SjardiWillems
commited on
Commit
•
e3f7f77
1
Parent(s):
b4b2e11
Training in progress, epoch 1
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- model.safetensors +1 -1
- run-1/checkpoint-108/config.json +25 -0
- run-1/checkpoint-108/model.safetensors +3 -0
- run-1/checkpoint-108/optimizer.pt +3 -0
- run-1/checkpoint-108/rng_state.pth +3 -0
- run-1/checkpoint-108/scheduler.pt +3 -0
- run-1/checkpoint-108/special_tokens_map.json +7 -0
- run-1/checkpoint-108/tokenizer.json +0 -0
- run-1/checkpoint-108/tokenizer_config.json +55 -0
- run-1/checkpoint-108/trainer_state.json +62 -0
- run-1/checkpoint-108/training_args.bin +3 -0
- run-1/checkpoint-108/vocab.txt +0 -0
- run-1/checkpoint-135/config.json +25 -0
- run-1/checkpoint-135/model.safetensors +3 -0
- run-1/checkpoint-135/optimizer.pt +3 -0
- run-1/checkpoint-135/rng_state.pth +3 -0
- run-1/checkpoint-135/scheduler.pt +3 -0
- run-1/checkpoint-135/special_tokens_map.json +7 -0
- run-1/checkpoint-135/tokenizer.json +0 -0
- run-1/checkpoint-135/tokenizer_config.json +55 -0
- run-1/checkpoint-135/trainer_state.json +71 -0
- run-1/checkpoint-135/training_args.bin +3 -0
- run-1/checkpoint-135/vocab.txt +0 -0
- run-1/checkpoint-54/config.json +25 -0
- run-1/checkpoint-54/model.safetensors +3 -0
- run-1/checkpoint-54/optimizer.pt +3 -0
- run-1/checkpoint-54/rng_state.pth +3 -0
- run-1/checkpoint-54/scheduler.pt +3 -0
- run-1/checkpoint-54/special_tokens_map.json +7 -0
- run-1/checkpoint-54/tokenizer.json +0 -0
- run-1/checkpoint-54/tokenizer_config.json +55 -0
- run-1/checkpoint-54/trainer_state.json +44 -0
- run-1/checkpoint-54/training_args.bin +3 -0
- run-1/checkpoint-54/vocab.txt +0 -0
- run-1/checkpoint-81/config.json +25 -0
- run-1/checkpoint-81/model.safetensors +3 -0
- run-1/checkpoint-81/optimizer.pt +3 -0
- run-1/checkpoint-81/rng_state.pth +3 -0
- run-1/checkpoint-81/scheduler.pt +3 -0
- run-1/checkpoint-81/special_tokens_map.json +7 -0
- run-1/checkpoint-81/tokenizer.json +0 -0
- run-1/checkpoint-81/tokenizer_config.json +55 -0
- run-1/checkpoint-81/trainer_state.json +53 -0
- run-1/checkpoint-81/training_args.bin +3 -0
- run-1/checkpoint-81/vocab.txt +0 -0
- run-2/checkpoint-27/config.json +25 -0
- run-2/checkpoint-27/model.safetensors +3 -0
- run-2/checkpoint-27/optimizer.pt +3 -0
- run-2/checkpoint-27/rng_state.pth +3 -0
- run-2/checkpoint-27/scheduler.pt +3 -0
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deb089e9ac2ba3e9bfee178463e0a5351fb79b4046211f6167830b3a160bf33d
|
3 |
size 267832560
|
run-1/checkpoint-108/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-1/checkpoint-108/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53a75a52c0a7268f698d6028850e95d4059b79b6994ea0a0a71f12991834f65e
|
3 |
+
size 267832560
|
run-1/checkpoint-108/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b733375cf7e51f52c587ff5c5803a525efda32f0f6b325493a7f65cefb9a35c2
|
3 |
+
size 535727290
|
run-1/checkpoint-108/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ff88cf6a68b56a9a8b1365826b59af04bc94bfa1a61a887391b00cc10709cf9
|
3 |
+
size 14244
|
run-1/checkpoint-108/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ba816e802e5059259aa15c86b6b47a6552618fdf5b523e3aeecc033159818c7
|
3 |
+
size 1064
|
run-1/checkpoint-108/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-1/checkpoint-108/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-108/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-1/checkpoint-108/trainer_state.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3259325330443582,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-108",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 108,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.6137323379516602,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4985,
|
16 |
+
"eval_samples_per_second": 2092.402,
|
17 |
+
"eval_steps_per_second": 132.405,
|
18 |
+
"step": 27
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.5712264180183411,
|
23 |
+
"eval_matthews_correlation": 0.20590544441185202,
|
24 |
+
"eval_runtime": 0.5232,
|
25 |
+
"eval_samples_per_second": 1993.581,
|
26 |
+
"eval_steps_per_second": 126.152,
|
27 |
+
"step": 54
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.5899873375892639,
|
32 |
+
"eval_matthews_correlation": 0.2957275464729565,
|
33 |
+
"eval_runtime": 0.6455,
|
34 |
+
"eval_samples_per_second": 1615.69,
|
35 |
+
"eval_steps_per_second": 102.239,
|
36 |
+
"step": 81
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_loss": 0.6281552314758301,
|
41 |
+
"eval_matthews_correlation": 0.3259325330443582,
|
42 |
+
"eval_runtime": 0.7017,
|
43 |
+
"eval_samples_per_second": 1486.423,
|
44 |
+
"eval_steps_per_second": 94.059,
|
45 |
+
"step": 108
|
46 |
+
}
|
47 |
+
],
|
48 |
+
"logging_steps": 500,
|
49 |
+
"max_steps": 135,
|
50 |
+
"num_input_tokens_seen": 0,
|
51 |
+
"num_train_epochs": 5,
|
52 |
+
"save_steps": 500,
|
53 |
+
"total_flos": 0,
|
54 |
+
"train_batch_size": 32,
|
55 |
+
"trial_name": null,
|
56 |
+
"trial_params": {
|
57 |
+
"learning_rate": 3.5363396216788776e-05,
|
58 |
+
"num_train_epochs": 5,
|
59 |
+
"per_device_train_batch_size": 32,
|
60 |
+
"seed": 2
|
61 |
+
}
|
62 |
+
}
|
run-1/checkpoint-108/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33b56f1742238d2f06643824383acf821a96e3f5c733d93be775d8db9f771896
|
3 |
+
size 4984
|
run-1/checkpoint-108/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-135/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-1/checkpoint-135/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c82f13f2ffe3e258baf546b925aed6f69d842a0285c747dff3b90edb0605eaa1
|
3 |
+
size 267832560
|
run-1/checkpoint-135/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6f9cdf2fdac0ef72c700f84956d35c76a99f1cddb69d7637cc66d92b60bd997
|
3 |
+
size 535727290
|
run-1/checkpoint-135/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d71ce280b59c0b5bf314439e654a2e5adb6bf73532c3af560e8f2a715df608b9
|
3 |
+
size 14244
|
run-1/checkpoint-135/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40abd27c087f798d42969f78042a3adc0c480e02268f7be72034aadba2dc6d2d
|
3 |
+
size 1064
|
run-1/checkpoint-135/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-135/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-135/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-135/trainer_state.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3367711412058402,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-135",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 135,
|
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": 0.6137323379516602,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4985,
|
16 |
+
"eval_samples_per_second": 2092.402,
|
17 |
+
"eval_steps_per_second": 132.405,
|
18 |
+
"step": 27
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.5712264180183411,
|
23 |
+
"eval_matthews_correlation": 0.20590544441185202,
|
24 |
+
"eval_runtime": 0.5232,
|
25 |
+
"eval_samples_per_second": 1993.581,
|
26 |
+
"eval_steps_per_second": 126.152,
|
27 |
+
"step": 54
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.5899873375892639,
|
32 |
+
"eval_matthews_correlation": 0.2957275464729565,
|
33 |
+
"eval_runtime": 0.6455,
|
34 |
+
"eval_samples_per_second": 1615.69,
|
35 |
+
"eval_steps_per_second": 102.239,
|
36 |
+
"step": 81
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_loss": 0.6281552314758301,
|
41 |
+
"eval_matthews_correlation": 0.3259325330443582,
|
42 |
+
"eval_runtime": 0.7017,
|
43 |
+
"eval_samples_per_second": 1486.423,
|
44 |
+
"eval_steps_per_second": 94.059,
|
45 |
+
"step": 108
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 5.0,
|
49 |
+
"eval_loss": 0.6593989133834839,
|
50 |
+
"eval_matthews_correlation": 0.3367711412058402,
|
51 |
+
"eval_runtime": 0.6019,
|
52 |
+
"eval_samples_per_second": 1732.92,
|
53 |
+
"eval_steps_per_second": 109.657,
|
54 |
+
"step": 135
|
55 |
+
}
|
56 |
+
],
|
57 |
+
"logging_steps": 500,
|
58 |
+
"max_steps": 135,
|
59 |
+
"num_input_tokens_seen": 0,
|
60 |
+
"num_train_epochs": 5,
|
61 |
+
"save_steps": 500,
|
62 |
+
"total_flos": 0,
|
63 |
+
"train_batch_size": 32,
|
64 |
+
"trial_name": null,
|
65 |
+
"trial_params": {
|
66 |
+
"learning_rate": 3.5363396216788776e-05,
|
67 |
+
"num_train_epochs": 5,
|
68 |
+
"per_device_train_batch_size": 32,
|
69 |
+
"seed": 2
|
70 |
+
}
|
71 |
+
}
|
run-1/checkpoint-135/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33b56f1742238d2f06643824383acf821a96e3f5c733d93be775d8db9f771896
|
3 |
+
size 4984
|
run-1/checkpoint-135/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-54/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-1/checkpoint-54/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:443ae768410c4fb2d7ac4bd28230ec79548e32b2fef7218cbd6cef4849ba28b5
|
3 |
+
size 267832560
|
run-1/checkpoint-54/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f48c12561980a6f7606aa5a6094d774b5041cc67abef4c3ee878e74e75ce137d
|
3 |
+
size 535727290
|
run-1/checkpoint-54/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bb45759d8cea5911373367bfb22f024d61f1e28d37295d2d156220ad1753b38
|
3 |
+
size 14244
|
run-1/checkpoint-54/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12b0e838a1115a2488b71e779082dce7fb4703100879bd16d20444069ee44909
|
3 |
+
size 1064
|
run-1/checkpoint-54/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-1/checkpoint-54/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-54/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-1/checkpoint-54/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.20590544441185202,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-54",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 54,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.6137323379516602,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4985,
|
16 |
+
"eval_samples_per_second": 2092.402,
|
17 |
+
"eval_steps_per_second": 132.405,
|
18 |
+
"step": 27
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.5712264180183411,
|
23 |
+
"eval_matthews_correlation": 0.20590544441185202,
|
24 |
+
"eval_runtime": 0.5232,
|
25 |
+
"eval_samples_per_second": 1993.581,
|
26 |
+
"eval_steps_per_second": 126.152,
|
27 |
+
"step": 54
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 135,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 5,
|
34 |
+
"save_steps": 500,
|
35 |
+
"total_flos": 0,
|
36 |
+
"train_batch_size": 32,
|
37 |
+
"trial_name": null,
|
38 |
+
"trial_params": {
|
39 |
+
"learning_rate": 3.5363396216788776e-05,
|
40 |
+
"num_train_epochs": 5,
|
41 |
+
"per_device_train_batch_size": 32,
|
42 |
+
"seed": 2
|
43 |
+
}
|
44 |
+
}
|
run-1/checkpoint-54/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33b56f1742238d2f06643824383acf821a96e3f5c733d93be775d8db9f771896
|
3 |
+
size 4984
|
run-1/checkpoint-54/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-81/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-1/checkpoint-81/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0799e5e610ad0116f53bd17357767c01b076f46a18d772057f6b2653d584e627
|
3 |
+
size 267832560
|
run-1/checkpoint-81/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56b47699f830504629604f4f31a2ec86a017c413c509659031f0cb32be70b49d
|
3 |
+
size 535727290
|
run-1/checkpoint-81/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e81c15a5ddd399b2a78a78e88aad4d8d0f73ebd73da31f6ab83057c2144aba58
|
3 |
+
size 14244
|
run-1/checkpoint-81/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f2ee9e092517bb12bff1a95437f075d2739c9b5ba04c75f12d1f0e4d2e911d7
|
3 |
+
size 1064
|
run-1/checkpoint-81/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-81/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-81/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-81/trainer_state.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.2957275464729565,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-81",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 81,
|
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": 0.6137323379516602,
|
14 |
+
"eval_matthews_correlation": 0.0,
|
15 |
+
"eval_runtime": 0.4985,
|
16 |
+
"eval_samples_per_second": 2092.402,
|
17 |
+
"eval_steps_per_second": 132.405,
|
18 |
+
"step": 27
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_loss": 0.5712264180183411,
|
23 |
+
"eval_matthews_correlation": 0.20590544441185202,
|
24 |
+
"eval_runtime": 0.5232,
|
25 |
+
"eval_samples_per_second": 1993.581,
|
26 |
+
"eval_steps_per_second": 126.152,
|
27 |
+
"step": 54
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_loss": 0.5899873375892639,
|
32 |
+
"eval_matthews_correlation": 0.2957275464729565,
|
33 |
+
"eval_runtime": 0.6455,
|
34 |
+
"eval_samples_per_second": 1615.69,
|
35 |
+
"eval_steps_per_second": 102.239,
|
36 |
+
"step": 81
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"logging_steps": 500,
|
40 |
+
"max_steps": 135,
|
41 |
+
"num_input_tokens_seen": 0,
|
42 |
+
"num_train_epochs": 5,
|
43 |
+
"save_steps": 500,
|
44 |
+
"total_flos": 0,
|
45 |
+
"train_batch_size": 32,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": {
|
48 |
+
"learning_rate": 3.5363396216788776e-05,
|
49 |
+
"num_train_epochs": 5,
|
50 |
+
"per_device_train_batch_size": 32,
|
51 |
+
"seed": 2
|
52 |
+
}
|
53 |
+
}
|
run-1/checkpoint-81/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33b56f1742238d2f06643824383acf821a96e3f5c733d93be775d8db9f771896
|
3 |
+
size 4984
|
run-1/checkpoint-81/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-27/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-2/checkpoint-27/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deb089e9ac2ba3e9bfee178463e0a5351fb79b4046211f6167830b3a160bf33d
|
3 |
+
size 267832560
|
run-2/checkpoint-27/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9516b058e496477f19f51008db1771b000eaf246f9e98c490d8a5ab51f6be89
|
3 |
+
size 535727290
|
run-2/checkpoint-27/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23e4eac4ccb653df691c572046a6c191bf2e41b96f073d92f8e06f4ada58c10e
|
3 |
+
size 14244
|
run-2/checkpoint-27/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1004f35ea8de92c80186b5611f92fa28944e8ce2152f4d8a62ae02fcaacd2f9c
|
3 |
+
size 1064
|