Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +54 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Mar08_00-02-34_Brians-Mac-mini/1678255359.717899/events.out.tfevents.1678255359.Brians-Mac-mini.13250.1 +3 -0
- runs/Mar08_00-02-34_Brians-Mac-mini/events.out.tfevents.1678255359.Brians-Mac-mini.13250.0 +3 -0
- runs/Mar08_00-04-27_Brians-Mac-mini/1678255471.555702/events.out.tfevents.1678255471.Brians-Mac-mini.13327.1 +3 -0
- runs/Mar08_00-04-27_Brians-Mac-mini/events.out.tfevents.1678255471.Brians-Mac-mini.13327.0 +3 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +68 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allenai/led-base-16384",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"LEDForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"attention_window": [
|
10 |
+
124,
|
11 |
+
124,
|
12 |
+
124,
|
13 |
+
124,
|
14 |
+
124,
|
15 |
+
124
|
16 |
+
],
|
17 |
+
"bos_token_id": 0,
|
18 |
+
"classif_dropout": 0.0,
|
19 |
+
"classifier_dropout": 0.0,
|
20 |
+
"d_model": 768,
|
21 |
+
"decoder_attention_heads": 12,
|
22 |
+
"decoder_ffn_dim": 3072,
|
23 |
+
"decoder_layerdrop": 0.0,
|
24 |
+
"decoder_layers": 6,
|
25 |
+
"decoder_start_token_id": 2,
|
26 |
+
"dropout": 0.1,
|
27 |
+
"encoder_attention_heads": 12,
|
28 |
+
"encoder_ffn_dim": 3072,
|
29 |
+
"encoder_layerdrop": 0.0,
|
30 |
+
"encoder_layers": 6,
|
31 |
+
"eos_token_id": 2,
|
32 |
+
"gradient_checkpointing": false,
|
33 |
+
"id2label": {
|
34 |
+
"0": "LABEL_0",
|
35 |
+
"1": "LABEL_1",
|
36 |
+
"2": "LABEL_2"
|
37 |
+
},
|
38 |
+
"init_std": 0.02,
|
39 |
+
"is_encoder_decoder": true,
|
40 |
+
"label2id": {
|
41 |
+
"LABEL_0": 0,
|
42 |
+
"LABEL_1": 1,
|
43 |
+
"LABEL_2": 2
|
44 |
+
},
|
45 |
+
"max_decoder_position_embeddings": 1024,
|
46 |
+
"max_encoder_position_embeddings": 16384,
|
47 |
+
"model_type": "led",
|
48 |
+
"num_hidden_layers": 6,
|
49 |
+
"pad_token_id": 1,
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.26.1",
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 50265
|
54 |
+
}
|
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:d850c3d345454c68bc9bb4ea305cc9cba3c778d635e45f5bbfa601d8a355a92f
|
3 |
+
size 647674353
|
runs/Mar08_00-02-34_Brians-Mac-mini/1678255359.717899/events.out.tfevents.1678255359.Brians-Mac-mini.13250.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bed4b6dac3c238f0cc090d40e20e36f58bb418c0f3f2a164aaac09093abf6e2
|
3 |
+
size 5962
|
runs/Mar08_00-02-34_Brians-Mac-mini/events.out.tfevents.1678255359.Brians-Mac-mini.13250.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e6919444b944be6507127c355e370b3fb3a10cea9c9173e0148194857edadd1
|
3 |
+
size 4656
|
runs/Mar08_00-04-27_Brians-Mac-mini/1678255471.555702/events.out.tfevents.1678255471.Brians-Mac-mini.13327.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17af34d7885e19598858692951cd12af6172ae145d776b2ef42b73bdff047475
|
3 |
+
size 5962
|
runs/Mar08_00-04-27_Brians-Mac-mini/events.out.tfevents.1678255471.Brians-Mac-mini.13327.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac7b23f9237535abbf1fa5e85e65c4749b7fb4459cc0d3409ae4905487ab94ae
|
3 |
+
size 4656
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"batch_size": null,
|
4 |
+
"batched": true,
|
5 |
+
"bos_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<s>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"cls_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"eos_token": {
|
22 |
+
"__type": "AddedToken",
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
},
|
29 |
+
"errors": "replace",
|
30 |
+
"mask_token": {
|
31 |
+
"__type": "AddedToken",
|
32 |
+
"content": "<mask>",
|
33 |
+
"lstrip": true,
|
34 |
+
"normalized": true,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
"model_max_length": 16384,
|
39 |
+
"name_or_path": "allenai/led-base-16384",
|
40 |
+
"pad_token": {
|
41 |
+
"__type": "AddedToken",
|
42 |
+
"content": "<pad>",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": true,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": false
|
47 |
+
},
|
48 |
+
"padding": true,
|
49 |
+
"sep_token": {
|
50 |
+
"__type": "AddedToken",
|
51 |
+
"content": "</s>",
|
52 |
+
"lstrip": false,
|
53 |
+
"normalized": true,
|
54 |
+
"rstrip": false,
|
55 |
+
"single_word": false
|
56 |
+
},
|
57 |
+
"special_tokens_map_file": "/Users/briandunn/.cache/huggingface/hub/models--allenai--led-base-16384/snapshots/38335783885b338d93791936c54bb4be46bebed9/special_tokens_map.json",
|
58 |
+
"tokenizer_class": "LEDTokenizer",
|
59 |
+
"truncation": true,
|
60 |
+
"unk_token": {
|
61 |
+
"__type": "AddedToken",
|
62 |
+
"content": "<unk>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": true,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false
|
67 |
+
}
|
68 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c15b4594d090fd6c767417e473388fcd794fa987cf28d8ee986880d337a56d81
|
3 |
+
size 3631
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|