CCChenRyan
commited on
Commit
•
5435f4a
1
Parent(s):
87d1784
Training in progress, epoch 3
Browse files- model.safetensors +1 -1
- run-0/checkpoint-1070/config.json +25 -0
- run-0/checkpoint-1070/model.safetensors +3 -0
- run-0/checkpoint-1070/optimizer.pt +3 -0
- run-0/checkpoint-1070/rng_state.pth +3 -0
- run-0/checkpoint-1070/scheduler.pt +3 -0
- run-0/checkpoint-1070/special_tokens_map.json +7 -0
- run-0/checkpoint-1070/tokenizer.json +0 -0
- run-0/checkpoint-1070/tokenizer_config.json +55 -0
- run-0/checkpoint-1070/trainer_state.json +56 -0
- run-0/checkpoint-1070/training_args.bin +3 -0
- run-0/checkpoint-1070/vocab.txt +0 -0
- run-0/checkpoint-1605/config.json +25 -0
- run-0/checkpoint-1605/model.safetensors +3 -0
- run-0/checkpoint-1605/optimizer.pt +3 -0
- run-0/checkpoint-1605/rng_state.pth +3 -0
- run-0/checkpoint-1605/scheduler.pt +3 -0
- run-0/checkpoint-1605/special_tokens_map.json +7 -0
- run-0/checkpoint-1605/tokenizer.json +0 -0
- run-0/checkpoint-1605/tokenizer_config.json +55 -0
- run-0/checkpoint-1605/trainer_state.json +71 -0
- run-0/checkpoint-1605/training_args.bin +3 -0
- run-0/checkpoint-1605/vocab.txt +0 -0
- run-0/checkpoint-535/config.json +25 -0
- run-0/checkpoint-535/model.safetensors +3 -0
- run-0/checkpoint-535/optimizer.pt +3 -0
- run-0/checkpoint-535/rng_state.pth +3 -0
- run-0/checkpoint-535/scheduler.pt +3 -0
- run-0/checkpoint-535/special_tokens_map.json +7 -0
- run-0/checkpoint-535/tokenizer.json +0 -0
- run-0/checkpoint-535/tokenizer_config.json +55 -0
- run-0/checkpoint-535/trainer_state.json +41 -0
- run-0/checkpoint-535/training_args.bin +3 -0
- run-0/checkpoint-535/vocab.txt +0 -0
- runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703298041.17d63b357dd6.603.2 +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be399b98f7c8ae3edf98046e915680a0ccecc7fac003892c545ee8155074ef7e
|
3 |
size 267832560
|
run-0/checkpoint-1070/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.36.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-0/checkpoint-1070/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53be7dc730d3c3b16ab672691f5214324a2b273b8d34957f68abc1aa8100c1dd
|
3 |
+
size 267832560
|
run-0/checkpoint-1070/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b34b67158a00d14bc87de8600f84eee2892bbf1df9c5919f52ab43b13defabdb
|
3 |
+
size 535727290
|
run-0/checkpoint-1070/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d527cf92603e2eb07dcb6bdf4d93b38e8c445aa68d8a318a2783f700607f251f
|
3 |
+
size 14244
|
run-0/checkpoint-1070/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f1229728cf993724b8881f21bd1a4cf6cd591df7f0056c66160b41224e2d3c6
|
3 |
+
size 1064
|
run-0/checkpoint-1070/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-0/checkpoint-1070/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-1070/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-0/checkpoint-1070/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5113483885735861,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1070",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1070,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.93,
|
13 |
+
"learning_rate": 2.6974691318652314e-05,
|
14 |
+
"loss": 0.5224,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_loss": 0.45828381180763245,
|
20 |
+
"eval_matthews_correlation": 0.49232077048388906,
|
21 |
+
"eval_runtime": 0.7395,
|
22 |
+
"eval_samples_per_second": 1410.5,
|
23 |
+
"eval_steps_per_second": 89.255,
|
24 |
+
"step": 535
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.87,
|
28 |
+
"learning_rate": 1.4768948640529096e-05,
|
29 |
+
"loss": 0.314,
|
30 |
+
"step": 1000
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_loss": 0.49012431502342224,
|
35 |
+
"eval_matthews_correlation": 0.5113483885735861,
|
36 |
+
"eval_runtime": 0.7314,
|
37 |
+
"eval_samples_per_second": 1425.94,
|
38 |
+
"eval_steps_per_second": 90.232,
|
39 |
+
"step": 1070
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 500,
|
43 |
+
"max_steps": 1605,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 3,
|
46 |
+
"save_steps": 500,
|
47 |
+
"total_flos": 86125542058992.0,
|
48 |
+
"train_batch_size": 16,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": {
|
51 |
+
"learning_rate": 3.918043399677554e-05,
|
52 |
+
"num_train_epochs": 3,
|
53 |
+
"per_device_train_batch_size": 16,
|
54 |
+
"seed": 35
|
55 |
+
}
|
56 |
+
}
|
run-0/checkpoint-1070/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:275f1d68a8ef32b480ebf8aa4b71dc84bc91a96440c4262c169a2b08dba67dca
|
3 |
+
size 4792
|
run-0/checkpoint-1070/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-1605/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.36.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-0/checkpoint-1605/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be399b98f7c8ae3edf98046e915680a0ccecc7fac003892c545ee8155074ef7e
|
3 |
+
size 267832560
|
run-0/checkpoint-1605/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4bacb3548d393ae92b1d8d14e64be2c491e36355ebc2e0bcf5ff7682e57f794
|
3 |
+
size 535727290
|
run-0/checkpoint-1605/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3ab7b3ce88f9c957bf9736593e286b037c5f25d26d57e508c5cbc5392499cd3
|
3 |
+
size 14244
|
run-0/checkpoint-1605/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:731817150ad45e75c8216fa81ed1228044d09ed4879a51125bad5b003222dda5
|
3 |
+
size 1064
|
run-0/checkpoint-1605/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-0/checkpoint-1605/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-1605/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-0/checkpoint-1605/trainer_state.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5278612142968102,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1605",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1605,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.93,
|
13 |
+
"learning_rate": 2.6974691318652314e-05,
|
14 |
+
"loss": 0.5224,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_loss": 0.45828381180763245,
|
20 |
+
"eval_matthews_correlation": 0.49232077048388906,
|
21 |
+
"eval_runtime": 0.7395,
|
22 |
+
"eval_samples_per_second": 1410.5,
|
23 |
+
"eval_steps_per_second": 89.255,
|
24 |
+
"step": 535
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.87,
|
28 |
+
"learning_rate": 1.4768948640529096e-05,
|
29 |
+
"loss": 0.314,
|
30 |
+
"step": 1000
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_loss": 0.49012431502342224,
|
35 |
+
"eval_matthews_correlation": 0.5113483885735861,
|
36 |
+
"eval_runtime": 0.7314,
|
37 |
+
"eval_samples_per_second": 1425.94,
|
38 |
+
"eval_steps_per_second": 90.232,
|
39 |
+
"step": 1070
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.8,
|
43 |
+
"learning_rate": 2.563205962405876e-06,
|
44 |
+
"loss": 0.1896,
|
45 |
+
"step": 1500
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.0,
|
49 |
+
"eval_loss": 0.680816113948822,
|
50 |
+
"eval_matthews_correlation": 0.5278612142968102,
|
51 |
+
"eval_runtime": 0.7451,
|
52 |
+
"eval_samples_per_second": 1399.731,
|
53 |
+
"eval_steps_per_second": 88.574,
|
54 |
+
"step": 1605
|
55 |
+
}
|
56 |
+
],
|
57 |
+
"logging_steps": 500,
|
58 |
+
"max_steps": 1605,
|
59 |
+
"num_input_tokens_seen": 0,
|
60 |
+
"num_train_epochs": 3,
|
61 |
+
"save_steps": 500,
|
62 |
+
"total_flos": 129011603648484.0,
|
63 |
+
"train_batch_size": 16,
|
64 |
+
"trial_name": null,
|
65 |
+
"trial_params": {
|
66 |
+
"learning_rate": 3.918043399677554e-05,
|
67 |
+
"num_train_epochs": 3,
|
68 |
+
"per_device_train_batch_size": 16,
|
69 |
+
"seed": 35
|
70 |
+
}
|
71 |
+
}
|
run-0/checkpoint-1605/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:275f1d68a8ef32b480ebf8aa4b71dc84bc91a96440c4262c169a2b08dba67dca
|
3 |
+
size 4792
|
run-0/checkpoint-1605/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-535/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.36.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-0/checkpoint-535/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:786715727f73289331eeaae75f1364c88e3837b1323e397cad1ec669e257ce17
|
3 |
+
size 267832560
|
run-0/checkpoint-535/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:795048860807a176255c9d05e22bef2a45617f45beaab4f7ef3f578cbfb8e3b7
|
3 |
+
size 535727290
|
run-0/checkpoint-535/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:985e3a52d6723d012b69041a0e4ac84bb65c0a8ccacd3181abad7951ab4e0111
|
3 |
+
size 14244
|
run-0/checkpoint-535/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9325ce93128e8136461c514b9afcaf3dee2f6f40ee36ed0ef434dfe71679584
|
3 |
+
size 1064
|
run-0/checkpoint-535/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-0/checkpoint-535/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-535/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-0/checkpoint-535/trainer_state.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.49232077048388906,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-535",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 535,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.93,
|
13 |
+
"learning_rate": 2.6974691318652314e-05,
|
14 |
+
"loss": 0.5224,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_loss": 0.45828381180763245,
|
20 |
+
"eval_matthews_correlation": 0.49232077048388906,
|
21 |
+
"eval_runtime": 0.7395,
|
22 |
+
"eval_samples_per_second": 1410.5,
|
23 |
+
"eval_steps_per_second": 89.255,
|
24 |
+
"step": 535
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"logging_steps": 500,
|
28 |
+
"max_steps": 1605,
|
29 |
+
"num_input_tokens_seen": 0,
|
30 |
+
"num_train_epochs": 3,
|
31 |
+
"save_steps": 500,
|
32 |
+
"total_flos": 43246466054976.0,
|
33 |
+
"train_batch_size": 16,
|
34 |
+
"trial_name": null,
|
35 |
+
"trial_params": {
|
36 |
+
"learning_rate": 3.918043399677554e-05,
|
37 |
+
"num_train_epochs": 3,
|
38 |
+
"per_device_train_batch_size": 16,
|
39 |
+
"seed": 35
|
40 |
+
}
|
41 |
+
}
|
run-0/checkpoint-535/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:275f1d68a8ef32b480ebf8aa4b71dc84bc91a96440c4262c169a2b08dba67dca
|
3 |
+
size 4792
|
run-0/checkpoint-535/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703298041.17d63b357dd6.603.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5a17a350f8a100b5c043ff5f102bbdca36730b17c1e61020c4607f0912f7edb
|
3 |
+
size 6176
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:275f1d68a8ef32b480ebf8aa4b71dc84bc91a96440c4262c169a2b08dba67dca
|
3 |
size 4792
|