Training in progress, epoch 2
Browse files- model.safetensors +1 -1
- run-0/checkpoint-2284/config.json +44 -0
- run-0/checkpoint-2284/model.safetensors +3 -0
- run-0/checkpoint-2284/optimizer.pt +3 -0
- run-0/checkpoint-2284/rng_state.pth +3 -0
- run-0/checkpoint-2284/scheduler.pt +3 -0
- run-0/checkpoint-2284/special_tokens_map.json +37 -0
- run-0/checkpoint-2284/tokenizer.json +0 -0
- run-0/checkpoint-2284/tokenizer_config.json +57 -0
- run-0/checkpoint-2284/trainer_state.json +68 -0
- run-0/checkpoint-2284/training_args.bin +3 -0
- run-0/checkpoint-2284/vocab.txt +0 -0
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 442514444
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:747d0d0127b2cc769138a9f755104e20e9d47485060ea3fcbf852e8841a2ea6a
|
3 |
size 442514444
|
run-0/checkpoint-2284/config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "klue/bert-base",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"LABEL_0": 0,
|
24 |
+
"LABEL_1": 1,
|
25 |
+
"LABEL_2": 2,
|
26 |
+
"LABEL_3": 3,
|
27 |
+
"LABEL_4": 4,
|
28 |
+
"LABEL_5": 5,
|
29 |
+
"LABEL_6": 6
|
30 |
+
},
|
31 |
+
"layer_norm_eps": 1e-12,
|
32 |
+
"max_position_embeddings": 512,
|
33 |
+
"model_type": "bert",
|
34 |
+
"num_attention_heads": 12,
|
35 |
+
"num_hidden_layers": 12,
|
36 |
+
"pad_token_id": 0,
|
37 |
+
"position_embedding_type": "absolute",
|
38 |
+
"problem_type": "single_label_classification",
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.36.2",
|
41 |
+
"type_vocab_size": 2,
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 32000
|
44 |
+
}
|
run-0/checkpoint-2284/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:747d0d0127b2cc769138a9f755104e20e9d47485060ea3fcbf852e8841a2ea6a
|
3 |
+
size 442514444
|
run-0/checkpoint-2284/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fceb54c7d93677042fb57d88b8280164b064c5f285de715af4e61f8fd88220dc
|
3 |
+
size 885149946
|
run-0/checkpoint-2284/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef0d2cc7a49b7d6245ae7aa4f35880aa5f891d7af87d1dda3caa238e6c6c4829
|
3 |
+
size 14244
|
run-0/checkpoint-2284/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df354d5faf621f6c49a9b18fd39181348871535b9c2e0809d8822b1092cf4671
|
3 |
+
size 1064
|
run-0/checkpoint-2284/special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
run-0/checkpoint-2284/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-2284/tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
run-0/checkpoint-2284/trainer_state.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8415413879849883,
|
3 |
+
"best_model_checkpoint": "test-klue/ynat-hps/run-0/checkpoint-2284",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2284,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.44,
|
13 |
+
"learning_rate": 1.5575177105745416e-05,
|
14 |
+
"loss": 0.7213,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.88,
|
19 |
+
"learning_rate": 1.4080438419973303e-05,
|
20 |
+
"loss": 0.5522,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.0,
|
25 |
+
"eval_f1": 0.8362527412907268,
|
26 |
+
"eval_loss": 0.6280386447906494,
|
27 |
+
"eval_runtime": 12.2023,
|
28 |
+
"eval_samples_per_second": 746.334,
|
29 |
+
"eval_steps_per_second": 2.95,
|
30 |
+
"step": 1142
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.31,
|
34 |
+
"learning_rate": 1.258569973420119e-05,
|
35 |
+
"loss": 0.4071,
|
36 |
+
"step": 1500
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 1.75,
|
40 |
+
"learning_rate": 1.1090961048429078e-05,
|
41 |
+
"loss": 0.4276,
|
42 |
+
"step": 2000
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 2.0,
|
46 |
+
"eval_f1": 0.8415413879849883,
|
47 |
+
"eval_loss": 0.7244753241539001,
|
48 |
+
"eval_runtime": 12.1177,
|
49 |
+
"eval_samples_per_second": 751.545,
|
50 |
+
"eval_steps_per_second": 2.971,
|
51 |
+
"step": 2284
|
52 |
+
}
|
53 |
+
],
|
54 |
+
"logging_steps": 500,
|
55 |
+
"max_steps": 5710,
|
56 |
+
"num_input_tokens_seen": 0,
|
57 |
+
"num_train_epochs": 5,
|
58 |
+
"save_steps": 500,
|
59 |
+
"total_flos": 76342633141200.0,
|
60 |
+
"train_batch_size": 4,
|
61 |
+
"trial_name": null,
|
62 |
+
"trial_params": {
|
63 |
+
"learning_rate": 1.706991579151753e-05,
|
64 |
+
"num_train_epochs": 5,
|
65 |
+
"per_device_train_batch_size": 4,
|
66 |
+
"seed": 2
|
67 |
+
}
|
68 |
+
}
|
run-0/checkpoint-2284/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:185884df1614b0552795213155dd59621bd6ecbfd58643aadc676456a6f4c005
|
3 |
+
size 4728
|
run-0/checkpoint-2284/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|