Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +45 -0
- pytorch_model.bin +3 -0
- runs/Jun21_22-00-16_node1462.palmetto.clemson.edu/1655863265.1974866/events.out.tfevents.1655863265.node1462.palmetto.clemson.edu.1828378.1 +3 -0
- runs/Jun21_22-00-16_node1462.palmetto.clemson.edu/events.out.tfevents.1655863261.node1462.palmetto.clemson.edu.1828378.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "yikuan8/Clinical-Longformer",
|
3 |
+
"architectures": [
|
4 |
+
"LongformerForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_mode": "longformer",
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"attention_window": [
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512
|
21 |
+
],
|
22 |
+
"bos_token_id": 0,
|
23 |
+
"classifier_dropout": null,
|
24 |
+
"eos_token_id": 2,
|
25 |
+
"gradient_checkpointing": false,
|
26 |
+
"hidden_act": "gelu",
|
27 |
+
"hidden_dropout_prob": 0.1,
|
28 |
+
"hidden_size": 768,
|
29 |
+
"ignore_attention_mask": false,
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"layer_norm_eps": 1e-05,
|
33 |
+
"max_position_embeddings": 4098,
|
34 |
+
"model_type": "longformer",
|
35 |
+
"num_attention_heads": 12,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"pad_token_id": 1,
|
38 |
+
"position_embedding_type": "absolute",
|
39 |
+
"sep_token_id": 2,
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.17.0",
|
42 |
+
"type_vocab_size": 1,
|
43 |
+
"use_cache": true,
|
44 |
+
"vocab_size": 50265
|
45 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4558719c06405b4da3130fd5d39582b898dc0e9ac6d72e9b328620df049bcb0e
|
3 |
+
size 594995866
|
runs/Jun21_22-00-16_node1462.palmetto.clemson.edu/1655863265.1974866/events.out.tfevents.1655863265.node1462.palmetto.clemson.edu.1828378.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd1ba7aae0e7379354cab641b400767fcedade3367beda1aa99b54d00a568a43
|
3 |
+
size 4815
|
runs/Jun21_22-00-16_node1462.palmetto.clemson.edu/events.out.tfevents.1655863261.node1462.palmetto.clemson.edu.1828378.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:014514a40d471ec2eb7ac6e484dc3034e59d1c34c2a54e91334b79f2f81deb86
|
3 |
+
size 4145
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdefef6e9dea5c1ca082754d020879015c1eca6664e2494392209dcff0a2ace8
|
3 |
+
size 3055
|