Training in progress, step 500
Browse files- config.json +74 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Nov07_18-46-33_3df0d55f520a/events.out.tfevents.1699382794.3df0d55f520a.5079.1 +3 -0
- runs/Nov07_19-03-16_3df0d55f520a/events.out.tfevents.1699383807.3df0d55f520a.5079.2 +3 -0
- runs/Nov07_19-04-57_3df0d55f520a/events.out.tfevents.1699383898.3df0d55f520a.19296.0 +3 -0
- runs/Nov07_19-08-33_3df0d55f520a/events.out.tfevents.1699384119.3df0d55f520a.19296.1 +3 -0
- runs/Nov07_19-09-39_3df0d55f520a/events.out.tfevents.1699384188.3df0d55f520a.19296.2 +3 -0
- runs/Nov07_19-10-43_3df0d55f520a/events.out.tfevents.1699384265.3df0d55f520a.19296.3 +3 -0
- runs/Nov07_19-12-07_3df0d55f520a/events.out.tfevents.1699384334.3df0d55f520a.19296.4 +3 -0
- runs/Nov07_19-14-21_3df0d55f520a/events.out.tfevents.1699384462.3df0d55f520a.21734.0 +3 -0
- runs/Nov07_19-22-57_3df0d55f520a/events.out.tfevents.1699384990.3df0d55f520a.21734.1 +3 -0
- runs/Nov07_19-53-15_3df0d55f520a/events.out.tfevents.1699386796.3df0d55f520a.31446.0 +3 -0
- runs/Nov07_19-53-15_3df0d55f520a/events.out.tfevents.1699386889.3df0d55f520a.31446.1 +3 -0
- runs/Nov07_19-53-15_3df0d55f520a/events.out.tfevents.1699387192.3df0d55f520a.31446.2 +3 -0
- runs/Nov07_20-06-44_3df0d55f520a/events.out.tfevents.1699387605.3df0d55f520a.35025.0 +3 -0
- runs/Nov07_20-12-26_3df0d55f520a/events.out.tfevents.1699387948.3df0d55f520a.36631.0 +3 -0
- runs/Nov07_20-33-21_3df0d55f520a/events.out.tfevents.1699389202.3df0d55f520a.41658.0 +3 -0
- runs/Nov08_05-33-40_3df0d55f520a/events.out.tfevents.1699421633.3df0d55f520a.170719.0 +3 -0
- runs/Nov08_06-17-13_3df0d55f520a/events.out.tfevents.1699424234.3df0d55f520a.180901.0 +3 -0
- runs/Nov08_08-01-22_3df0d55f520a/events.out.tfevents.1699430483.3df0d55f520a.206630.0 +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 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-large",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 1024,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 4096,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 16,
|
23 |
+
"encoder_ffn_dim": 4096,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 12,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"forced_bos_token_id": 0,
|
28 |
+
"forced_eos_token_id": 2,
|
29 |
+
"gradient_checkpointing": false,
|
30 |
+
"id2label": {
|
31 |
+
"0": "LABEL_0",
|
32 |
+
"1": "LABEL_1",
|
33 |
+
"2": "LABEL_2"
|
34 |
+
},
|
35 |
+
"init_std": 0.02,
|
36 |
+
"is_encoder_decoder": true,
|
37 |
+
"label2id": {
|
38 |
+
"LABEL_0": 0,
|
39 |
+
"LABEL_1": 1,
|
40 |
+
"LABEL_2": 2
|
41 |
+
},
|
42 |
+
"max_position_embeddings": 1024,
|
43 |
+
"model_type": "bart",
|
44 |
+
"no_repeat_ngram_size": 3,
|
45 |
+
"normalize_before": false,
|
46 |
+
"num_beams": 4,
|
47 |
+
"num_hidden_layers": 12,
|
48 |
+
"pad_token_id": 1,
|
49 |
+
"scale_embedding": false,
|
50 |
+
"task_specific_params": {
|
51 |
+
"summarization": {
|
52 |
+
"length_penalty": 1.0,
|
53 |
+
"max_length": 128,
|
54 |
+
"min_length": 12,
|
55 |
+
"num_beams": 4
|
56 |
+
},
|
57 |
+
"summarization_cnn": {
|
58 |
+
"length_penalty": 2.0,
|
59 |
+
"max_length": 142,
|
60 |
+
"min_length": 56,
|
61 |
+
"num_beams": 4
|
62 |
+
},
|
63 |
+
"summarization_xsum": {
|
64 |
+
"length_penalty": 1.0,
|
65 |
+
"max_length": 62,
|
66 |
+
"min_length": 11,
|
67 |
+
"num_beams": 6
|
68 |
+
}
|
69 |
+
},
|
70 |
+
"torch_dtype": "float32",
|
71 |
+
"transformers_version": "4.35.0",
|
72 |
+
"use_cache": true,
|
73 |
+
"vocab_size": 50265
|
74 |
+
}
|
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 sha256:6bc651fa03f7d414df9b5d0f53c19e759a82b734674d35d412b1ed2d975fbc0a
|
3 |
+
size 1625426996
|
runs/Nov07_18-46-33_3df0d55f520a/events.out.tfevents.1699382794.3df0d55f520a.5079.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3b1585de960965d674beb78ef2404bc84c7417799581b8b364063dae5c6b285
|
3 |
+
size 5883
|
runs/Nov07_19-03-16_3df0d55f520a/events.out.tfevents.1699383807.3df0d55f520a.5079.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5179574dff79364bbf964a6b3243f55b5bbc656e41d36f0f096b4ffe6e9d326
|
3 |
+
size 4184
|
runs/Nov07_19-04-57_3df0d55f520a/events.out.tfevents.1699383898.3df0d55f520a.19296.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d66f9bd253ea85d70e9e56e4f2edd74b3fa4c845efc885f40ea257e16c4d8d4e
|
3 |
+
size 10952
|
runs/Nov07_19-08-33_3df0d55f520a/events.out.tfevents.1699384119.3df0d55f520a.19296.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cc1c887de56337a4d34e7194c2c344ad8b2dc859784ac2bc4362b6041499ea0
|
3 |
+
size 5520
|
runs/Nov07_19-09-39_3df0d55f520a/events.out.tfevents.1699384188.3df0d55f520a.19296.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:718d4b87c6927e7d895c93552ca38eaee061e8c3738d93735307f6e288112c06
|
3 |
+
size 5520
|
runs/Nov07_19-10-43_3df0d55f520a/events.out.tfevents.1699384265.3df0d55f520a.19296.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6d71dfabce9573296a1fe9ead367f89c8a37a9d0dac511c624106ba6f14b300
|
3 |
+
size 5520
|
runs/Nov07_19-12-07_3df0d55f520a/events.out.tfevents.1699384334.3df0d55f520a.19296.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cce75aae4b889595f58a05b9013197ea2b2e1f6643919827921554a59a0a865
|
3 |
+
size 4184
|
runs/Nov07_19-14-21_3df0d55f520a/events.out.tfevents.1699384462.3df0d55f520a.21734.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00c34288fb85e9ace767c288eb604cbef526fff4b5048651e8bc35eddb6e1425
|
3 |
+
size 5520
|
runs/Nov07_19-22-57_3df0d55f520a/events.out.tfevents.1699384990.3df0d55f520a.21734.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9129af1ab432006d490179096584e64a1f68d99ca4341dbc4074b3bf80da421
|
3 |
+
size 10952
|
runs/Nov07_19-53-15_3df0d55f520a/events.out.tfevents.1699386796.3df0d55f520a.31446.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ba753dd0a8c96e5c18efff573fde96ff03ab0f5d03c2c1e5fa0c66b3cfbcc72
|
3 |
+
size 5520
|
runs/Nov07_19-53-15_3df0d55f520a/events.out.tfevents.1699386889.3df0d55f520a.31446.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd9ee282fc53ccb9d8ec6001856b9ccd6be9f3897f1b39e9e2b1d25cd564fd1d
|
3 |
+
size 10952
|
runs/Nov07_19-53-15_3df0d55f520a/events.out.tfevents.1699387192.3df0d55f520a.31446.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:428da12eb4d4deada52dca285b384dbc6e4bb55f939bef4731154126dd29aee4
|
3 |
+
size 5520
|
runs/Nov07_20-06-44_3df0d55f520a/events.out.tfevents.1699387605.3df0d55f520a.35025.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2142e3b6931c67a2d08ae39ec59462b3624aecf6709c6e9f0c051d0896cc7488
|
3 |
+
size 5520
|
runs/Nov07_20-12-26_3df0d55f520a/events.out.tfevents.1699387948.3df0d55f520a.36631.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5fed113d5e9959320a37e4bcae2a0ca47e310f23975403c89a8e04d0f7cfc0b
|
3 |
+
size 5520
|
runs/Nov07_20-33-21_3df0d55f520a/events.out.tfevents.1699389202.3df0d55f520a.41658.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce4f268c999632b03ba531a89cbae0045d9849f50577b0e126fb2b398e8141d3
|
3 |
+
size 5519
|
runs/Nov08_05-33-40_3df0d55f520a/events.out.tfevents.1699421633.3df0d55f520a.170719.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc7132768c2d24bf7d7ee3dabc5ab808202024a4ee228859ddc9f8490248439b
|
3 |
+
size 5519
|
runs/Nov08_06-17-13_3df0d55f520a/events.out.tfevents.1699424234.3df0d55f520a.180901.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfd717e1cfae73159ef80eb9f546023e9c5d716fe2582e0f53842152ad18b1db
|
3 |
+
size 5889
|
runs/Nov08_08-01-22_3df0d55f520a/events.out.tfevents.1699430483.3df0d55f520a.206630.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d48e388e91669969aa7b608abfa15d99f801e4d257359bbb2aab5ee3db63c28
|
3 |
+
size 6046
|
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": true,
|
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": true,
|
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": 1024,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "BartTokenizer",
|
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:ee8a0ea73b90335e5011186a2c21f1d04bd285a73066c8343a161c9cdb49a81c
|
3 |
+
size 4792
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|