Training in progress, epoch 3
Browse files- model.safetensors +1 -1
- run-1/checkpoint-1070/config.json +25 -0
- run-1/checkpoint-1070/model.safetensors +3 -0
- run-1/checkpoint-1070/optimizer.pt +3 -0
- run-1/checkpoint-1070/rng_state.pth +3 -0
- run-1/checkpoint-1070/scheduler.pt +3 -0
- run-1/checkpoint-1070/special_tokens_map.json +7 -0
- run-1/checkpoint-1070/tokenizer.json +0 -0
- run-1/checkpoint-1070/tokenizer_config.json +55 -0
- run-1/checkpoint-1070/trainer_state.json +56 -0
- run-1/checkpoint-1070/training_args.bin +3 -0
- run-1/checkpoint-1070/vocab.txt +0 -0
- run-1/checkpoint-1605/config.json +25 -0
- run-1/checkpoint-1605/model.safetensors +3 -0
- run-1/checkpoint-1605/optimizer.pt +3 -0
- run-1/checkpoint-1605/rng_state.pth +3 -0
- run-1/checkpoint-1605/scheduler.pt +3 -0
- run-1/checkpoint-1605/special_tokens_map.json +7 -0
- run-1/checkpoint-1605/tokenizer.json +0 -0
- run-1/checkpoint-1605/tokenizer_config.json +55 -0
- run-1/checkpoint-1605/trainer_state.json +71 -0
- run-1/checkpoint-1605/training_args.bin +3 -0
- run-1/checkpoint-1605/vocab.txt +0 -0
- run-1/checkpoint-535/config.json +25 -0
- run-1/checkpoint-535/model.safetensors +3 -0
- run-1/checkpoint-535/optimizer.pt +3 -0
- run-1/checkpoint-535/rng_state.pth +3 -0
- run-1/checkpoint-535/scheduler.pt +3 -0
- run-1/checkpoint-535/special_tokens_map.json +7 -0
- run-1/checkpoint-535/tokenizer.json +0 -0
- run-1/checkpoint-535/tokenizer_config.json +55 -0
- run-1/checkpoint-535/trainer_state.json +41 -0
- run-1/checkpoint-535/training_args.bin +3 -0
- run-1/checkpoint-535/vocab.txt +0 -0
- runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703298290.48296f50e732.508.2 +2 -2
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:f0d0caa0deb1b519e78b52e713da9d8c6abd46aa1cddba88b7c36b730eb38257
|
3 |
size 267832560
|
run-1/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-1/checkpoint-1070/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24389e4d1bd1ae3b9e71e5a3fb56fe4755f9bdd928e61c9b580b6852030e1bb6
|
3 |
+
size 267832560
|
run-1/checkpoint-1070/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1629a2c6eef7ad7247c0ec849dda657d7e467ef22ed0601a1aa8ed67366d876b
|
3 |
+
size 535727290
|
run-1/checkpoint-1070/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2acddda86d531697dfc287d92ffeeba8004b7269a3fdba85711eb70ca125f5d2
|
3 |
+
size 14308
|
run-1/checkpoint-1070/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acb8041fe40897d36e9b5a587128692ebca1933df9bffc0611ffd136d01f76a1
|
3 |
+
size 1064
|
run-1/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-1/checkpoint-1070/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/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-1/checkpoint-1070/trainer_state.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.48170038113970914,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 4.894237945372658e-05,
|
14 |
+
"loss": 0.5408,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_loss": 0.48756271600723267,
|
20 |
+
"eval_matthews_correlation": 0.4371151083758757,
|
21 |
+
"eval_runtime": 0.7652,
|
22 |
+
"eval_samples_per_second": 1363.003,
|
23 |
+
"eval_steps_per_second": 86.249,
|
24 |
+
"step": 535
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.87,
|
28 |
+
"learning_rate": 3.769125774022621e-05,
|
29 |
+
"loss": 0.3186,
|
30 |
+
"step": 1000
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_loss": 0.4699440896511078,
|
35 |
+
"eval_matthews_correlation": 0.48170038113970914,
|
36 |
+
"eval_runtime": 0.7508,
|
37 |
+
"eval_samples_per_second": 1389.228,
|
38 |
+
"eval_steps_per_second": 87.909,
|
39 |
+
"step": 1070
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 500,
|
43 |
+
"max_steps": 2675,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 5,
|
46 |
+
"save_steps": 500,
|
47 |
+
"total_flos": 85640690681880.0,
|
48 |
+
"train_batch_size": 16,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": {
|
51 |
+
"learning_rate": 6.019350116722694e-05,
|
52 |
+
"num_train_epochs": 5,
|
53 |
+
"per_device_train_batch_size": 16,
|
54 |
+
"seed": 13
|
55 |
+
}
|
56 |
+
}
|
run-1/checkpoint-1070/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf249ce55272fbde68001c7053fc83d7d8152ef8c83e36c8c055bcdcbd21b4af
|
3 |
+
size 4792
|
run-1/checkpoint-1070/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/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-1/checkpoint-1605/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0d0caa0deb1b519e78b52e713da9d8c6abd46aa1cddba88b7c36b730eb38257
|
3 |
+
size 267832560
|
run-1/checkpoint-1605/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6784d11ac8e3dcc467a208ba8a7f7b6a536df8b42e6559775bfb4fa9787fc145
|
3 |
+
size 535727290
|
run-1/checkpoint-1605/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f81496d2d2f600acf32b0444c99c3f213144677320ec4f3ac7f32e86ddece358
|
3 |
+
size 14308
|
run-1/checkpoint-1605/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83103f1ff5155c7a40e0f207a7d48783cd77ee351408f11896715d31c858d2d9
|
3 |
+
size 1064
|
run-1/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-1/checkpoint-1605/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/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-1/checkpoint-1605/trainer_state.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.48170038113970914,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1070",
|
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": 4.894237945372658e-05,
|
14 |
+
"loss": 0.5408,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_loss": 0.48756271600723267,
|
20 |
+
"eval_matthews_correlation": 0.4371151083758757,
|
21 |
+
"eval_runtime": 0.7652,
|
22 |
+
"eval_samples_per_second": 1363.003,
|
23 |
+
"eval_steps_per_second": 86.249,
|
24 |
+
"step": 535
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.87,
|
28 |
+
"learning_rate": 3.769125774022621e-05,
|
29 |
+
"loss": 0.3186,
|
30 |
+
"step": 1000
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_loss": 0.4699440896511078,
|
35 |
+
"eval_matthews_correlation": 0.48170038113970914,
|
36 |
+
"eval_runtime": 0.7508,
|
37 |
+
"eval_samples_per_second": 1389.228,
|
38 |
+
"eval_steps_per_second": 87.909,
|
39 |
+
"step": 1070
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.8,
|
43 |
+
"learning_rate": 2.644013602672585e-05,
|
44 |
+
"loss": 0.2026,
|
45 |
+
"step": 1500
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.0,
|
49 |
+
"eval_loss": 0.7681801319122314,
|
50 |
+
"eval_matthews_correlation": 0.47428224772244454,
|
51 |
+
"eval_runtime": 0.7372,
|
52 |
+
"eval_samples_per_second": 1414.877,
|
53 |
+
"eval_steps_per_second": 89.532,
|
54 |
+
"step": 1605
|
55 |
+
}
|
56 |
+
],
|
57 |
+
"logging_steps": 500,
|
58 |
+
"max_steps": 2675,
|
59 |
+
"num_input_tokens_seen": 0,
|
60 |
+
"num_train_epochs": 5,
|
61 |
+
"save_steps": 500,
|
62 |
+
"total_flos": 128002833360672.0,
|
63 |
+
"train_batch_size": 16,
|
64 |
+
"trial_name": null,
|
65 |
+
"trial_params": {
|
66 |
+
"learning_rate": 6.019350116722694e-05,
|
67 |
+
"num_train_epochs": 5,
|
68 |
+
"per_device_train_batch_size": 16,
|
69 |
+
"seed": 13
|
70 |
+
}
|
71 |
+
}
|
run-1/checkpoint-1605/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf249ce55272fbde68001c7053fc83d7d8152ef8c83e36c8c055bcdcbd21b4af
|
3 |
+
size 4792
|
run-1/checkpoint-1605/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/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-1/checkpoint-535/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3b4845f29fe2be5ccd2617cc4156462b8b5e96a95b5c783bea6cfa45438d98c
|
3 |
+
size 267832560
|
run-1/checkpoint-535/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83926b04b4544955d4734bfe7f82ec4a0e7654d520da57c491fb2ba239d50cea
|
3 |
+
size 535727290
|
run-1/checkpoint-535/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d76d3449f3983e2e391e8727c5f1e8869503b5c1bb6f139ad1c94fe911c76405
|
3 |
+
size 14308
|
run-1/checkpoint-535/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8e6c8205a5fe1fe40139683afad1fcc5e80fe0aa3433a2975a2d63b83f23d59
|
3 |
+
size 1064
|
run-1/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-1/checkpoint-535/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/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-1/checkpoint-535/trainer_state.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4371151083758757,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 4.894237945372658e-05,
|
14 |
+
"loss": 0.5408,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_loss": 0.48756271600723267,
|
20 |
+
"eval_matthews_correlation": 0.4371151083758757,
|
21 |
+
"eval_runtime": 0.7652,
|
22 |
+
"eval_samples_per_second": 1363.003,
|
23 |
+
"eval_steps_per_second": 86.249,
|
24 |
+
"step": 535
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"logging_steps": 500,
|
28 |
+
"max_steps": 2675,
|
29 |
+
"num_input_tokens_seen": 0,
|
30 |
+
"num_train_epochs": 5,
|
31 |
+
"save_steps": 500,
|
32 |
+
"total_flos": 42956693620416.0,
|
33 |
+
"train_batch_size": 16,
|
34 |
+
"trial_name": null,
|
35 |
+
"trial_params": {
|
36 |
+
"learning_rate": 6.019350116722694e-05,
|
37 |
+
"num_train_epochs": 5,
|
38 |
+
"per_device_train_batch_size": 16,
|
39 |
+
"seed": 13
|
40 |
+
}
|
41 |
+
}
|
run-1/checkpoint-535/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf249ce55272fbde68001c7053fc83d7d8152ef8c83e36c8c055bcdcbd21b4af
|
3 |
+
size 4792
|
run-1/checkpoint-535/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703298290.48296f50e732.508.2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43162c13e2cca35c8e4530b51c9f6f6a1596ee058f4f8996843649f184a06a36
|
3 |
+
size 6314
|