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 +58 -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 +74 -0
- run-1/checkpoint-1605/training_args.bin +3 -0
- run-1/checkpoint-1605/vocab.txt +0 -0
- runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711160724.4cc37c544afe.560.3 +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 sha256:054c391121ab39940194288952ec175fa0bb61748960a0f580b545a1da835c76
|
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": "4.39.1",
|
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 sha256:628953c447ffc25cdfe3f955d4716c4242bf5bfb8a54b7c8f12e454417d23973
|
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 sha256:5c86e80ab845ff87641672769d58067566678a42d463ef1ea91b7a75c1a7d8fc
|
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 sha256:735953fa6cd11e734791dd5c81df81ae523716b7a8b84ab1913e5a1d4b7503d1
|
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 sha256:0affb95f8b8d62dd7a8abdd3b12a80911efa0558fe278b4fbe37b43faced9dac
|
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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.2835704013245166,
|
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 |
+
"grad_norm": 4.029795169830322,
|
14 |
+
"learning_rate": 1.7163903856453514e-06,
|
15 |
+
"loss": 0.6033,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_loss": 0.5766915082931519,
|
21 |
+
"eval_matthews_correlation": 0.0,
|
22 |
+
"eval_runtime": 0.7097,
|
23 |
+
"eval_samples_per_second": 1469.555,
|
24 |
+
"eval_steps_per_second": 92.992,
|
25 |
+
"step": 535
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.87,
|
29 |
+
"grad_norm": 4.412518501281738,
|
30 |
+
"learning_rate": 1.1931006339242075e-06,
|
31 |
+
"loss": 0.5433,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_loss": 0.5463550686836243,
|
37 |
+
"eval_matthews_correlation": 0.2835704013245166,
|
38 |
+
"eval_runtime": 1.1159,
|
39 |
+
"eval_samples_per_second": 934.633,
|
40 |
+
"eval_steps_per_second": 59.143,
|
41 |
+
"step": 1070
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"logging_steps": 500,
|
45 |
+
"max_steps": 2140,
|
46 |
+
"num_input_tokens_seen": 0,
|
47 |
+
"num_train_epochs": 4,
|
48 |
+
"save_steps": 500,
|
49 |
+
"total_flos": 85414564692768.0,
|
50 |
+
"train_batch_size": 16,
|
51 |
+
"trial_name": null,
|
52 |
+
"trial_params": {
|
53 |
+
"learning_rate": 2.2396801373664952e-06,
|
54 |
+
"num_train_epochs": 4,
|
55 |
+
"per_device_train_batch_size": 16,
|
56 |
+
"seed": 33
|
57 |
+
}
|
58 |
+
}
|
run-1/checkpoint-1070/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:358c5c99400b0deb976ef4d481ff138cc391693d34c093052ecece5e47feca40
|
3 |
+
size 4984
|
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": "4.39.1",
|
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 sha256:054c391121ab39940194288952ec175fa0bb61748960a0f580b545a1da835c76
|
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 sha256:5e10d91f5215b986027e3d7423071aac8abf1cbeb8ebd139b924f97e28ef0596
|
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 sha256:6844877a379b357f8ff18127035270a302389fab3af650d5edea9f984bbcb60c
|
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:e3836c6e966e3796900bfe25ccba67e34d3964ae33a75c9816b6f2c87109eccc
|
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 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3731107016234198,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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 |
+
"grad_norm": 4.029795169830322,
|
14 |
+
"learning_rate": 1.7163903856453514e-06,
|
15 |
+
"loss": 0.6033,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_loss": 0.5766915082931519,
|
21 |
+
"eval_matthews_correlation": 0.0,
|
22 |
+
"eval_runtime": 0.7097,
|
23 |
+
"eval_samples_per_second": 1469.555,
|
24 |
+
"eval_steps_per_second": 92.992,
|
25 |
+
"step": 535
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.87,
|
29 |
+
"grad_norm": 4.412518501281738,
|
30 |
+
"learning_rate": 1.1931006339242075e-06,
|
31 |
+
"loss": 0.5433,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_loss": 0.5463550686836243,
|
37 |
+
"eval_matthews_correlation": 0.2835704013245166,
|
38 |
+
"eval_runtime": 1.1159,
|
39 |
+
"eval_samples_per_second": 934.633,
|
40 |
+
"eval_steps_per_second": 59.143,
|
41 |
+
"step": 1070
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.8,
|
45 |
+
"grad_norm": 4.607611656188965,
|
46 |
+
"learning_rate": 6.69810882203064e-07,
|
47 |
+
"loss": 0.491,
|
48 |
+
"step": 1500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_loss": 0.5242806077003479,
|
53 |
+
"eval_matthews_correlation": 0.3731107016234198,
|
54 |
+
"eval_runtime": 0.7889,
|
55 |
+
"eval_samples_per_second": 1322.174,
|
56 |
+
"eval_steps_per_second": 83.666,
|
57 |
+
"step": 1605
|
58 |
+
}
|
59 |
+
],
|
60 |
+
"logging_steps": 500,
|
61 |
+
"max_steps": 2140,
|
62 |
+
"num_input_tokens_seen": 0,
|
63 |
+
"num_train_epochs": 4,
|
64 |
+
"save_steps": 500,
|
65 |
+
"total_flos": 128596608126132.0,
|
66 |
+
"train_batch_size": 16,
|
67 |
+
"trial_name": null,
|
68 |
+
"trial_params": {
|
69 |
+
"learning_rate": 2.2396801373664952e-06,
|
70 |
+
"num_train_epochs": 4,
|
71 |
+
"per_device_train_batch_size": 16,
|
72 |
+
"seed": 33
|
73 |
+
}
|
74 |
+
}
|
run-1/checkpoint-1605/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:358c5c99400b0deb976ef4d481ff138cc391693d34c093052ecece5e47feca40
|
3 |
+
size 4984
|
run-1/checkpoint-1605/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711160724.4cc37c544afe.560.3
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 sha256:1afd83044724a2a3381f3afc1b17e8684fd12650b174e13323ed67d33dfbdacc
|
3 |
+
size 7122
|