Training in progress, step 500
Browse files
config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/prophetnet-large-uncased",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_cross_attention": true,
|
6 |
+
"architectures": [
|
7 |
+
"ProphetNetForCausalLM"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.1,
|
10 |
+
"bos_token_id": 102,
|
11 |
+
"decoder_ffn_dim": 4096,
|
12 |
+
"decoder_layerdrop": 0.0,
|
13 |
+
"decoder_max_position_embeddings": 514,
|
14 |
+
"decoder_start_token_id": 102,
|
15 |
+
"disable_ngram_loss": false,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"early_stopping": null,
|
18 |
+
"encoder_ffn_dim": 4096,
|
19 |
+
"encoder_layerdrop": 0.0,
|
20 |
+
"encoder_max_position_embeddings": 513,
|
21 |
+
"eos_token_id": 102,
|
22 |
+
"eps": 0.0,
|
23 |
+
"hidden_size": 1024,
|
24 |
+
"id2label": {
|
25 |
+
"0": "LABEL_0",
|
26 |
+
"1": "LABEL_1",
|
27 |
+
"2": "LABEL_2"
|
28 |
+
},
|
29 |
+
"init_std": 0.02,
|
30 |
+
"is_decoder": true,
|
31 |
+
"is_encoder_decoder": false,
|
32 |
+
"label2id": {
|
33 |
+
"LABEL_0": 0,
|
34 |
+
"LABEL_1": 1,
|
35 |
+
"LABEL_2": 2
|
36 |
+
},
|
37 |
+
"length_penalty": null,
|
38 |
+
"max_length": null,
|
39 |
+
"max_position_embeddings": 512,
|
40 |
+
"model_type": "prophetnet",
|
41 |
+
"ngram": 2,
|
42 |
+
"no_repeat_ngram_size": null,
|
43 |
+
"num_beams": null,
|
44 |
+
"num_buckets": 32,
|
45 |
+
"num_decoder_attention_heads": 16,
|
46 |
+
"num_decoder_layers": 12,
|
47 |
+
"num_encoder_attention_heads": 16,
|
48 |
+
"num_encoder_layers": 12,
|
49 |
+
"output_past": false,
|
50 |
+
"pad_token_id": 0,
|
51 |
+
"prefix": " ",
|
52 |
+
"relative_max_distance": 128,
|
53 |
+
"task_specific_params": {
|
54 |
+
"summarization": {
|
55 |
+
"early_stopping": true,
|
56 |
+
"length_penalty": 2.0,
|
57 |
+
"no_repeat_ngram_size": 3,
|
58 |
+
"num_beams": 4
|
59 |
+
}
|
60 |
+
},
|
61 |
+
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.46.2",
|
63 |
+
"use_cache": true,
|
64 |
+
"vocab_size": 30522
|
65 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73181445c12e05b53f1d957c7a8d09bbca055cc6123e829871e4be4a73a917ec
|
3 |
+
size 958605904
|
runs/Dec04_20-17-41_94ad683935fa/events.out.tfevents.1733343465.94ad683935fa.511.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:638f755f4ebbe6fdea760a35fc9df7b54af8690c4b681374f7c6c51cc544c77d
|
3 |
+
size 5939
|
runs/Dec04_20-19-20_94ad683935fa/events.out.tfevents.1733343562.94ad683935fa.511.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eb22e46e3fe11290142de70a429cb0e57e1636f7167bfe7ba6ac6488602ee8b
|
3 |
+
size 6692
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cac0143e8e97bc873d1bd5a937091021fadb332880a0156a160ba5f4a1bab54f
|
3 |
+
size 5304
|