Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +81 -0
- logs/1698567414.48361/events.out.tfevents.1698567414.ba03445939ee.521.1 +3 -0
- logs/1698568602.429512/events.out.tfevents.1698568602.ba03445939ee.521.3 +3 -0
- logs/1698568656.588409/events.out.tfevents.1698568656.ba03445939ee.521.5 +3 -0
- logs/events.out.tfevents.1698567414.ba03445939ee.521.0 +3 -0
- logs/events.out.tfevents.1698568602.ba03445939ee.521.2 +3 -0
- logs/events.out.tfevents.1698568656.ba03445939ee.521.4 +3 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-base",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"adapters": {
|
6 |
+
"adapters": {},
|
7 |
+
"config_map": {},
|
8 |
+
"fusion_config_map": {},
|
9 |
+
"fusions": {}
|
10 |
+
},
|
11 |
+
"add_bias_logits": false,
|
12 |
+
"add_final_layer_norm": false,
|
13 |
+
"architectures": [
|
14 |
+
"BartForSequenceClassification"
|
15 |
+
],
|
16 |
+
"attention_dropout": 0.1,
|
17 |
+
"bos_token_id": 0,
|
18 |
+
"classif_dropout": 0.1,
|
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 |
+
"early_stopping": true,
|
28 |
+
"encoder_attention_heads": 12,
|
29 |
+
"encoder_ffn_dim": 3072,
|
30 |
+
"encoder_layerdrop": 0.0,
|
31 |
+
"encoder_layers": 6,
|
32 |
+
"eos_token_id": 2,
|
33 |
+
"forced_bos_token_id": 0,
|
34 |
+
"forced_eos_token_id": 2,
|
35 |
+
"gradient_checkpointing": false,
|
36 |
+
"id2label": {
|
37 |
+
"0": "human",
|
38 |
+
"1": "ia"
|
39 |
+
},
|
40 |
+
"init_std": 0.02,
|
41 |
+
"is_encoder_decoder": true,
|
42 |
+
"label2id": {
|
43 |
+
"LABEL_0": 0,
|
44 |
+
"LABEL_1": 1,
|
45 |
+
"LABEL_2": 2
|
46 |
+
},
|
47 |
+
"max_position_embeddings": 1024,
|
48 |
+
"model_type": "bart",
|
49 |
+
"no_repeat_ngram_size": 3,
|
50 |
+
"normalize_before": false,
|
51 |
+
"normalize_embedding": true,
|
52 |
+
"num_beams": 4,
|
53 |
+
"num_hidden_layers": 6,
|
54 |
+
"pad_token_id": 1,
|
55 |
+
"problem_type": "single_label_classification",
|
56 |
+
"scale_embedding": false,
|
57 |
+
"task_specific_params": {
|
58 |
+
"summarization": {
|
59 |
+
"length_penalty": 1.0,
|
60 |
+
"max_length": 128,
|
61 |
+
"min_length": 12,
|
62 |
+
"num_beams": 4
|
63 |
+
},
|
64 |
+
"summarization_cnn": {
|
65 |
+
"length_penalty": 2.0,
|
66 |
+
"max_length": 142,
|
67 |
+
"min_length": 56,
|
68 |
+
"num_beams": 4
|
69 |
+
},
|
70 |
+
"summarization_xsum": {
|
71 |
+
"length_penalty": 1.0,
|
72 |
+
"max_length": 62,
|
73 |
+
"min_length": 11,
|
74 |
+
"num_beams": 6
|
75 |
+
}
|
76 |
+
},
|
77 |
+
"torch_dtype": "float32",
|
78 |
+
"transformers_version": "4.26.1",
|
79 |
+
"use_cache": true,
|
80 |
+
"vocab_size": 50265
|
81 |
+
}
|
logs/1698567414.48361/events.out.tfevents.1698567414.ba03445939ee.521.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd9385e8f2555fe06831de4662b1bb6ce954e2c767cb0e6628e2bf4b41660bb4
|
3 |
+
size 5753
|
logs/1698568602.429512/events.out.tfevents.1698568602.ba03445939ee.521.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e910d67eafab4d84b77beb7fdee40554918016767e8de3c530c95459e32c928
|
3 |
+
size 5753
|
logs/1698568656.588409/events.out.tfevents.1698568656.ba03445939ee.521.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71e4a7bc9a9feb872bb1de79ae567cac3d1ee1a53517e0e8363c0d5440b7172e
|
3 |
+
size 5753
|
logs/events.out.tfevents.1698567414.ba03445939ee.521.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49490d46ef1a7e506f48250efd3383aba0b2ab76538677dbe9dba777d3b3d0db
|
3 |
+
size 64680
|
logs/events.out.tfevents.1698568602.ba03445939ee.521.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58a5886c9e77b46daacb8afdc5e2bcf40cf8e9bd088e13e471f4b61ebd7d91ed
|
3 |
+
size 5673
|
logs/events.out.tfevents.1698568656.ba03445939ee.521.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59fbd375af7f01f0ff3783ee4b37739b736a5fd423d08b5f1626516e730e276a
|
3 |
+
size 65152
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8727d6887482b0c9e337ebd9a1aabe9b874f1bb154f3d489cfd5d6bf556dc3c
|
3 |
+
size 560140006
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a46573c1df23150701f6a8728e3225036243b502a9e617920dd7d4dee8c934b8
|
3 |
+
size 3960
|