GIanlucaRub
commited on
Commit
•
52316d7
1
Parent(s):
1ea194a
updated
Browse files- checkpoint-2976/config.json +35 -0
- checkpoint-2976/optimizer.pt +3 -0
- checkpoint-2976/pytorch_model.bin +3 -0
- checkpoint-2976/rng_state.pth +3 -0
- checkpoint-2976/scheduler.pt +3 -0
- checkpoint-2976/special_tokens_map.json +7 -0
- checkpoint-2976/tokenizer.json +0 -0
- checkpoint-2976/tokenizer_config.json +14 -0
- checkpoint-2976/trainer_state.json +46 -0
- checkpoint-2976/training_args.bin +3 -0
- checkpoint-2976/vocab.txt +0 -0
- checkpoint-5952/config.json +35 -0
- checkpoint-5952/optimizer.pt +3 -0
- checkpoint-5952/pytorch_model.bin +3 -0
- checkpoint-5952/rng_state.pth +3 -0
- checkpoint-5952/scheduler.pt +3 -0
- checkpoint-5952/special_tokens_map.json +7 -0
- checkpoint-5952/tokenizer.json +0 -0
- checkpoint-5952/tokenizer_config.json +14 -0
- checkpoint-5952/trainer_state.json +82 -0
- checkpoint-5952/training_args.bin +3 -0
- checkpoint-5952/vocab.txt +0 -0
checkpoint-2976/config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0,
|
19 |
+
"LABEL_1": 1,
|
20 |
+
"LABEL_2": 2
|
21 |
+
},
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "distilbert",
|
24 |
+
"n_heads": 12,
|
25 |
+
"n_layers": 6,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"problem_type": "single_label_classification",
|
28 |
+
"qa_dropout": 0.1,
|
29 |
+
"seq_classif_dropout": 0.2,
|
30 |
+
"sinusoidal_pos_embds": false,
|
31 |
+
"tie_weights_": true,
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.25.1",
|
34 |
+
"vocab_size": 30522
|
35 |
+
}
|
checkpoint-2976/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35627352e081a94eafbb0da4cf49340248d1e2a134c7aec170f380ecc160cb53
|
3 |
+
size 535707205
|
checkpoint-2976/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6289bfd4e488b5449457e402c23f42af477bd7b81c2bf27cd7bf4ab40aa866f
|
3 |
+
size 267858605
|
checkpoint-2976/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:707f8ff492be0f55e7f91751a1e00e78dde2263a56aaee154128b61462fd9c2d
|
3 |
+
size 14575
|
checkpoint-2976/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08533d345770655c6aa6aa0f020790fe1e56b762ec1040db15952c75171766fc
|
3 |
+
size 627
|
checkpoint-2976/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 |
+
}
|
checkpoint-2976/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2976/tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "distilbert-base-uncased",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "DistilBertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
checkpoint-2976/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 2976,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.17,
|
12 |
+
"learning_rate": 1.831989247311828e-05,
|
13 |
+
"loss": 0.6085,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.34,
|
18 |
+
"learning_rate": 1.663978494623656e-05,
|
19 |
+
"loss": 0.6656,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.5,
|
24 |
+
"learning_rate": 1.4959677419354839e-05,
|
25 |
+
"loss": 0.6649,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.67,
|
30 |
+
"learning_rate": 1.3279569892473118e-05,
|
31 |
+
"loss": 0.6354,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.84,
|
36 |
+
"learning_rate": 1.1599462365591398e-05,
|
37 |
+
"loss": 0.6208,
|
38 |
+
"step": 2500
|
39 |
+
}
|
40 |
+
],
|
41 |
+
"max_steps": 5952,
|
42 |
+
"num_train_epochs": 2,
|
43 |
+
"total_flos": 564640713514710.0,
|
44 |
+
"trial_name": null,
|
45 |
+
"trial_params": null
|
46 |
+
}
|
checkpoint-2976/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67c08a7bf2ed8903ca1336500ecc6f4f4e7dd6055e2674f9a6f97f9af9ca9dc0
|
3 |
+
size 3451
|
checkpoint-2976/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-5952/config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0,
|
19 |
+
"LABEL_1": 1,
|
20 |
+
"LABEL_2": 2
|
21 |
+
},
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "distilbert",
|
24 |
+
"n_heads": 12,
|
25 |
+
"n_layers": 6,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"problem_type": "single_label_classification",
|
28 |
+
"qa_dropout": 0.1,
|
29 |
+
"seq_classif_dropout": 0.2,
|
30 |
+
"sinusoidal_pos_embds": false,
|
31 |
+
"tie_weights_": true,
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.25.1",
|
34 |
+
"vocab_size": 30522
|
35 |
+
}
|
checkpoint-5952/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82762aefe5b3d6f5ebd4a21bbd2133ab24b25177b1419b31a601af134b038c53
|
3 |
+
size 535707205
|
checkpoint-5952/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:207561cee7eee177c05892fbdf39ec05db73fc2cac883b6b1545a1ee1bfba7dc
|
3 |
+
size 267858605
|
checkpoint-5952/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:554f7cd9102172a98939d889979a27e4d0e91c2f385f3690da30d7cf4ff95425
|
3 |
+
size 14575
|
checkpoint-5952/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcf86e2e568732acfe875975d84ecca5bf05ab67424b6af65470f2d290ad731e
|
3 |
+
size 627
|
checkpoint-5952/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 |
+
}
|
checkpoint-5952/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-5952/tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "distilbert-base-uncased",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "DistilBertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
checkpoint-5952/trainer_state.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 5952,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.17,
|
12 |
+
"learning_rate": 1.831989247311828e-05,
|
13 |
+
"loss": 0.6085,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.34,
|
18 |
+
"learning_rate": 1.663978494623656e-05,
|
19 |
+
"loss": 0.6656,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.5,
|
24 |
+
"learning_rate": 1.4959677419354839e-05,
|
25 |
+
"loss": 0.6649,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.67,
|
30 |
+
"learning_rate": 1.3279569892473118e-05,
|
31 |
+
"loss": 0.6354,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.84,
|
36 |
+
"learning_rate": 1.1599462365591398e-05,
|
37 |
+
"loss": 0.6208,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.01,
|
42 |
+
"learning_rate": 9.919354838709679e-06,
|
43 |
+
"loss": 0.6138,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.18,
|
48 |
+
"learning_rate": 8.239247311827959e-06,
|
49 |
+
"loss": 0.5066,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.34,
|
54 |
+
"learning_rate": 6.5591397849462365e-06,
|
55 |
+
"loss": 0.4947,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.51,
|
60 |
+
"learning_rate": 4.879032258064517e-06,
|
61 |
+
"loss": 0.4856,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.68,
|
66 |
+
"learning_rate": 3.198924731182796e-06,
|
67 |
+
"loss": 0.4776,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.85,
|
72 |
+
"learning_rate": 1.5188172043010754e-06,
|
73 |
+
"loss": 0.4842,
|
74 |
+
"step": 5500
|
75 |
+
}
|
76 |
+
],
|
77 |
+
"max_steps": 5952,
|
78 |
+
"num_train_epochs": 2,
|
79 |
+
"total_flos": 1129973529784770.0,
|
80 |
+
"trial_name": null,
|
81 |
+
"trial_params": null
|
82 |
+
}
|
checkpoint-5952/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67c08a7bf2ed8903ca1336500ecc6f4f4e7dd6055e2674f9a6f97f9af9ca9dc0
|
3 |
+
size 3451
|
checkpoint-5952/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|