Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +73 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Jan17_01-45-27_6a2e78aa07ce/1642383950.1557813/events.out.tfevents.1642383950.6a2e78aa07ce.104.1 +3 -0
- runs/Jan17_01-45-27_6a2e78aa07ce/events.out.tfevents.1642383950.6a2e78aa07ce.104.0 +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 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_eos_token_id": 2,
|
28 |
+
"gradient_checkpointing": false,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1",
|
32 |
+
"2": "LABEL_2"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1,
|
39 |
+
"LABEL_2": 2
|
40 |
+
},
|
41 |
+
"max_position_embeddings": 1024,
|
42 |
+
"model_type": "bart",
|
43 |
+
"no_repeat_ngram_size": 3,
|
44 |
+
"normalize_before": false,
|
45 |
+
"num_beams": 4,
|
46 |
+
"num_hidden_layers": 12,
|
47 |
+
"pad_token_id": 1,
|
48 |
+
"scale_embedding": false,
|
49 |
+
"task_specific_params": {
|
50 |
+
"summarization": {
|
51 |
+
"length_penalty": 1.0,
|
52 |
+
"max_length": 128,
|
53 |
+
"min_length": 12,
|
54 |
+
"num_beams": 4
|
55 |
+
},
|
56 |
+
"summarization_cnn": {
|
57 |
+
"length_penalty": 2.0,
|
58 |
+
"max_length": 142,
|
59 |
+
"min_length": 56,
|
60 |
+
"num_beams": 4
|
61 |
+
},
|
62 |
+
"summarization_xsum": {
|
63 |
+
"length_penalty": 1.0,
|
64 |
+
"max_length": 62,
|
65 |
+
"min_length": 11,
|
66 |
+
"num_beams": 6
|
67 |
+
}
|
68 |
+
},
|
69 |
+
"torch_dtype": "float32",
|
70 |
+
"transformers_version": "4.15.0",
|
71 |
+
"use_cache": true,
|
72 |
+
"vocab_size": 50265
|
73 |
+
}
|
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:e427e0e835ab0f9d96764007d0d652680141c0b7db0054cdc12df13c57fc6419
|
3 |
+
size 1625557313
|
runs/Jan17_01-45-27_6a2e78aa07ce/1642383950.1557813/events.out.tfevents.1642383950.6a2e78aa07ce.104.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33a39b5b2babc531deae957792e0f2f5cc74988a3cd9d5c84970ab1f78327348
|
3 |
+
size 5007
|
runs/Jan17_01-45-27_6a2e78aa07ce/events.out.tfevents.1642383950.6a2e78aa07ce.104.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f5ba56a6b1c9837811d7e2ffe68909b85adb403343875976a154c830211aeca
|
3 |
+
size 4594
|
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 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large", "tokenizer_class": "BartTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4628639968bbbb4d81bb3c6abb3578e28e6ec8cc0732b5a7ab7282722e0d947
|
3 |
+
size 3119
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|