Commit
•
3971a92
1
Parent(s):
0496121
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-1/checkpoint-1069/config.json +25 -0
- run-1/checkpoint-1069/model.safetensors +3 -0
- run-1/checkpoint-1069/optimizer.pt +3 -0
- run-1/checkpoint-1069/rng_state.pth +3 -0
- run-1/checkpoint-1069/scheduler.pt +3 -0
- run-1/checkpoint-1069/special_tokens_map.json +7 -0
- run-1/checkpoint-1069/tokenizer.json +0 -0
- run-1/checkpoint-1069/tokenizer_config.json +55 -0
- run-1/checkpoint-1069/trainer_state.json +49 -0
- run-1/checkpoint-1069/training_args.bin +3 -0
- run-1/checkpoint-1069/vocab.txt +0 -0
- run-1/checkpoint-2138/config.json +25 -0
- run-1/checkpoint-2138/model.safetensors +3 -0
- run-1/checkpoint-2138/optimizer.pt +3 -0
- run-1/checkpoint-2138/rng_state.pth +3 -0
- run-1/checkpoint-2138/scheduler.pt +3 -0
- run-1/checkpoint-2138/special_tokens_map.json +7 -0
- run-1/checkpoint-2138/tokenizer.json +0 -0
- run-1/checkpoint-2138/tokenizer_config.json +55 -0
- run-1/checkpoint-2138/trainer_state.json +72 -0
- run-1/checkpoint-2138/training_args.bin +3 -0
- run-1/checkpoint-2138/vocab.txt +0 -0
- run-2/checkpoint-2138/config.json +1 -1
- run-2/checkpoint-2138/model.safetensors +1 -1
- run-2/checkpoint-2138/optimizer.pt +1 -1
- run-2/checkpoint-2138/rng_state.pth +2 -2
- run-2/checkpoint-2138/scheduler.pt +1 -1
- run-2/checkpoint-2138/tokenizer.json +1 -6
- run-2/checkpoint-2138/tokenizer_config.json +1 -1
- run-2/checkpoint-2138/trainer_state.json +28 -28
- run-2/checkpoint-2138/training_args.bin +2 -2
- runs/Apr23_13-58-51_309eb7d6022b/events.out.tfevents.1713888517.309eb7d6022b.9612.3 +3 -0
- runs/Apr23_13-58-51_309eb7d6022b/events.out.tfevents.1713891455.309eb7d6022b.9612.4 +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 sha256:2292682bda06383e4668b0f29444519a7ce7f188949e7579abc9eba8b70995bd
|
3 |
size 267832560
|
run-1/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": "4.40.0",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-1/checkpoint-1069/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17d4d69227744c8fc16a68bd010522a972bc2d428dbdb302186db88506db9f87
|
3 |
+
size 267832560
|
run-1/checkpoint-1069/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c5bb2b02a77795f51587c809b8be2334e87b4f3d8fd4ef13032b77288dbe9ee
|
3 |
+
size 535724410
|
run-1/checkpoint-1069/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43691fea594f06f1fe96c4d21d3a558ea9118f1a617efafcc9baaf97b6953f76
|
3 |
+
size 14054
|
run-1/checkpoint-1069/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d40b0e91e46a33f574601e6097676a162b3d370f67167526748b34eb0e6c5114
|
3 |
+
size 1064
|
run-1/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-1/checkpoint-1069/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/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": 1000000000000000019884624838656,
|
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-1069/trainer_state.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3611067385212146,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/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": 0.4677268475210477,
|
13 |
+
"grad_norm": 2.976968765258789,
|
14 |
+
"learning_rate": 5.1710250568684506e-05,
|
15 |
+
"loss": 0.5872,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.9354536950420954,
|
20 |
+
"grad_norm": 3.4058539867401123,
|
21 |
+
"learning_rate": 3.592568079802378e-05,
|
22 |
+
"loss": 0.5491,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.0,
|
27 |
+
"eval_loss": 0.5090050101280212,
|
28 |
+
"eval_matthews_correlation": 0.3611067385212146,
|
29 |
+
"eval_runtime": 28.3466,
|
30 |
+
"eval_samples_per_second": 36.794,
|
31 |
+
"eval_steps_per_second": 2.328,
|
32 |
+
"step": 1069
|
33 |
+
}
|
34 |
+
],
|
35 |
+
"logging_steps": 500,
|
36 |
+
"max_steps": 2138,
|
37 |
+
"num_input_tokens_seen": 0,
|
38 |
+
"num_train_epochs": 2,
|
39 |
+
"save_steps": 500,
|
40 |
+
"total_flos": 37680765508320.0,
|
41 |
+
"train_batch_size": 8,
|
42 |
+
"trial_name": null,
|
43 |
+
"trial_params": {
|
44 |
+
"learning_rate": 6.749482033934521e-05,
|
45 |
+
"num_train_epochs": 2,
|
46 |
+
"per_device_train_batch_size": 8,
|
47 |
+
"seed": 25
|
48 |
+
}
|
49 |
+
}
|
run-1/checkpoint-1069/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86af0a103816c5520416e0097dd89d50a07cbde39cfa749f0effccd48467f774
|
3 |
+
size 5048
|
run-1/checkpoint-1069/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/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": "4.40.0",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-1/checkpoint-2138/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cec4ce1d2b9f76db5a8dedca630e6f833ee08905c7efdc3173e0d174c1130648
|
3 |
+
size 267832560
|
run-1/checkpoint-2138/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6de591f08904fd53e4c847c659bc95a41069c1f0c2b910487b6da18ed83ff7a
|
3 |
+
size 535724410
|
run-1/checkpoint-2138/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e37bb18caef6eb447741eff7ae91dfd3fcfa8bc8a63135e1f691bb2da338921c
|
3 |
+
size 14054
|
run-1/checkpoint-2138/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6da3a89515b59dff37c5a264b589ef20e97716e0f62e87efd04721694227d277
|
3 |
+
size 1064
|
run-1/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-1/checkpoint-2138/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/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": 1000000000000000019884624838656,
|
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-2138/trainer_state.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4546806571399457,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2138",
|
4 |
+
"epoch": 2.0,
|
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": 0.4677268475210477,
|
13 |
+
"grad_norm": 2.976968765258789,
|
14 |
+
"learning_rate": 5.1710250568684506e-05,
|
15 |
+
"loss": 0.5872,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.9354536950420954,
|
20 |
+
"grad_norm": 3.4058539867401123,
|
21 |
+
"learning_rate": 3.592568079802378e-05,
|
22 |
+
"loss": 0.5491,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.0,
|
27 |
+
"eval_loss": 0.5090050101280212,
|
28 |
+
"eval_matthews_correlation": 0.3611067385212146,
|
29 |
+
"eval_runtime": 28.3466,
|
30 |
+
"eval_samples_per_second": 36.794,
|
31 |
+
"eval_steps_per_second": 2.328,
|
32 |
+
"step": 1069
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.4031805425631432,
|
36 |
+
"grad_norm": 5.668572902679443,
|
37 |
+
"learning_rate": 2.014111102736307e-05,
|
38 |
+
"loss": 0.3878,
|
39 |
+
"step": 1500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.8709073900841908,
|
43 |
+
"grad_norm": 1.8915776014328003,
|
44 |
+
"learning_rate": 4.3565412567023575e-06,
|
45 |
+
"loss": 0.3562,
|
46 |
+
"step": 2000
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 2.0,
|
50 |
+
"eval_loss": 0.5790878534317017,
|
51 |
+
"eval_matthews_correlation": 0.4546806571399457,
|
52 |
+
"eval_runtime": 29.1964,
|
53 |
+
"eval_samples_per_second": 35.724,
|
54 |
+
"eval_steps_per_second": 2.261,
|
55 |
+
"step": 2138
|
56 |
+
}
|
57 |
+
],
|
58 |
+
"logging_steps": 500,
|
59 |
+
"max_steps": 2138,
|
60 |
+
"num_input_tokens_seen": 0,
|
61 |
+
"num_train_epochs": 2,
|
62 |
+
"save_steps": 500,
|
63 |
+
"total_flos": 75350923275732.0,
|
64 |
+
"train_batch_size": 8,
|
65 |
+
"trial_name": null,
|
66 |
+
"trial_params": {
|
67 |
+
"learning_rate": 6.749482033934521e-05,
|
68 |
+
"num_train_epochs": 2,
|
69 |
+
"per_device_train_batch_size": 8,
|
70 |
+
"seed": 25
|
71 |
+
}
|
72 |
+
}
|
run-1/checkpoint-2138/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86af0a103816c5520416e0097dd89d50a07cbde39cfa749f0effccd48467f774
|
3 |
+
size 5048
|
run-1/checkpoint-2138/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-2138/config.json
CHANGED
@@ -20,6 +20,6 @@
|
|
20 |
"sinusoidal_pos_embds": false,
|
21 |
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.
|
24 |
"vocab_size": 30522
|
25 |
}
|
|
|
20 |
"sinusoidal_pos_embds": false,
|
21 |
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.0",
|
24 |
"vocab_size": 30522
|
25 |
}
|
run-2/checkpoint-2138/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 sha256:2292682bda06383e4668b0f29444519a7ce7f188949e7579abc9eba8b70995bd
|
3 |
size 267832560
|
run-2/checkpoint-2138/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535724410
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38d9932cadcc72e99b583551907c150e219d3002dac2a084260e2fc459be870c
|
3 |
size 535724410
|
run-2/checkpoint-2138/rng_state.pth
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 sha256:22a50707598de04408565ca20d1c05f242653f0f6139d0cfac55909f5c83c345
|
3 |
+
size 13990
|
run-2/checkpoint-2138/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fc268b5b567f4a019701f42c405b694232d88ed3e059f86b8fab8ae11c200b7
|
3 |
size 1064
|
run-2/checkpoint-2138/tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 512,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
run-2/checkpoint-2138/tokenizer_config.json
CHANGED
@@ -45,7 +45,7 @@
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
-
"model_max_length":
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 1000000000000000019884624838656,
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
run-2/checkpoint-2138/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-2138",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
@@ -9,55 +9,55 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 0.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate": 6.
|
22 |
-
"loss": 0.
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 0.
|
27 |
-
"grad_norm":
|
28 |
-
"learning_rate": 5.
|
29 |
-
"loss": 0.
|
30 |
"step": 1500
|
31 |
},
|
32 |
{
|
33 |
-
"epoch": 0.
|
34 |
-
"grad_norm":
|
35 |
-
"learning_rate":
|
36 |
-
"loss": 0.
|
37 |
"step": 2000
|
38 |
},
|
39 |
{
|
40 |
"epoch": 1.0,
|
41 |
-
"eval_loss": 0.
|
42 |
-
"eval_matthews_correlation": 0.
|
43 |
-
"eval_runtime":
|
44 |
-
"eval_samples_per_second":
|
45 |
-
"eval_steps_per_second": 2.
|
46 |
"step": 2138
|
47 |
}
|
48 |
],
|
49 |
"logging_steps": 500,
|
50 |
-
"max_steps":
|
51 |
"num_input_tokens_seen": 0,
|
52 |
-
"num_train_epochs":
|
53 |
"save_steps": 500,
|
54 |
-
"total_flos":
|
55 |
"train_batch_size": 4,
|
56 |
"trial_name": null,
|
57 |
"trial_params": {
|
58 |
-
"learning_rate":
|
59 |
-
"num_train_epochs":
|
60 |
"per_device_train_batch_size": 4,
|
61 |
-
"seed":
|
62 |
}
|
63 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.42239354524181305,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-2138",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.23386342376052385,
|
13 |
+
"grad_norm": 6.864675998687744,
|
14 |
+
"learning_rate": 7.257742157959134e-06,
|
15 |
+
"loss": 0.6169,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.4677268475210477,
|
20 |
+
"grad_norm": 18.30718421936035,
|
21 |
+
"learning_rate": 6.296706384924291e-06,
|
22 |
+
"loss": 0.5397,
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.7015902712815716,
|
27 |
+
"grad_norm": 14.399059295654297,
|
28 |
+
"learning_rate": 5.335670611889448e-06,
|
29 |
+
"loss": 0.5124,
|
30 |
"step": 1500
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 0.9354536950420954,
|
34 |
+
"grad_norm": 33.269954681396484,
|
35 |
+
"learning_rate": 4.3746348388546045e-06,
|
36 |
+
"loss": 0.5342,
|
37 |
"step": 2000
|
38 |
},
|
39 |
{
|
40 |
"epoch": 1.0,
|
41 |
+
"eval_loss": 0.543093740940094,
|
42 |
+
"eval_matthews_correlation": 0.42239354524181305,
|
43 |
+
"eval_runtime": 28.1501,
|
44 |
+
"eval_samples_per_second": 37.051,
|
45 |
+
"eval_steps_per_second": 2.345,
|
46 |
"step": 2138
|
47 |
}
|
48 |
],
|
49 |
"logging_steps": 500,
|
50 |
+
"max_steps": 4276,
|
51 |
"num_input_tokens_seen": 0,
|
52 |
+
"num_train_epochs": 2,
|
53 |
"save_steps": 500,
|
54 |
+
"total_flos": 32740145499072.0,
|
55 |
"train_batch_size": 4,
|
56 |
"trial_name": null,
|
57 |
"trial_params": {
|
58 |
+
"learning_rate": 8.218777930993977e-06,
|
59 |
+
"num_train_epochs": 2,
|
60 |
"per_device_train_batch_size": 4,
|
61 |
+
"seed": 38
|
62 |
}
|
63 |
}
|
run-2/checkpoint-2138/training_args.bin
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 sha256:52a3b2e1ec5a1c8f67e0f69b146b5cfc61a90f4dd76ed7c7f6e062bc7284397e
|
3 |
+
size 5048
|
runs/Apr23_13-58-51_309eb7d6022b/events.out.tfevents.1713888517.309eb7d6022b.9612.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d78acdc914cfc78e7d15bbfcf5050104d0377f4dbc5f34b09d9315e64803d3f1
|
3 |
+
size 6517
|
runs/Apr23_13-58-51_309eb7d6022b/events.out.tfevents.1713891455.309eb7d6022b.9612.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65bf00178bc1f8c40047d100076acb7b102065294378fdaf2cda23e9c08234dc
|
3 |
+
size 5828
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52a3b2e1ec5a1c8f67e0f69b146b5cfc61a90f4dd76ed7c7f6e062bc7284397e
|
3 |
size 5048
|