galkowskim
commited on
Commit
•
da8e98f
1
Parent(s):
e0bab4c
Training in progress, epoch 3
Browse files- config.json +52 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jun15_12-20-59_dgx-4.eden/events.out.tfevents.1718446860.dgx-4.eden.3560955.0 +3 -0
- runs/Jun15_12-25-00_dgx-4.eden/events.out.tfevents.1718447100.dgx-4.eden.3560955.1 +3 -0
- runs/Jun15_12-27-12_dgx-4.eden/events.out.tfevents.1718447232.dgx-4.eden.3560955.2 +3 -0
- runs/Jun15_12-29-35_dgx-4.eden/events.out.tfevents.1718447375.dgx-4.eden.3560955.3 +3 -0
- runs/Jun15_12-31-53_dgx-4.eden/events.out.tfevents.1718447513.dgx-4.eden.3560955.4 +3 -0
- runs/Jun15_15-33-40_dgx-3.eden/events.out.tfevents.1718458421.dgx-3.eden.1799020.0 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
256,
|
10 |
+
256,
|
11 |
+
256,
|
12 |
+
256,
|
13 |
+
256,
|
14 |
+
256,
|
15 |
+
256,
|
16 |
+
256,
|
17 |
+
256,
|
18 |
+
256,
|
19 |
+
256,
|
20 |
+
256
|
21 |
+
],
|
22 |
+
"bos_token_id": 0,
|
23 |
+
"eos_token_id": 2,
|
24 |
+
"gradient_checkpointing": false,
|
25 |
+
"hidden_act": "gelu",
|
26 |
+
"hidden_dropout_prob": 0.1,
|
27 |
+
"hidden_size": 768,
|
28 |
+
"id2label": {
|
29 |
+
"0": "SADNESS",
|
30 |
+
"1": "JOY"
|
31 |
+
},
|
32 |
+
"ignore_attention_mask": false,
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
+
"label2id": {
|
36 |
+
"JOY": 1,
|
37 |
+
"SADNESS": 0
|
38 |
+
},
|
39 |
+
"layer_norm_eps": 1e-05,
|
40 |
+
"max_position_embeddings": 514,
|
41 |
+
"model_type": "longformer",
|
42 |
+
"num_attention_heads": 12,
|
43 |
+
"num_hidden_layers": 12,
|
44 |
+
"onnx_export": false,
|
45 |
+
"pad_token_id": 1,
|
46 |
+
"problem_type": "single_label_classification",
|
47 |
+
"sep_token_id": 2,
|
48 |
+
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.40.0",
|
50 |
+
"type_vocab_size": 1,
|
51 |
+
"vocab_size": 50265
|
52 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78a083f83608e2f3ce129095acff28dadd77faf157c984f4a5ad93cea2e1fc72
|
3 |
+
size 583668128
|
runs/Jun15_12-20-59_dgx-4.eden/events.out.tfevents.1718446860.dgx-4.eden.3560955.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb4f6284225f86623cb562e337a3d083c2f8d154ff63688691fc5c80e78f4c3c
|
3 |
+
size 19908
|
runs/Jun15_12-25-00_dgx-4.eden/events.out.tfevents.1718447100.dgx-4.eden.3560955.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85224f744687f14d4bcaa81319162e2b1d7aca5b1b0173f438036b3b265a6b26
|
3 |
+
size 13319
|
runs/Jun15_12-27-12_dgx-4.eden/events.out.tfevents.1718447232.dgx-4.eden.3560955.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1f9413b417b1788036e9260a2f7cde5e30ea9430e09eb82fd97f62f91112fa0
|
3 |
+
size 13108
|
runs/Jun15_12-29-35_dgx-4.eden/events.out.tfevents.1718447375.dgx-4.eden.3560955.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:508af74910598fb67d3ff4e1e2bc9e49ba57c2f5105eebcab5c17b915199e3c2
|
3 |
+
size 12897
|
runs/Jun15_12-31-53_dgx-4.eden/events.out.tfevents.1718447513.dgx-4.eden.3560955.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b61cce44d27345feea156bb3d491a06caf3c38476042ceed057a8e34c79def49
|
3 |
+
size 16695
|
runs/Jun15_15-33-40_dgx-3.eden/events.out.tfevents.1718458421.dgx-3.eden.1799020.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51ecbb4768ab0ec0e0535a798f1366ae45adfe91ba96715ab087468e73ebe79d
|
3 |
+
size 26918
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "LongformerTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f01262f43ecd01d66ff5989e041037fb656faf23e90fb760e9156c419444d8fb
|
3 |
+
size 5112
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|