Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +66 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "moussaKam/barthez-orangesum-title",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": true,
|
7 |
+
"architectures": [
|
8 |
+
"MBartForConditionalGeneration"
|
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 |
+
"do_blenderbot_90_layernorm": false,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"early_stopping": true,
|
23 |
+
"encoder_attention_heads": 12,
|
24 |
+
"encoder_ffn_dim": 3072,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"extra_pos_embeddings": 2,
|
29 |
+
"force_bos_token_to_be_generated": false,
|
30 |
+
"forced_eos_token_id": 2,
|
31 |
+
"id2label": {
|
32 |
+
"0": "LABEL_0",
|
33 |
+
"1": "LABEL_1",
|
34 |
+
"2": "LABEL_2"
|
35 |
+
},
|
36 |
+
"init_std": 0.02,
|
37 |
+
"is_encoder_decoder": true,
|
38 |
+
"label2id": {
|
39 |
+
"LABEL_0": 0,
|
40 |
+
"LABEL_1": 1,
|
41 |
+
"LABEL_2": 2
|
42 |
+
},
|
43 |
+
"max_position_embeddings": 1024,
|
44 |
+
"model_type": "mbart",
|
45 |
+
"normalize_before": true,
|
46 |
+
"normalize_embedding": true,
|
47 |
+
"num_hidden_layers": 6,
|
48 |
+
"pad_token_id": 1,
|
49 |
+
"scale_embedding": false,
|
50 |
+
"static_position_embeddings": false,
|
51 |
+
"task_specific_params": {
|
52 |
+
"summarization": {
|
53 |
+
"early_stopping": true,
|
54 |
+
"length_penalty": 2.0,
|
55 |
+
"max_length": 100,
|
56 |
+
"min_length": 10,
|
57 |
+
"no_repeat_ngram_size": 3,
|
58 |
+
"num_beams": 4
|
59 |
+
}
|
60 |
+
},
|
61 |
+
"tokenizer_class": "BarthezTokenizer",
|
62 |
+
"torch_dtype": "float32",
|
63 |
+
"transformers_version": "4.21.1",
|
64 |
+
"use_cache": true,
|
65 |
+
"vocab_size": 50002
|
66 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08cf793563e44b84857c66cdf408fe53dd740890ce3362ce31c926040e507447
|
3 |
+
size 557173745
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58ada5319deb9f21cbfcafd3bdc355946e89c206b37d532523fe5acc0824f708
|
3 |
+
size 3439
|