anamelchor
commited on
Commit
•
b3e478a
1
Parent(s):
2f1fbb2
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-4/checkpoint-268/config.json +25 -0
- run-4/checkpoint-268/model.safetensors +3 -0
- run-4/checkpoint-268/optimizer.pt +3 -0
- run-4/checkpoint-268/rng_state.pth +3 -0
- run-4/checkpoint-268/scheduler.pt +3 -0
- run-4/checkpoint-268/special_tokens_map.json +7 -0
- run-4/checkpoint-268/tokenizer.json +0 -0
- run-4/checkpoint-268/tokenizer_config.json +55 -0
- run-4/checkpoint-268/trainer_state.json +44 -0
- run-4/checkpoint-268/training_args.bin +3 -0
- run-4/checkpoint-268/vocab.txt +0 -0
- run-4/checkpoint-402/config.json +25 -0
- run-4/checkpoint-402/model.safetensors +3 -0
- run-4/checkpoint-402/optimizer.pt +3 -0
- run-4/checkpoint-402/rng_state.pth +3 -0
- run-4/checkpoint-402/scheduler.pt +3 -0
- run-4/checkpoint-402/special_tokens_map.json +7 -0
- run-4/checkpoint-402/tokenizer.json +0 -0
- run-4/checkpoint-402/tokenizer_config.json +55 -0
- run-4/checkpoint-402/trainer_state.json +53 -0
- run-4/checkpoint-402/training_args.bin +3 -0
- run-4/checkpoint-402/vocab.txt +0 -0
- run-4/checkpoint-536/config.json +25 -0
- run-4/checkpoint-536/model.safetensors +3 -0
- run-4/checkpoint-536/optimizer.pt +3 -0
- run-4/checkpoint-536/rng_state.pth +3 -0
- run-4/checkpoint-536/scheduler.pt +3 -0
- run-4/checkpoint-536/special_tokens_map.json +7 -0
- run-4/checkpoint-536/tokenizer.json +0 -0
- run-4/checkpoint-536/tokenizer_config.json +55 -0
- run-4/checkpoint-536/trainer_state.json +69 -0
- run-4/checkpoint-536/training_args.bin +3 -0
- run-4/checkpoint-536/vocab.txt +0 -0
- run-5/checkpoint-1069/config.json +25 -0
- run-5/checkpoint-1069/model.safetensors +3 -0
- run-5/checkpoint-1069/optimizer.pt +3 -0
- run-5/checkpoint-1069/rng_state.pth +3 -0
- run-5/checkpoint-1069/scheduler.pt +3 -0
- run-5/checkpoint-1069/special_tokens_map.json +7 -0
- run-5/checkpoint-1069/tokenizer.json +0 -0
- run-5/checkpoint-1069/tokenizer_config.json +55 -0
- run-5/checkpoint-1069/trainer_state.json +49 -0
- run-5/checkpoint-1069/training_args.bin +3 -0
- run-5/checkpoint-1069/vocab.txt +0 -0
- runs/Mar03_19-18-26_abc5bcbabcce/events.out.tfevents.1709494800.abc5bcbabcce.1176.34 +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 sha256:3bb0769215bc4b65b8a878eadca5f9abe81f01fb7baaaeb07cc3bee938eae377
|
3 |
size 267832560
|
run-4/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": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-4/checkpoint-268/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25f6ba58a5224e66bf2ab5b57add549c662f1971a69192272412182fe1a43d63
|
3 |
+
size 267832560
|
run-4/checkpoint-268/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b11e5ca8625d3721901638a9bfa21678b0fffcec5f2009323ce8b8925b31b74
|
3 |
+
size 535727290
|
run-4/checkpoint-268/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53079ad91e486c98e8caf2a5b821a40f9f8d0d282dd8358913897962422a16f7
|
3 |
+
size 14244
|
run-4/checkpoint-268/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be8f8bd8e02a4995b4225fbd9b133e1be7195799d1c0d6930c7175e9aa52ae67
|
3 |
+
size 1064
|
run-4/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-4/checkpoint-268/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/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-4/checkpoint-268/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3353914849277504,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-268",
|
4 |
+
"epoch": 2.0,
|
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": 0.5707044005393982,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.8134,
|
16 |
+
"eval_samples_per_second": 1282.322,
|
17 |
+
"eval_steps_per_second": 81.144,
|
18 |
+
"step": 134
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.5365880727767944,
|
23 |
+
"eval_matthews_correlation": 0.3353914849277504,
|
24 |
+
"eval_runtime": 1.2298,
|
25 |
+
"eval_samples_per_second": 848.08,
|
26 |
+
"eval_steps_per_second": 53.666,
|
27 |
+
"step": 268
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 536,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 4,
|
34 |
+
"save_steps": 500,
|
35 |
+
"total_flos": 0,
|
36 |
+
"train_batch_size": 64,
|
37 |
+
"trial_name": null,
|
38 |
+
"trial_params": {
|
39 |
+
"learning_rate": 4.585789875360977e-06,
|
40 |
+
"num_train_epochs": 4,
|
41 |
+
"per_device_train_batch_size": 64,
|
42 |
+
"seed": 15
|
43 |
+
}
|
44 |
+
}
|
run-4/checkpoint-268/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ef0ff731fdc2cae0b198ef145bbb3fe7f7944e070856b621fff8bb1f2969dcb
|
3 |
+
size 4984
|
run-4/checkpoint-268/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-402/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": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-4/checkpoint-402/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76451a4576c8f4c5c9c12219167ee73d2dfeb1998d5c64adef92e28ef9524246
|
3 |
+
size 267832560
|
run-4/checkpoint-402/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b2ca73bcfe796e614f6426ddb0a16b8b6a7911fb54ab810ac7af3e24808c837
|
3 |
+
size 535727290
|
run-4/checkpoint-402/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac757dfc09ac9ec253905d4baf960343b58ff78a80fc4bfed9bfd51e6293eebc
|
3 |
+
size 14244
|
run-4/checkpoint-402/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2563de7dea436dbbf7c32099117d51382e2cda8c37c07b2eb71b32122274537
|
3 |
+
size 1064
|
run-4/checkpoint-402/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-4/checkpoint-402/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-402/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-4/checkpoint-402/trainer_state.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.394328439257328,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-402",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 402,
|
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": 0.5707044005393982,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.8134,
|
16 |
+
"eval_samples_per_second": 1282.322,
|
17 |
+
"eval_steps_per_second": 81.144,
|
18 |
+
"step": 134
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.5365880727767944,
|
23 |
+
"eval_matthews_correlation": 0.3353914849277504,
|
24 |
+
"eval_runtime": 1.2298,
|
25 |
+
"eval_samples_per_second": 848.08,
|
26 |
+
"eval_steps_per_second": 53.666,
|
27 |
+
"step": 268
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.5241007804870605,
|
32 |
+
"eval_matthews_correlation": 0.394328439257328,
|
33 |
+
"eval_runtime": 1.3904,
|
34 |
+
"eval_samples_per_second": 750.158,
|
35 |
+
"eval_steps_per_second": 47.469,
|
36 |
+
"step": 402
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"logging_steps": 500,
|
40 |
+
"max_steps": 536,
|
41 |
+
"num_input_tokens_seen": 0,
|
42 |
+
"num_train_epochs": 4,
|
43 |
+
"save_steps": 500,
|
44 |
+
"total_flos": 0,
|
45 |
+
"train_batch_size": 64,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": {
|
48 |
+
"learning_rate": 4.585789875360977e-06,
|
49 |
+
"num_train_epochs": 4,
|
50 |
+
"per_device_train_batch_size": 64,
|
51 |
+
"seed": 15
|
52 |
+
}
|
53 |
+
}
|
run-4/checkpoint-402/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ef0ff731fdc2cae0b198ef145bbb3fe7f7944e070856b621fff8bb1f2969dcb
|
3 |
+
size 4984
|
run-4/checkpoint-402/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/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": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-4/checkpoint-536/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32c5e38dab8d92e21c1ef86516d08bfe86fa42dcbd6f1615e436806ec8f0779c
|
3 |
+
size 267832560
|
run-4/checkpoint-536/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c20db350579974cc7223744ea7a715818ff9b43630cac5cc51daa9c57fe0a30
|
3 |
+
size 535727290
|
run-4/checkpoint-536/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd5c385b865c6d2a09d605a4ab3e2a71e227c207603025dffa2ea1cf040e0b84
|
3 |
+
size 14244
|
run-4/checkpoint-536/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77c6bb16aa015d05c79546c50d7faa31f5dee43e232c36bba619ba8e55385d42
|
3 |
+
size 1064
|
run-4/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-4/checkpoint-536/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/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-4/checkpoint-536/trainer_state.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.39789056142736157,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-536",
|
4 |
+
"epoch": 4.0,
|
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": 0.5707044005393982,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.8134,
|
16 |
+
"eval_samples_per_second": 1282.322,
|
17 |
+
"eval_steps_per_second": 81.144,
|
18 |
+
"step": 134
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.5365880727767944,
|
23 |
+
"eval_matthews_correlation": 0.3353914849277504,
|
24 |
+
"eval_runtime": 1.2298,
|
25 |
+
"eval_samples_per_second": 848.08,
|
26 |
+
"eval_steps_per_second": 53.666,
|
27 |
+
"step": 268
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.5241007804870605,
|
32 |
+
"eval_matthews_correlation": 0.394328439257328,
|
33 |
+
"eval_runtime": 1.3904,
|
34 |
+
"eval_samples_per_second": 750.158,
|
35 |
+
"eval_steps_per_second": 47.469,
|
36 |
+
"step": 402
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.73,
|
40 |
+
"grad_norm": 3.5259664058685303,
|
41 |
+
"learning_rate": 3.080008125242447e-07,
|
42 |
+
"loss": 0.522,
|
43 |
+
"step": 500
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 4.0,
|
47 |
+
"eval_loss": 0.5204655528068542,
|
48 |
+
"eval_matthews_correlation": 0.39789056142736157,
|
49 |
+
"eval_runtime": 0.7847,
|
50 |
+
"eval_samples_per_second": 1329.246,
|
51 |
+
"eval_steps_per_second": 84.113,
|
52 |
+
"step": 536
|
53 |
+
}
|
54 |
+
],
|
55 |
+
"logging_steps": 500,
|
56 |
+
"max_steps": 536,
|
57 |
+
"num_input_tokens_seen": 0,
|
58 |
+
"num_train_epochs": 4,
|
59 |
+
"save_steps": 500,
|
60 |
+
"total_flos": 208937050509444.0,
|
61 |
+
"train_batch_size": 64,
|
62 |
+
"trial_name": null,
|
63 |
+
"trial_params": {
|
64 |
+
"learning_rate": 4.585789875360977e-06,
|
65 |
+
"num_train_epochs": 4,
|
66 |
+
"per_device_train_batch_size": 64,
|
67 |
+
"seed": 15
|
68 |
+
}
|
69 |
+
}
|
run-4/checkpoint-536/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ef0ff731fdc2cae0b198ef145bbb3fe7f7944e070856b621fff8bb1f2969dcb
|
3 |
+
size 4984
|
run-4/checkpoint-536/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-5/checkpoint-1069/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": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-5/checkpoint-1069/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bb0769215bc4b65b8a878eadca5f9abe81f01fb7baaaeb07cc3bee938eae377
|
3 |
+
size 267832560
|
run-5/checkpoint-1069/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96ac692c59fc699fa7ec4907b716023ce709e3ddaf040ca1621fbefdce862acf
|
3 |
+
size 535727290
|
run-5/checkpoint-1069/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5ff70c86db436175a3cadd2a8532f8685b60da1ad30dcdfbbfc82dfd659f57b
|
3 |
+
size 14244
|
run-5/checkpoint-1069/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3a18dfd8730be074cf172d58088e455b1ef87d283883c6c33265c94bc57dec6
|
3 |
+
size 1064
|
run-5/checkpoint-1069/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-1069/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-5/checkpoint-1069/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-1069/trainer_state.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3815798845625387,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1069",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1069,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.47,
|
13 |
+
"grad_norm": 4.201667785644531,
|
14 |
+
"learning_rate": 5.188675273838238e-05,
|
15 |
+
"loss": 0.5755,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.94,
|
20 |
+
"grad_norm": 6.084535598754883,
|
21 |
+
"learning_rate": 4.501615518298217e-05,
|
22 |
+
"loss": 0.5472,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.0,
|
27 |
+
"eval_loss": 0.519609808921814,
|
28 |
+
"eval_matthews_correlation": 0.3815798845625387,
|
29 |
+
"eval_runtime": 0.7379,
|
30 |
+
"eval_samples_per_second": 1413.43,
|
31 |
+
"eval_steps_per_second": 89.44,
|
32 |
+
"step": 1069
|
33 |
+
}
|
34 |
+
],
|
35 |
+
"logging_steps": 500,
|
36 |
+
"max_steps": 4276,
|
37 |
+
"num_input_tokens_seen": 0,
|
38 |
+
"num_train_epochs": 4,
|
39 |
+
"save_steps": 500,
|
40 |
+
"total_flos": 37691114523840.0,
|
41 |
+
"train_batch_size": 8,
|
42 |
+
"trial_name": null,
|
43 |
+
"trial_params": {
|
44 |
+
"learning_rate": 5.875735029378259e-05,
|
45 |
+
"num_train_epochs": 4,
|
46 |
+
"per_device_train_batch_size": 8,
|
47 |
+
"seed": 36
|
48 |
+
}
|
49 |
+
}
|
run-5/checkpoint-1069/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5e7f5820919b1fe7d99aa7f153f7dd93c21637fefcb6b5a4d0a8059d5d02875
|
3 |
+
size 4984
|
run-5/checkpoint-1069/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar03_19-18-26_abc5bcbabcce/events.out.tfevents.1709494800.abc5bcbabcce.1176.34
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78d3e2b4cf5763c6506bdac51338b26bfbae0d7c951b591aaa8518851f861335
|
3 |
+
size 6055
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5e7f5820919b1fe7d99aa7f153f7dd93c21637fefcb6b5a4d0a8059d5d02875
|
3 |
size 4984
|