Jorge Lopez Grisman
commited on
Commit
•
55f9a6e
1
Parent(s):
fad52ea
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +77 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/May31_14-29-23_ip-172-16-83-143.ec2.internal/1654007408.4133217/events.out.tfevents.1654007408.ip-172-16-83-143.ec2.internal.40995.1 +3 -0
- runs/May31_14-29-23_ip-172-16-83-143.ec2.internal/events.out.tfevents.1654007408.ip-172-16-83-143.ec2.internal.40995.0 +3 -0
- runs/May31_14-31-35_ip-172-16-83-143.ec2.internal/1654007803.2083786/events.out.tfevents.1654007803.ip-172-16-83-143.ec2.internal.6056.1 +3 -0
- runs/May31_14-31-35_ip-172-16-83-143.ec2.internal/events.out.tfevents.1654007803.ip-172-16-83-143.ec2.internal.6056.0 +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 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sshleifer/distilbart-cnn-12-6",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": false,
|
8 |
+
"architectures": [
|
9 |
+
"BartForConditionalGeneration"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.0,
|
14 |
+
"classifier_dropout": 0.0,
|
15 |
+
"d_model": 1024,
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 4096,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 6,
|
20 |
+
"decoder_start_token_id": 2,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"early_stopping": true,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 4096,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 12,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"extra_pos_embeddings": 2,
|
29 |
+
"force_bos_token_to_be_generated": true,
|
30 |
+
"forced_bos_token_id": 0,
|
31 |
+
"forced_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 |
+
"length_penalty": 2.0,
|
46 |
+
"max_length": 142,
|
47 |
+
"max_position_embeddings": 1024,
|
48 |
+
"min_length": 56,
|
49 |
+
"model_type": "bart",
|
50 |
+
"no_repeat_ngram_size": 3,
|
51 |
+
"normalize_before": false,
|
52 |
+
"normalize_embedding": true,
|
53 |
+
"num_beams": 4,
|
54 |
+
"num_hidden_layers": 12,
|
55 |
+
"output_past": true,
|
56 |
+
"pad_token_id": 1,
|
57 |
+
"prefix": " ",
|
58 |
+
"replacing_rate": 0,
|
59 |
+
"scale_embedding": false,
|
60 |
+
"static_position_embeddings": false,
|
61 |
+
"student_decoder_layers": null,
|
62 |
+
"student_encoder_layers": null,
|
63 |
+
"task_specific_params": {
|
64 |
+
"summarization": {
|
65 |
+
"early_stopping": true,
|
66 |
+
"length_penalty": 2.0,
|
67 |
+
"max_length": 142,
|
68 |
+
"min_length": 56,
|
69 |
+
"no_repeat_ngram_size": 3,
|
70 |
+
"num_beams": 4
|
71 |
+
}
|
72 |
+
},
|
73 |
+
"torch_dtype": "float32",
|
74 |
+
"transformers_version": "4.19.2",
|
75 |
+
"use_cache": true,
|
76 |
+
"vocab_size": 50264
|
77 |
+
}
|
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 sha256:8f3a02e96fbb0429dff921a093438f8da9a4632c10336126a91b12fa4b8f0717
|
3 |
+
size 1222361081
|
runs/May31_14-29-23_ip-172-16-83-143.ec2.internal/1654007408.4133217/events.out.tfevents.1654007408.ip-172-16-83-143.ec2.internal.40995.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06f25d13c4fefb9e14e7b736fd7133696d223ae623d6a79c22af9637d007fa94
|
3 |
+
size 5462
|
runs/May31_14-29-23_ip-172-16-83-143.ec2.internal/events.out.tfevents.1654007408.ip-172-16-83-143.ec2.internal.40995.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:566868ec7532e6f406bf78809c28fef0234d6d035cf4a2b8a899acd0577e3a63
|
3 |
+
size 4136
|
runs/May31_14-31-35_ip-172-16-83-143.ec2.internal/1654007803.2083786/events.out.tfevents.1654007803.ip-172-16-83-143.ec2.internal.6056.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed918238487e602f7967d6e8dab93cb5fcbdd293ce39cdb9a5dec7dc2b148557
|
3 |
+
size 5462
|
runs/May31_14-31-35_ip-172-16-83-143.ec2.internal/events.out.tfevents.1654007803.ip-172-16-83-143.ec2.internal.6056.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1af92dc8bbdbf060afebe4bac8c72e13649b7ac388ec96c1e729009f6c92c7a
|
3 |
+
size 5176
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
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": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "sshleifer/distilbart-cnn-12-6", "tokenizer_class": "BartTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e69db456566cb2f06a2869e2bc1704b04a37ae8ab65dfbd76e5741f13203093
|
3 |
+
size 3375
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|