Training in progress, epoch 1
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- model.safetensors +1 -1
- run-5/checkpoint-108/config.json +25 -0
- run-5/checkpoint-108/model.safetensors +3 -0
- run-5/checkpoint-108/optimizer.pt +3 -0
- run-5/checkpoint-108/rng_state.pth +3 -0
- run-5/checkpoint-108/scheduler.pt +3 -0
- run-5/checkpoint-108/special_tokens_map.json +7 -0
- run-5/checkpoint-108/tokenizer.json +0 -0
- run-5/checkpoint-108/tokenizer_config.json +55 -0
- run-5/checkpoint-108/trainer_state.json +44 -0
- run-5/checkpoint-108/training_args.bin +3 -0
- run-5/checkpoint-108/vocab.txt +0 -0
- run-5/checkpoint-162/config.json +25 -0
- run-5/checkpoint-162/model.safetensors +3 -0
- run-5/checkpoint-162/optimizer.pt +3 -0
- run-5/checkpoint-162/rng_state.pth +3 -0
- run-5/checkpoint-162/scheduler.pt +3 -0
- run-5/checkpoint-162/special_tokens_map.json +7 -0
- run-5/checkpoint-162/tokenizer.json +0 -0
- run-5/checkpoint-162/tokenizer_config.json +55 -0
- run-5/checkpoint-162/trainer_state.json +53 -0
- run-5/checkpoint-162/training_args.bin +3 -0
- run-5/checkpoint-162/vocab.txt +0 -0
- run-5/checkpoint-216/config.json +25 -0
- run-5/checkpoint-216/model.safetensors +3 -0
- run-5/checkpoint-216/optimizer.pt +3 -0
- run-5/checkpoint-216/rng_state.pth +3 -0
- run-5/checkpoint-216/scheduler.pt +3 -0
- run-5/checkpoint-216/special_tokens_map.json +7 -0
- run-5/checkpoint-216/tokenizer.json +0 -0
- run-5/checkpoint-216/tokenizer_config.json +55 -0
- run-5/checkpoint-216/trainer_state.json +62 -0
- run-5/checkpoint-216/training_args.bin +3 -0
- run-5/checkpoint-216/vocab.txt +0 -0
- run-5/checkpoint-54/config.json +25 -0
- run-5/checkpoint-54/model.safetensors +3 -0
- run-5/checkpoint-54/optimizer.pt +3 -0
- run-5/checkpoint-54/rng_state.pth +3 -0
- run-5/checkpoint-54/scheduler.pt +3 -0
- run-5/checkpoint-54/special_tokens_map.json +7 -0
- run-5/checkpoint-54/tokenizer.json +0 -0
- run-5/checkpoint-54/tokenizer_config.json +55 -0
- run-5/checkpoint-54/trainer_state.json +35 -0
- run-5/checkpoint-54/training_args.bin +3 -0
- run-5/checkpoint-54/vocab.txt +0 -0
- run-6/checkpoint-107/config.json +25 -0
- run-6/checkpoint-107/model.safetensors +3 -0
- run-6/checkpoint-107/optimizer.pt +3 -0
- run-6/checkpoint-107/rng_state.pth +3 -0
- run-6/checkpoint-107/scheduler.pt +3 -0
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 sha256:2d9d23539cd0695db1fa3cf1edbe16f251e6fdee17c0c8565e864464fb03af40
|
3 |
size 267832560
|
run-5/checkpoint-108/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": "4.38.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-5/checkpoint-108/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab6fa01dd40cb59081cd6576481a5347eee0bb8f3a7e09026ac1ae64b87c8ca6
|
3 |
+
size 267832560
|
run-5/checkpoint-108/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e3d41aefdfc8424c8cd0c8d2d1a9a1b93d8721d734df900a3edaab93a3d8d8b
|
3 |
+
size 535727290
|
run-5/checkpoint-108/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c4b9a356b936f34e80b8988d0533b6ccc979a1a99e1b9dcfeb2bd63e40d084d
|
3 |
+
size 14308
|
run-5/checkpoint-108/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb944de7ff34d45f91ccddd299fc4150aeea38bba4225421e80620c08c91f946
|
3 |
+
size 1064
|
run-5/checkpoint-108/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-5/checkpoint-108/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-5/checkpoint-108/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-5/checkpoint-108/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.26725251307906606,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-108",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 108,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.573951244354248,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.722,
|
16 |
+
"eval_samples_per_second": 1444.613,
|
17 |
+
"eval_steps_per_second": 91.414,
|
18 |
+
"step": 54
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6243596076965332,
|
23 |
+
"eval_matthews_correlation": 0.26725251307906606,
|
24 |
+
"eval_runtime": 0.8323,
|
25 |
+
"eval_samples_per_second": 1253.157,
|
26 |
+
"eval_steps_per_second": 79.298,
|
27 |
+
"step": 108
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 216,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 4,
|
34 |
+
"save_steps": 500,
|
35 |
+
"total_flos": 0,
|
36 |
+
"train_batch_size": 16,
|
37 |
+
"trial_name": null,
|
38 |
+
"trial_params": {
|
39 |
+
"learning_rate": 3.68477446435844e-05,
|
40 |
+
"num_train_epochs": 4,
|
41 |
+
"per_device_train_batch_size": 16,
|
42 |
+
"seed": 14
|
43 |
+
}
|
44 |
+
}
|
run-5/checkpoint-108/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aaeef0b5638aa7bffa914cdba3eae3b1bd5b4b4b80b699028f568d31d6caa14
|
3 |
+
size 4984
|
run-5/checkpoint-108/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-5/checkpoint-162/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": "4.38.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-5/checkpoint-162/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3630e980306b0760c40355cf1af641d547fa71923384202261aba86336b0a826
|
3 |
+
size 267832560
|
run-5/checkpoint-162/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3163aa80d5e319a3079b70c512086327458e5d2db287d352e827ab8c4e6718b
|
3 |
+
size 535727290
|
run-5/checkpoint-162/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:086fe3c49adc6b40803a7b365c5fbc89fb451fee0d81268a5a846e6d5c9258c3
|
3 |
+
size 14308
|
run-5/checkpoint-162/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:451ef27c517ea4b60ec6c566ea0d4a7dcd8c6988142829a8e6659ef8784989f7
|
3 |
+
size 1064
|
run-5/checkpoint-162/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-5/checkpoint-162/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-5/checkpoint-162/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-5/checkpoint-162/trainer_state.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.2956825972622334,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-162",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 162,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.573951244354248,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.722,
|
16 |
+
"eval_samples_per_second": 1444.613,
|
17 |
+
"eval_steps_per_second": 91.414,
|
18 |
+
"step": 54
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6243596076965332,
|
23 |
+
"eval_matthews_correlation": 0.26725251307906606,
|
24 |
+
"eval_runtime": 0.8323,
|
25 |
+
"eval_samples_per_second": 1253.157,
|
26 |
+
"eval_steps_per_second": 79.298,
|
27 |
+
"step": 108
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.7463017702102661,
|
32 |
+
"eval_matthews_correlation": 0.2956825972622334,
|
33 |
+
"eval_runtime": 0.9504,
|
34 |
+
"eval_samples_per_second": 1097.444,
|
35 |
+
"eval_steps_per_second": 69.445,
|
36 |
+
"step": 162
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"logging_steps": 500,
|
40 |
+
"max_steps": 216,
|
41 |
+
"num_input_tokens_seen": 0,
|
42 |
+
"num_train_epochs": 4,
|
43 |
+
"save_steps": 500,
|
44 |
+
"total_flos": 0,
|
45 |
+
"train_batch_size": 16,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": {
|
48 |
+
"learning_rate": 3.68477446435844e-05,
|
49 |
+
"num_train_epochs": 4,
|
50 |
+
"per_device_train_batch_size": 16,
|
51 |
+
"seed": 14
|
52 |
+
}
|
53 |
+
}
|
run-5/checkpoint-162/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aaeef0b5638aa7bffa914cdba3eae3b1bd5b4b4b80b699028f568d31d6caa14
|
3 |
+
size 4984
|
run-5/checkpoint-162/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-5/checkpoint-216/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": "4.38.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-5/checkpoint-216/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:538d5e48b639cce2729ebdc85733de1f5ddf0bd01d627a8ba7522ba5ab4beffd
|
3 |
+
size 267832560
|
run-5/checkpoint-216/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69d321139089ebe68570f1a739afc6c385cc9e82e11f276e9f9e931fa95fa3ed
|
3 |
+
size 535727290
|
run-5/checkpoint-216/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:639cc486ddd25964291086a7e900330704bf0fdbe15c694d6cf8878271fe1e4c
|
3 |
+
size 14308
|
run-5/checkpoint-216/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efc539f17843f923c4bd78cb57bba1f37dc95818a2bd7f25b8eaa8a070ee222e
|
3 |
+
size 1064
|
run-5/checkpoint-216/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-5/checkpoint-216/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-5/checkpoint-216/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-5/checkpoint-216/trainer_state.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.30837420944189176,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-216",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 216,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.573951244354248,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.722,
|
16 |
+
"eval_samples_per_second": 1444.613,
|
17 |
+
"eval_steps_per_second": 91.414,
|
18 |
+
"step": 54
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.6243596076965332,
|
23 |
+
"eval_matthews_correlation": 0.26725251307906606,
|
24 |
+
"eval_runtime": 0.8323,
|
25 |
+
"eval_samples_per_second": 1253.157,
|
26 |
+
"eval_steps_per_second": 79.298,
|
27 |
+
"step": 108
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.7463017702102661,
|
32 |
+
"eval_matthews_correlation": 0.2956825972622334,
|
33 |
+
"eval_runtime": 0.9504,
|
34 |
+
"eval_samples_per_second": 1097.444,
|
35 |
+
"eval_steps_per_second": 69.445,
|
36 |
+
"step": 162
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_loss": 0.8294790387153625,
|
41 |
+
"eval_matthews_correlation": 0.30837420944189176,
|
42 |
+
"eval_runtime": 0.7759,
|
43 |
+
"eval_samples_per_second": 1344.228,
|
44 |
+
"eval_steps_per_second": 85.061,
|
45 |
+
"step": 216
|
46 |
+
}
|
47 |
+
],
|
48 |
+
"logging_steps": 500,
|
49 |
+
"max_steps": 216,
|
50 |
+
"num_input_tokens_seen": 0,
|
51 |
+
"num_train_epochs": 4,
|
52 |
+
"save_steps": 500,
|
53 |
+
"total_flos": 0,
|
54 |
+
"train_batch_size": 16,
|
55 |
+
"trial_name": null,
|
56 |
+
"trial_params": {
|
57 |
+
"learning_rate": 3.68477446435844e-05,
|
58 |
+
"num_train_epochs": 4,
|
59 |
+
"per_device_train_batch_size": 16,
|
60 |
+
"seed": 14
|
61 |
+
}
|
62 |
+
}
|
run-5/checkpoint-216/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aaeef0b5638aa7bffa914cdba3eae3b1bd5b4b4b80b699028f568d31d6caa14
|
3 |
+
size 4984
|
run-5/checkpoint-216/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-5/checkpoint-54/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": "4.38.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-5/checkpoint-54/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b84db3cc8dbc96de5c9d1fc8b3fd91b55765ccb7770d2d3d5e7d0ea59acd5479
|
3 |
+
size 267832560
|
run-5/checkpoint-54/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b47c68e478eda3e6a13ea902979a69d0ed74a69170f805991ea4de863b2fa428
|
3 |
+
size 535727290
|
run-5/checkpoint-54/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11339de46475a7309630f05c599e7b50266187088ab6074ad475e86fe14329b7
|
3 |
+
size 14308
|
run-5/checkpoint-54/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14d9c64b89c2e6bf5c7ab4398b0e3483e7fef973dabdd9b4976ef4557e136823
|
3 |
+
size 1064
|
run-5/checkpoint-54/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-5/checkpoint-54/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-5/checkpoint-54/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-5/checkpoint-54/trainer_state.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-54",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 54,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.573951244354248,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.722,
|
16 |
+
"eval_samples_per_second": 1444.613,
|
17 |
+
"eval_steps_per_second": 91.414,
|
18 |
+
"step": 54
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 216,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 4,
|
25 |
+
"save_steps": 500,
|
26 |
+
"total_flos": 0,
|
27 |
+
"train_batch_size": 16,
|
28 |
+
"trial_name": null,
|
29 |
+
"trial_params": {
|
30 |
+
"learning_rate": 3.68477446435844e-05,
|
31 |
+
"num_train_epochs": 4,
|
32 |
+
"per_device_train_batch_size": 16,
|
33 |
+
"seed": 14
|
34 |
+
}
|
35 |
+
}
|
run-5/checkpoint-54/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aaeef0b5638aa7bffa914cdba3eae3b1bd5b4b4b80b699028f568d31d6caa14
|
3 |
+
size 4984
|
run-5/checkpoint-54/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-6/checkpoint-107/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": "4.38.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-6/checkpoint-107/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d9d23539cd0695db1fa3cf1edbe16f251e6fdee17c0c8565e864464fb03af40
|
3 |
+
size 267832560
|
run-6/checkpoint-107/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa50c88e978f0f04e8cdecb00677f6b6de4c0c498f9c726c33c1b3895282abd4
|
3 |
+
size 535727290
|
run-6/checkpoint-107/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdb698281ab938a70a61271363685f2d7e752fe7c8a72ba36a263b9514b36aaa
|
3 |
+
size 14244
|
run-6/checkpoint-107/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cb5c18cfc5d54013870b7a5da10d1053b8276e7b6798ded96156b13afc5cf90
|
3 |
+
size 1064
|