Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-1134/config.json +30 -0
- checkpoint-1134/optimizer.pt +3 -0
- checkpoint-1134/pytorch_model.bin +3 -0
- checkpoint-1134/rng_state.pth +3 -0
- checkpoint-1134/scheduler.pt +3 -0
- checkpoint-1134/trainer_state.json +0 -0
- checkpoint-1134/training_args.bin +3 -0
- checkpoint-1512/config.json +30 -0
- checkpoint-1512/optimizer.pt +3 -0
- checkpoint-1512/pytorch_model.bin +3 -0
- checkpoint-1512/rng_state.pth +3 -0
- checkpoint-1512/scheduler.pt +3 -0
- checkpoint-1512/trainer_state.json +0 -0
- checkpoint-1512/training_args.bin +3 -0
- checkpoint-1890/config.json +30 -0
- checkpoint-1890/optimizer.pt +3 -0
- checkpoint-1890/pytorch_model.bin +3 -0
- checkpoint-1890/rng_state.pth +3 -0
- checkpoint-1890/scheduler.pt +3 -0
- checkpoint-1890/trainer_state.json +0 -0
- checkpoint-1890/training_args.bin +3 -0
- checkpoint-2268/config.json +30 -0
- checkpoint-2268/optimizer.pt +3 -0
- checkpoint-2268/pytorch_model.bin +3 -0
- checkpoint-2268/rng_state.pth +3 -0
- checkpoint-2268/scheduler.pt +3 -0
- checkpoint-2268/trainer_state.json +0 -0
- checkpoint-2268/training_args.bin +3 -0
- checkpoint-2646/config.json +30 -0
- checkpoint-2646/optimizer.pt +3 -0
- checkpoint-2646/pytorch_model.bin +3 -0
- checkpoint-2646/rng_state.pth +3 -0
- checkpoint-2646/scheduler.pt +3 -0
- checkpoint-2646/trainer_state.json +0 -0
- checkpoint-2646/training_args.bin +3 -0
- checkpoint-3024/config.json +30 -0
- checkpoint-3024/optimizer.pt +3 -0
- checkpoint-3024/pytorch_model.bin +3 -0
- checkpoint-3024/rng_state.pth +3 -0
- checkpoint-3024/scheduler.pt +3 -0
- checkpoint-3024/trainer_state.json +0 -0
- checkpoint-3024/training_args.bin +3 -0
- checkpoint-3402/config.json +30 -0
- checkpoint-3402/optimizer.pt +3 -0
- checkpoint-3402/pytorch_model.bin +3 -0
- checkpoint-3402/rng_state.pth +3 -0
- checkpoint-3402/scheduler.pt +3 -0
- checkpoint-3402/trainer_state.json +0 -0
- checkpoint-3402/training_args.bin +3 -0
- checkpoint-378/config.json +30 -0
checkpoint-1134/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
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": "NO DISASTER",
|
13 |
+
"1": "DISASTER"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "distilbert",
|
18 |
+
"n_heads": 12,
|
19 |
+
"n_layers": 6,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"qa_dropout": 0.1,
|
24 |
+
"seq_classif_dropout": 0.2,
|
25 |
+
"sinusoidal_pos_embds": false,
|
26 |
+
"tie_weights_": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.30.2",
|
29 |
+
"vocab_size": 28996
|
30 |
+
}
|
checkpoint-1134/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:288a3a2153c0322b4276e669c96adb82618323aa14dd22a877cdc10d5ff281fc
|
3 |
+
size 526325317
|
checkpoint-1134/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf607644ed3f532ddfcf22bf3b6b096f6d857686842d3ded36af6cf515d24b7c
|
3 |
+
size 263167661
|
checkpoint-1134/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:589ad13af77107a97b9c7365d87d9e8ab0ae8d444ec08c6f1b85dafe8552374c
|
3 |
+
size 14575
|
checkpoint-1134/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6c1f9635b56ab51528d4beb03bca865e6a9a33739312547fb70a929ef992f64
|
3 |
+
size 627
|
checkpoint-1134/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1134/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7c01d8e107b4a20c0ba0f3692dae4e25d8f1dffe1d23d6e4f4bdf92b87ab5ea
|
3 |
+
size 3899
|
checkpoint-1512/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
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": "NO DISASTER",
|
13 |
+
"1": "DISASTER"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "distilbert",
|
18 |
+
"n_heads": 12,
|
19 |
+
"n_layers": 6,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"qa_dropout": 0.1,
|
24 |
+
"seq_classif_dropout": 0.2,
|
25 |
+
"sinusoidal_pos_embds": false,
|
26 |
+
"tie_weights_": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.30.2",
|
29 |
+
"vocab_size": 28996
|
30 |
+
}
|
checkpoint-1512/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87ce52713400f327c5fd03cd733de4a3969a3062515aba0904a292f02e98fe96
|
3 |
+
size 526325317
|
checkpoint-1512/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c453f3f6a59f2ec8da836d5fdb537bd870363dc090f30d9341e30fb9a06987b
|
3 |
+
size 263167661
|
checkpoint-1512/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4652bd48bb7c106c661fd71929aac1388a67e4cd1e78571ff090909c5e7dc7d0
|
3 |
+
size 14575
|
checkpoint-1512/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08dda3a4f935a7a4b13455d1b343f791c393a17cccb53664b36097e59734998c
|
3 |
+
size 627
|
checkpoint-1512/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1512/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7c01d8e107b4a20c0ba0f3692dae4e25d8f1dffe1d23d6e4f4bdf92b87ab5ea
|
3 |
+
size 3899
|
checkpoint-1890/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
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": "NO DISASTER",
|
13 |
+
"1": "DISASTER"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "distilbert",
|
18 |
+
"n_heads": 12,
|
19 |
+
"n_layers": 6,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"qa_dropout": 0.1,
|
24 |
+
"seq_classif_dropout": 0.2,
|
25 |
+
"sinusoidal_pos_embds": false,
|
26 |
+
"tie_weights_": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.30.2",
|
29 |
+
"vocab_size": 28996
|
30 |
+
}
|
checkpoint-1890/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d678854dbfdcfa8b908c9332ac25c1f8ef0c3ff62cfa32314a14fdeba3398df
|
3 |
+
size 526325317
|
checkpoint-1890/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f57911e1cd736481c049e1f00b39d9c6f9570bb5e62277d1525fea2092d3ff61
|
3 |
+
size 263167661
|
checkpoint-1890/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4736e2b29a3bb716eb6278813e759366aca017726091b3748ed8a0cbd6fca255
|
3 |
+
size 14575
|
checkpoint-1890/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04b47afbdd02c26529bafa5013aad97cbb6f1bc4bbbff15fd4376d3ffddaeab4
|
3 |
+
size 627
|
checkpoint-1890/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1890/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7c01d8e107b4a20c0ba0f3692dae4e25d8f1dffe1d23d6e4f4bdf92b87ab5ea
|
3 |
+
size 3899
|
checkpoint-2268/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
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": "NO DISASTER",
|
13 |
+
"1": "DISASTER"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "distilbert",
|
18 |
+
"n_heads": 12,
|
19 |
+
"n_layers": 6,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"qa_dropout": 0.1,
|
24 |
+
"seq_classif_dropout": 0.2,
|
25 |
+
"sinusoidal_pos_embds": false,
|
26 |
+
"tie_weights_": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.30.2",
|
29 |
+
"vocab_size": 28996
|
30 |
+
}
|
checkpoint-2268/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb00801aa9d975c647b6e878986a419cd3cade5e19595bca603265b4e575932c
|
3 |
+
size 526325317
|
checkpoint-2268/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aecf74abbd12126248d1ab6b0343cb7f1a8e8ea550da4711db32b4c27f1a460b
|
3 |
+
size 263167661
|
checkpoint-2268/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a0a36e41b0f6ae09acc41f6d5ee6a72f9ef8ae9bbab3384bc65d0290dfa4975
|
3 |
+
size 14575
|
checkpoint-2268/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:587b3803bf070c7fd1a5809542f456d09391b47ebc2a66313fffa72515a3cc84
|
3 |
+
size 627
|
checkpoint-2268/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2268/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7c01d8e107b4a20c0ba0f3692dae4e25d8f1dffe1d23d6e4f4bdf92b87ab5ea
|
3 |
+
size 3899
|
checkpoint-2646/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
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": "NO DISASTER",
|
13 |
+
"1": "DISASTER"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "distilbert",
|
18 |
+
"n_heads": 12,
|
19 |
+
"n_layers": 6,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"qa_dropout": 0.1,
|
24 |
+
"seq_classif_dropout": 0.2,
|
25 |
+
"sinusoidal_pos_embds": false,
|
26 |
+
"tie_weights_": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.30.2",
|
29 |
+
"vocab_size": 28996
|
30 |
+
}
|
checkpoint-2646/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53912039cd2f47825838734a584e08d2a7dd2446c9cec942224fd1ae50de1e47
|
3 |
+
size 526325317
|
checkpoint-2646/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8689e4c6d7995e2fae60d4a7f938d919a858337c1e51bab76711830eb6f9063b
|
3 |
+
size 263167661
|
checkpoint-2646/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4efd6b59e664dd5d3e5b916b9efad5576e8242df7a17314fc41a8cf175dd2d31
|
3 |
+
size 14575
|
checkpoint-2646/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad115c008906441ed2ca379a9e36021b2662b360f7030e43093fc964b8bf0d60
|
3 |
+
size 627
|
checkpoint-2646/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2646/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7c01d8e107b4a20c0ba0f3692dae4e25d8f1dffe1d23d6e4f4bdf92b87ab5ea
|
3 |
+
size 3899
|
checkpoint-3024/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
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": "NO DISASTER",
|
13 |
+
"1": "DISASTER"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "distilbert",
|
18 |
+
"n_heads": 12,
|
19 |
+
"n_layers": 6,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"qa_dropout": 0.1,
|
24 |
+
"seq_classif_dropout": 0.2,
|
25 |
+
"sinusoidal_pos_embds": false,
|
26 |
+
"tie_weights_": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.30.2",
|
29 |
+
"vocab_size": 28996
|
30 |
+
}
|
checkpoint-3024/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4adf5995dfff43bbcf0456a8150fb2939f3bf8c44115a1f81d62b513c5962006
|
3 |
+
size 526325317
|
checkpoint-3024/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d502e804f64e2acd194387aa5fd310131d70f8506192f89f513436dc2de8916
|
3 |
+
size 263167661
|
checkpoint-3024/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab62b0bebbe356352a4069309bea70f50837588122439261bc3e8a0e6ce05c23
|
3 |
+
size 14575
|
checkpoint-3024/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9daf155d8896ce2ce99e58ebee9b511a9716e2308a91ca6e9dfd99c08653734
|
3 |
+
size 627
|
checkpoint-3024/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3024/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7c01d8e107b4a20c0ba0f3692dae4e25d8f1dffe1d23d6e4f4bdf92b87ab5ea
|
3 |
+
size 3899
|
checkpoint-3402/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
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": "NO DISASTER",
|
13 |
+
"1": "DISASTER"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "distilbert",
|
18 |
+
"n_heads": 12,
|
19 |
+
"n_layers": 6,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"qa_dropout": 0.1,
|
24 |
+
"seq_classif_dropout": 0.2,
|
25 |
+
"sinusoidal_pos_embds": false,
|
26 |
+
"tie_weights_": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.30.2",
|
29 |
+
"vocab_size": 28996
|
30 |
+
}
|
checkpoint-3402/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e85edc83ec5ffe29136a805b6f367bf7eb43dff879939b6df7aa705d88753f94
|
3 |
+
size 526325317
|
checkpoint-3402/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:212663d3b081d1c5839dc0e4fb48b43cc45e577bc88f440512f19584946b9db6
|
3 |
+
size 263167661
|
checkpoint-3402/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33e0373cf75568e9b513cbf91702bd9f246da33da5b59e14eb78b0282c54ab90
|
3 |
+
size 14575
|
checkpoint-3402/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:329ec617799a517751e41c3900a932ef850318bdb418eea4fee34fa1016db88a
|
3 |
+
size 627
|
checkpoint-3402/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3402/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7c01d8e107b4a20c0ba0f3692dae4e25d8f1dffe1d23d6e4f4bdf92b87ab5ea
|
3 |
+
size 3899
|
checkpoint-378/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-cased",
|
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": "NO DISASTER",
|
13 |
+
"1": "DISASTER"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "distilbert",
|
18 |
+
"n_heads": 12,
|
19 |
+
"n_layers": 6,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"qa_dropout": 0.1,
|
24 |
+
"seq_classif_dropout": 0.2,
|
25 |
+
"sinusoidal_pos_embds": false,
|
26 |
+
"tie_weights_": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.30.2",
|
29 |
+
"vocab_size": 28996
|
30 |
+
}
|