Training in progress, epoch 1
Browse files- config.json +14 -1
- pytorch_model.bin +2 -2
- tokenizer.json +16 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -5,10 +5,11 @@
|
|
5 |
"add_bias_logits": false,
|
6 |
"add_final_layer_norm": false,
|
7 |
"architectures": [
|
8 |
-
"
|
9 |
],
|
10 |
"attention_dropout": 0.1,
|
11 |
"bos_token_id": 0,
|
|
|
12 |
"classif_dropout": 0.1,
|
13 |
"classifier_dropout": 0.0,
|
14 |
"d_model": 768,
|
@@ -27,18 +28,22 @@
|
|
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,
|
@@ -47,7 +52,15 @@
|
|
47 |
"num_beams": 4,
|
48 |
"num_hidden_layers": 6,
|
49 |
"pad_token_id": 1,
|
|
|
|
|
|
|
|
|
|
|
50 |
"scale_embedding": false,
|
|
|
|
|
|
|
51 |
"task_specific_params": {
|
52 |
"summarization": {
|
53 |
"length_penalty": 1.0,
|
|
|
5 |
"add_bias_logits": false,
|
6 |
"add_final_layer_norm": false,
|
7 |
"architectures": [
|
8 |
+
"BartPrefixPropForConditionalGeneration"
|
9 |
],
|
10 |
"attention_dropout": 0.1,
|
11 |
"bos_token_id": 0,
|
12 |
+
"bptt_depth": -1,
|
13 |
"classif_dropout": 0.1,
|
14 |
"classifier_dropout": 0.0,
|
15 |
"d_model": 768,
|
|
|
28 |
"forced_bos_token_id": 0,
|
29 |
"forced_eos_token_id": 2,
|
30 |
"gradient_checkpointing": false,
|
31 |
+
"hidden_dropout_prob": 0.1,
|
32 |
"id2label": {
|
33 |
"0": "LABEL_0",
|
34 |
"1": "LABEL_1",
|
35 |
"2": "LABEL_2"
|
36 |
},
|
37 |
"init_std": 0.02,
|
38 |
+
"input_size": 512,
|
39 |
"is_encoder_decoder": true,
|
40 |
"label2id": {
|
41 |
"LABEL_0": 0,
|
42 |
"LABEL_1": 1,
|
43 |
"LABEL_2": 2
|
44 |
},
|
45 |
+
"label_max_size": 256,
|
46 |
+
"max_n_segments": 4,
|
47 |
"max_position_embeddings": 1024,
|
48 |
"model_type": "bart",
|
49 |
"no_repeat_ngram_size": 3,
|
|
|
52 |
"num_beams": 4,
|
53 |
"num_hidden_layers": 6,
|
54 |
"pad_token_id": 1,
|
55 |
+
"post_seq_len": 128,
|
56 |
+
"pre_seq_len": 16,
|
57 |
+
"prefix_projection": false,
|
58 |
+
"propagate_prefix": "only",
|
59 |
+
"propagate_prefix_scalar": false,
|
60 |
"scale_embedding": false,
|
61 |
+
"segment_alignment": "left",
|
62 |
+
"sum_loss": true,
|
63 |
+
"sum_token_size": 0,
|
64 |
"task_specific_params": {
|
65 |
"summarization": {
|
66 |
"length_penalty": 1.0,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b02ac8497bf83830b37b64270aefd83dd3875bca8812ce9f74eecc155b06552f
|
3 |
+
size 558266465
|
tokenizer.json
CHANGED
@@ -1,7 +1,21 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 128,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 128
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 1,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "<pad>"
|
18 |
+
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4283
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d633429ad9b7a18638882560b49fca2fc9e26569b5e79111084ab774711b6099
|
3 |
size 4283
|