Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-1/checkpoint-268/config.json +25 -0
- run-1/checkpoint-268/model.safetensors +3 -0
- run-1/checkpoint-268/optimizer.pt +3 -0
- run-1/checkpoint-268/rng_state.pth +3 -0
- run-1/checkpoint-268/scheduler.pt +3 -0
- run-1/checkpoint-268/special_tokens_map.json +7 -0
- run-1/checkpoint-268/tokenizer.json +0 -0
- run-1/checkpoint-268/tokenizer_config.json +55 -0
- run-1/checkpoint-268/trainer_state.json +47 -0
- run-1/checkpoint-268/training_args.bin +3 -0
- run-1/checkpoint-268/vocab.txt +0 -0
- run-1/checkpoint-536/config.json +25 -0
- run-1/checkpoint-536/model.safetensors +3 -0
- run-1/checkpoint-536/optimizer.pt +3 -0
- run-1/checkpoint-536/rng_state.pth +3 -0
- run-1/checkpoint-536/scheduler.pt +3 -0
- run-1/checkpoint-536/special_tokens_map.json +7 -0
- run-1/checkpoint-536/tokenizer.json +0 -0
- run-1/checkpoint-536/tokenizer_config.json +55 -0
- run-1/checkpoint-536/trainer_state.json +63 -0
- run-1/checkpoint-536/training_args.bin +3 -0
- run-1/checkpoint-536/vocab.txt +0 -0
- run-1/checkpoint-804/config.json +25 -0
- run-1/checkpoint-804/model.safetensors +3 -0
- run-1/checkpoint-804/optimizer.pt +3 -0
- run-1/checkpoint-804/rng_state.pth +3 -0
- run-1/checkpoint-804/scheduler.pt +3 -0
- run-1/checkpoint-804/special_tokens_map.json +7 -0
- run-1/checkpoint-804/tokenizer.json +0 -0
- run-1/checkpoint-804/tokenizer_config.json +55 -0
- run-1/checkpoint-804/trainer_state.json +72 -0
- run-1/checkpoint-804/training_args.bin +3 -0
- run-1/checkpoint-804/vocab.txt +0 -0
- run-2/checkpoint-2138/config.json +25 -0
- run-2/checkpoint-2138/model.safetensors +3 -0
- run-2/checkpoint-2138/optimizer.pt +3 -0
- run-2/checkpoint-2138/rng_state.pth +3 -0
- run-2/checkpoint-2138/scheduler.pt +3 -0
- run-2/checkpoint-2138/special_tokens_map.json +7 -0
- run-2/checkpoint-2138/tokenizer.json +0 -0
- run-2/checkpoint-2138/tokenizer_config.json +55 -0
- run-2/checkpoint-2138/trainer_state.json +75 -0
- run-2/checkpoint-2138/training_args.bin +3 -0
- run-2/checkpoint-2138/vocab.txt +0 -0
- runs/Jun16_07-07-37_5152ff55fb03/events.out.tfevents.1718522516.5152ff55fb03.1457.5 +3 -0
- runs/Jun16_07-07-37_5152ff55fb03/events.out.tfevents.1718522681.5152ff55fb03.1457.6 +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 sha256:738bba97e1668d5e8487eb29280792d7355302c838121fcd105f9ac36b46c91e
|
3 |
size 267832560
|
run-1/checkpoint-268/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": "4.41.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-1/checkpoint-268/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:809a309b6832b1fb9203f354f7568e4f5f0035410ad3608986956a999de305db
|
3 |
+
size 267832560
|
run-1/checkpoint-268/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79736e496d8a2faa6e838996839902dafc987e2fb074b699a1201782ed0caaf3
|
3 |
+
size 535727290
|
run-1/checkpoint-268/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:636c26ca65f4f30a1c3e135e94d3b26461c90d0bb24695afa1aeee6fc1da70d9
|
3 |
+
size 14244
|
run-1/checkpoint-268/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e5af260da107756f8599f8e397d135d86b194cb50bf516753153c5e1caf63f5
|
3 |
+
size 1064
|
run-1/checkpoint-268/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-268/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-268/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-268/trainer_state.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.47933610275431493,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-268",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 268,
|
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": 0.4548027515411377,
|
14 |
+
"eval_matthews_correlation": 0.47933610275431493,
|
15 |
+
"eval_runtime": 0.987,
|
16 |
+
"eval_samples_per_second": 1056.73,
|
17 |
+
"eval_steps_per_second": 132.724,
|
18 |
+
"step": 268
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 804,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 3,
|
25 |
+
"save_steps": 500,
|
26 |
+
"stateful_callbacks": {
|
27 |
+
"TrainerControl": {
|
28 |
+
"args": {
|
29 |
+
"should_epoch_stop": false,
|
30 |
+
"should_evaluate": false,
|
31 |
+
"should_log": false,
|
32 |
+
"should_save": true,
|
33 |
+
"should_training_stop": false
|
34 |
+
},
|
35 |
+
"attributes": {}
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"total_flos": 0,
|
39 |
+
"train_batch_size": 32,
|
40 |
+
"trial_name": null,
|
41 |
+
"trial_params": {
|
42 |
+
"learning_rate": 5.117482253804467e-05,
|
43 |
+
"num_train_epochs": 3,
|
44 |
+
"per_device_train_batch_size": 32,
|
45 |
+
"seed": 16
|
46 |
+
}
|
47 |
+
}
|
run-1/checkpoint-268/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fd0fdb184dba5762080f1330346e68c1f830882bfd92f60d1fe89174f18c204
|
3 |
+
size 5176
|
run-1/checkpoint-268/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-536/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": "4.41.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-1/checkpoint-536/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b255911c919558080bf089abe8deba778e5891800da048e8800b8327ccc98a76
|
3 |
+
size 267832560
|
run-1/checkpoint-536/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c5b50bc8786c4e262ff8b67fd77c17e6b0135da6766f08411e0e18ced4aa422
|
3 |
+
size 535727290
|
run-1/checkpoint-536/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cca38366c5dc82f42fb9927dcfe6751fb767707a158207296ea4af9d0a3e5dd9
|
3 |
+
size 14244
|
run-1/checkpoint-536/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54ecc0aaf30a31f98270b60c62c6dd7efcc5abcfc86b125b89a6c4927e6f8237
|
3 |
+
size 1064
|
run-1/checkpoint-536/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-536/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-536/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-536/trainer_state.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5274949902750498,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-536",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 536,
|
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": 0.4548027515411377,
|
14 |
+
"eval_matthews_correlation": 0.47933610275431493,
|
15 |
+
"eval_runtime": 0.987,
|
16 |
+
"eval_samples_per_second": 1056.73,
|
17 |
+
"eval_steps_per_second": 132.724,
|
18 |
+
"step": 268
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.8656716417910446,
|
22 |
+
"grad_norm": 7.233431816101074,
|
23 |
+
"learning_rate": 1.9349684143738284e-05,
|
24 |
+
"loss": 0.4133,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_loss": 0.46222877502441406,
|
30 |
+
"eval_matthews_correlation": 0.5274949902750498,
|
31 |
+
"eval_runtime": 1.8381,
|
32 |
+
"eval_samples_per_second": 567.436,
|
33 |
+
"eval_steps_per_second": 71.269,
|
34 |
+
"step": 536
|
35 |
+
}
|
36 |
+
],
|
37 |
+
"logging_steps": 500,
|
38 |
+
"max_steps": 804,
|
39 |
+
"num_input_tokens_seen": 0,
|
40 |
+
"num_train_epochs": 3,
|
41 |
+
"save_steps": 500,
|
42 |
+
"stateful_callbacks": {
|
43 |
+
"TrainerControl": {
|
44 |
+
"args": {
|
45 |
+
"should_epoch_stop": false,
|
46 |
+
"should_evaluate": false,
|
47 |
+
"should_log": false,
|
48 |
+
"should_save": true,
|
49 |
+
"should_training_stop": false
|
50 |
+
},
|
51 |
+
"attributes": {}
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"total_flos": 95031128639340.0,
|
55 |
+
"train_batch_size": 32,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": {
|
58 |
+
"learning_rate": 5.117482253804467e-05,
|
59 |
+
"num_train_epochs": 3,
|
60 |
+
"per_device_train_batch_size": 32,
|
61 |
+
"seed": 16
|
62 |
+
}
|
63 |
+
}
|
run-1/checkpoint-536/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fd0fdb184dba5762080f1330346e68c1f830882bfd92f60d1fe89174f18c204
|
3 |
+
size 5176
|
run-1/checkpoint-536/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-804/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": "4.41.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-1/checkpoint-804/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:387849cc378828d7906275deeb0a93ead29aa07f3f33c2358ad77600bd420db3
|
3 |
+
size 267832560
|
run-1/checkpoint-804/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ddb49b153608d57bc9a1bb5be6cc0b7eb20098f7a775b27bb3bac1f9f4fa1d7
|
3 |
+
size 535727290
|
run-1/checkpoint-804/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc6489302d42a40157290677a1b8573446ec6d423d0dc3726aa88083c39aae25
|
3 |
+
size 14244
|
run-1/checkpoint-804/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ead7a93ba746babddc9f842f5aedd06dc3fc10a431f3afaef448b176d864127
|
3 |
+
size 1064
|
run-1/checkpoint-804/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-804/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-804/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-804/trainer_state.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5308567193176762,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-804",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 804,
|
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": 0.4548027515411377,
|
14 |
+
"eval_matthews_correlation": 0.47933610275431493,
|
15 |
+
"eval_runtime": 0.987,
|
16 |
+
"eval_samples_per_second": 1056.73,
|
17 |
+
"eval_steps_per_second": 132.724,
|
18 |
+
"step": 268
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.8656716417910446,
|
22 |
+
"grad_norm": 7.233431816101074,
|
23 |
+
"learning_rate": 1.9349684143738284e-05,
|
24 |
+
"loss": 0.4133,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_loss": 0.46222877502441406,
|
30 |
+
"eval_matthews_correlation": 0.5274949902750498,
|
31 |
+
"eval_runtime": 1.8381,
|
32 |
+
"eval_samples_per_second": 567.436,
|
33 |
+
"eval_steps_per_second": 71.269,
|
34 |
+
"step": 536
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"eval_loss": 0.6320855021476746,
|
39 |
+
"eval_matthews_correlation": 0.5308567193176762,
|
40 |
+
"eval_runtime": 1.085,
|
41 |
+
"eval_samples_per_second": 961.258,
|
42 |
+
"eval_steps_per_second": 120.733,
|
43 |
+
"step": 804
|
44 |
+
}
|
45 |
+
],
|
46 |
+
"logging_steps": 500,
|
47 |
+
"max_steps": 804,
|
48 |
+
"num_input_tokens_seen": 0,
|
49 |
+
"num_train_epochs": 3,
|
50 |
+
"save_steps": 500,
|
51 |
+
"stateful_callbacks": {
|
52 |
+
"TrainerControl": {
|
53 |
+
"args": {
|
54 |
+
"should_epoch_stop": false,
|
55 |
+
"should_evaluate": false,
|
56 |
+
"should_log": false,
|
57 |
+
"should_save": true,
|
58 |
+
"should_training_stop": true
|
59 |
+
},
|
60 |
+
"attributes": {}
|
61 |
+
}
|
62 |
+
},
|
63 |
+
"total_flos": 95031128639340.0,
|
64 |
+
"train_batch_size": 32,
|
65 |
+
"trial_name": null,
|
66 |
+
"trial_params": {
|
67 |
+
"learning_rate": 5.117482253804467e-05,
|
68 |
+
"num_train_epochs": 3,
|
69 |
+
"per_device_train_batch_size": 32,
|
70 |
+
"seed": 16
|
71 |
+
}
|
72 |
+
}
|
run-1/checkpoint-804/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fd0fdb184dba5762080f1330346e68c1f830882bfd92f60d1fe89174f18c204
|
3 |
+
size 5176
|
run-1/checkpoint-804/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-2138/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": "4.41.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-2/checkpoint-2138/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:738bba97e1668d5e8487eb29280792d7355302c838121fcd105f9ac36b46c91e
|
3 |
+
size 267832560
|
run-2/checkpoint-2138/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18377862456ac03444d1237e93919e5706fc12210762cb24e6e5278b8956e965
|
3 |
+
size 535727290
|
run-2/checkpoint-2138/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5008a6b97f7f941a202ea9000ec91099bbc523c9bc2122970f9599146b56306f
|
3 |
+
size 14308
|
run-2/checkpoint-2138/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5107db85b422504d0d53a8ea15a442bacc0896332cbbf7d0b4eb7e62a9af0181
|
3 |
+
size 1064
|
run-2/checkpoint-2138/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-2/checkpoint-2138/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-2138/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-2/checkpoint-2138/trainer_state.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.25376727839543856,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-2138",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2138,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.23386342376052385,
|
13 |
+
"grad_norm": 3.80633282661438,
|
14 |
+
"learning_rate": 1.4038087770081304e-06,
|
15 |
+
"loss": 0.6287,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.4677268475210477,
|
20 |
+
"grad_norm": 5.112864017486572,
|
21 |
+
"learning_rate": 1.3349270902069464e-06,
|
22 |
+
"loss": 0.5844,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.7015902712815716,
|
27 |
+
"grad_norm": 16.39091682434082,
|
28 |
+
"learning_rate": 1.2660454034057625e-06,
|
29 |
+
"loss": 0.5781,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.9354536950420954,
|
34 |
+
"grad_norm": 7.839633464813232,
|
35 |
+
"learning_rate": 1.1971637166045783e-06,
|
36 |
+
"loss": 0.5482,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.0,
|
41 |
+
"eval_loss": 0.5578071475028992,
|
42 |
+
"eval_matthews_correlation": 0.25376727839543856,
|
43 |
+
"eval_runtime": 1.0111,
|
44 |
+
"eval_samples_per_second": 1031.593,
|
45 |
+
"eval_steps_per_second": 129.567,
|
46 |
+
"step": 2138
|
47 |
+
}
|
48 |
+
],
|
49 |
+
"logging_steps": 500,
|
50 |
+
"max_steps": 10690,
|
51 |
+
"num_input_tokens_seen": 0,
|
52 |
+
"num_train_epochs": 5,
|
53 |
+
"save_steps": 500,
|
54 |
+
"stateful_callbacks": {
|
55 |
+
"TrainerControl": {
|
56 |
+
"args": {
|
57 |
+
"should_epoch_stop": false,
|
58 |
+
"should_evaluate": false,
|
59 |
+
"should_log": false,
|
60 |
+
"should_save": true,
|
61 |
+
"should_training_stop": false
|
62 |
+
},
|
63 |
+
"attributes": {}
|
64 |
+
}
|
65 |
+
},
|
66 |
+
"total_flos": 32693574929232.0,
|
67 |
+
"train_batch_size": 4,
|
68 |
+
"trial_name": null,
|
69 |
+
"trial_params": {
|
70 |
+
"learning_rate": 1.4726904638093145e-06,
|
71 |
+
"num_train_epochs": 5,
|
72 |
+
"per_device_train_batch_size": 4,
|
73 |
+
"seed": 37
|
74 |
+
}
|
75 |
+
}
|
run-2/checkpoint-2138/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0576f7d7c7a556468716db9c3a189f008e7820db6e39f98cfa101cc682a87d0c
|
3 |
+
size 5176
|
run-2/checkpoint-2138/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Jun16_07-07-37_5152ff55fb03/events.out.tfevents.1718522516.5152ff55fb03.1457.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b3f2f8704a0f8ca9ec0a31d22b5a68aeda18bca4c79806e4b3fdd2ddb2a1455
|
3 |
+
size 6357
|
runs/Jun16_07-07-37_5152ff55fb03/events.out.tfevents.1718522681.5152ff55fb03.1457.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82902a571f3627fb564ed68b438b7cc7620711f2d9b8941bcc38f8e5038ceb6a
|
3 |
+
size 6177
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0576f7d7c7a556468716db9c3a189f008e7820db6e39f98cfa101cc682a87d0c
|
3 |
size 5176
|