
298 |
+
"eval_micro_f1": 0.7900552486187846,
|
299 |
+
"eval_micro_precision": 0.8301886792452831,
|
300 |
+
"eval_micro_recall": 0.7536231884057971,
|
301 |
+
"eval_runtime": 2.7725,
|
302 |
+
"eval_samples_per_second": 350.229,
|
303 |
+
"eval_steps_per_second": 11.181,
|
304 |
+
"step": 2698
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 20.14,
|
308 |
+
"eval_loss": 0.16402311623096466,
|
309 |
+
"eval_macro_f1": 0.5892530505072842,
|
310 |
+
"eval_macro_precision": 0.6727972959139897,
|
311 |
+
"eval_macro_recall": 0.5367187180351005,
|
312 |
+
"eval_micro_f1": 0.779319916724497,
|
313 |
+
"eval_micro_precision": 0.8233137829912024,
|
314 |
+
"eval_micro_recall": 0.7397891963109354,
|
315 |
+
"eval_runtime": 2.7746,
|
316 |
+
"eval_samples_per_second": 349.963,
|
317 |
+
"eval_steps_per_second": 11.173,
|
318 |
+
"step": 2840
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 21.15,
|
322 |
+
"eval_loss": 0.16335928440093994,
|
323 |
+
"eval_macro_f1": 0.6332863501223459,
|
324 |
+
"eval_macro_precision": 0.7578187629295322,
|
325 |
+
"eval_macro_recall": 0.5685989504723161,
|
326 |
+
"eval_micro_f1": 0.7924791086350974,
|
327 |
+
"eval_micro_precision": 0.8404726735598228,
|
328 |
+
"eval_micro_recall": 0.7496706192358367,
|
329 |
+
"eval_runtime": 2.7725,
|
330 |
+
"eval_samples_per_second": 350.229,
|
331 |
+
"eval_steps_per_second": 11.181,
|
332 |
+
"step": 2982
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 21.28,
|
336 |
+
"learning_rate": 2.58031678132765e-05,
|
337 |
+
"loss": 0.011,
|
338 |
+
"step": 3000
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 22.16,
|
342 |
+
"eval_loss": 0.16375195980072021,
|
343 |
+
"eval_macro_f1": 0.6343242676719218,
|
344 |
+
"eval_macro_precision": 0.7473720060268463,
|
345 |
+
"eval_macro_recall": 0.5714537925969617,
|
346 |
+
"eval_micro_f1": 0.7909878682842287,
|
347 |
+
"eval_micro_precision": 0.8346744696415508,
|
348 |
+
"eval_micro_recall": 0.7516469038208169,
|
349 |
+
"eval_runtime": 2.7735,
|
350 |
+
"eval_samples_per_second": 350.093,
|
351 |
+
"eval_steps_per_second": 11.177,
|
352 |
+
"step": 3124
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 23.16,
|
356 |
+
"eval_loss": 0.16090567409992218,
|
357 |
+
"eval_macro_f1": 0.6491296227815271,
|
358 |
+
"eval_macro_precision": 0.7487080551943797,
|
359 |
+
"eval_macro_recall": 0.5927079340096836,
|
360 |
+
"eval_micro_f1": 0.7961299239806496,
|
361 |
+
"eval_micro_precision": 0.8372093023255814,
|
362 |
+
"eval_micro_recall": 0.758893280632411,
|
363 |
+
"eval_runtime": 2.7735,
|
364 |
+
"eval_samples_per_second": 350.094,
|
365 |
+
"eval_steps_per_second": 11.177,
|
366 |
+
"step": 3266
|
367 |
+
}
|
368 |
+
],
|
369 |
+
"max_steps": 14100,
|
370 |
+
"num_train_epochs": 100,
|
371 |
+
"total_flos": 1.2446273222900736e+16,
|
372 |
+
"trial_name": null,
|
373 |
+
"trial_params": {
|
374 |
+
"adam_epsilon": 6.356433345691159e-10,
|
375 |
+
"learning_rate": 3.084757089028641e-05,
|
376 |
+
"per_device_eval_batch_size": 32,
|
377 |
+
"per_device_train_batch_size": 16,
|
378 |
+
"seed": 326,
|
379 |
+
"warmup_steps": 830,
|
380 |
+
"weight_decay": 0.0009910374448883887
|
381 |
+
}
|
382 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8b7f323c1b5dbfa731b4c4816647448376c6ed3b12e43aeda40bcbd1093c542
|
3 |
+
size 3439
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|