Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +75 -0
- pytorch_model.bin +3 -0
- runs/Mar20_00-12-40_munich/1710868372.5883222/events.out.tfevents.1710868372.munich.2642613.1 +3 -0
- runs/Mar20_00-12-40_munich/events.out.tfevents.1710868372.munich.2642613.0 +3 -0
- runs/Mar20_00-13-44_munich/1710868431.9608793/events.out.tfevents.1710868431.munich.2644759.1 +3 -0
- runs/Mar20_00-13-44_munich/events.out.tfevents.1710868431.munich.2644759.0 +3 -0
- runs/Mar20_00-14-35_munich/1710868481.938479/events.out.tfevents.1710868481.munich.2645116.1 +3 -0
- runs/Mar20_00-14-35_munich/events.out.tfevents.1710868481.munich.2645116.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-base",
|
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": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 12,
|
23 |
+
"encoder_ffn_dim": 3072,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
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 |
+
"normalize_embedding": true,
|
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,
|
54 |
+
"max_length": 128,
|
55 |
+
"min_length": 12,
|
56 |
+
"num_beams": 4
|
57 |
+
},
|
58 |
+
"summarization_cnn": {
|
59 |
+
"length_penalty": 2.0,
|
60 |
+
"max_length": 142,
|
61 |
+
"min_length": 56,
|
62 |
+
"num_beams": 4
|
63 |
+
},
|
64 |
+
"summarization_xsum": {
|
65 |
+
"length_penalty": 1.0,
|
66 |
+
"max_length": 62,
|
67 |
+
"min_length": 11,
|
68 |
+
"num_beams": 6
|
69 |
+
}
|
70 |
+
},
|
71 |
+
"torch_dtype": "float32",
|
72 |
+
"transformers_version": "4.26.1",
|
73 |
+
"use_cache": true,
|
74 |
+
"vocab_size": 50265
|
75 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:832783ea3b1a468cfc775065634423bef4b26e03aaa82100ac54023266c5b583
|
3 |
+
size 557971229
|
runs/Mar20_00-12-40_munich/1710868372.5883222/events.out.tfevents.1710868372.munich.2642613.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10d803761cc1a7ed8ba2a53a6bfe9ae6562446308b1554f25629ae0878d0d7eb
|
3 |
+
size 6065
|
runs/Mar20_00-12-40_munich/events.out.tfevents.1710868372.munich.2642613.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b559f815058dc099bbe02a3250eabd1fac6c04ce313f5ab84dc50c80b22a874
|
3 |
+
size 5179
|
runs/Mar20_00-13-44_munich/1710868431.9608793/events.out.tfevents.1710868431.munich.2644759.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d480bceb491c3588ac9b2494662561bd31e01c5ca6183cc4b6ff609d40d06bf4
|
3 |
+
size 6065
|
runs/Mar20_00-13-44_munich/events.out.tfevents.1710868431.munich.2644759.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45a6b5c0392d22c98f5b4794afb57bf83330a63a757f14421b5c931e54b8b9c0
|
3 |
+
size 5180
|
runs/Mar20_00-14-35_munich/1710868481.938479/events.out.tfevents.1710868481.munich.2645116.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f98e828109b4284775858f45e2af8024286d1f3ae08c80b41ce5252f43f17f9
|
3 |
+
size 6065
|
runs/Mar20_00-14-35_munich/events.out.tfevents.1710868481.munich.2645116.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:285184fd6dbb1453e86637728c451011a95084f26d5aaad334aed0e1f5536f12
|
3 |
+
size 5784
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:343ca8f7f91acfd191f7191de22d2ce9a8016d407f77193e923d7a9a6dce2545
|
3 |
+
size 3707
|