Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +46 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Apr16_03-57-10_784672f2512a/1650081466.1278062/events.out.tfevents.1650081466.784672f2512a.74.1 +3 -0
- runs/Apr16_03-57-10_784672f2512a/events.out.tfevents.1650081466.784672f2512a.74.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allenai/longformer-base-4096",
|
3 |
+
"architectures": [
|
4 |
+
"LongformerForSequenceClassification"
|
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 |
+
"problem_type": "single_label_classification",
|
40 |
+
"sep_token_id": 2,
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.18.0",
|
43 |
+
"type_vocab_size": 1,
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 50265
|
46 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39601b652d2fb7837003e98066a0b2b9a01401440b87cf151c71d2eeb45384f0
|
3 |
+
size 594770205
|
runs/Apr16_03-57-10_784672f2512a/1650081466.1278062/events.out.tfevents.1650081466.784672f2512a.74.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dd3b4fd3076ffbb35502b01c9d782cdeee8b726162d601603b9a77a02e6cf25
|
3 |
+
size 4813
|
runs/Apr16_03-57-10_784672f2512a/events.out.tfevents.1650081466.784672f2512a.74.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:122058606a012b5339be0469598350ee4fc7b2c81bdd4e1aa76ad831fb87b969
|
3 |
+
size 3702
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 4096, "special_tokens_map_file": null, "name_or_path": "allenai/longformer-base-4096", "tokenizer_class": "LongformerTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99d57f55e7c6e2821b88cd87c70ab72acf535db0cbb1f9830f52e81ba3473aa0
|
3 |
+
size 3055
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|