Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +60 -0
- pytorch_model.bin +3 -0
- runs/Aug01_06-06-14_923fe6008f1d/events.out.tfevents.1690869980.923fe6008f1d.22508.0 +3 -0
- runs/Aug01_06-19-38_923fe6008f1d/events.out.tfevents.1690870781.923fe6008f1d.22508.1 +3 -0
- runs/Aug01_06-20-56_923fe6008f1d/events.out.tfevents.1690870859.923fe6008f1d.22508.2 +3 -0
- runs/Aug01_06-21-16_923fe6008f1d/events.out.tfevents.1690870879.923fe6008f1d.22508.3 +3 -0
- runs/Aug01_06-24-35_923fe6008f1d/events.out.tfevents.1690871078.923fe6008f1d.22508.4 +3 -0
- runs/Aug01_06-26-08_923fe6008f1d/events.out.tfevents.1690871171.923fe6008f1d.22508.5 +3 -0
- runs/Aug01_06-27-56_923fe6008f1d/events.out.tfevents.1690871279.923fe6008f1d.22508.6 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-small",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 512,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "relu",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "relu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": false,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
20 |
+
"num_decoder_layers": 6,
|
21 |
+
"num_heads": 8,
|
22 |
+
"num_layers": 6,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"task_specific_params": {
|
28 |
+
"summarization": {
|
29 |
+
"early_stopping": true,
|
30 |
+
"length_penalty": 2.0,
|
31 |
+
"max_length": 200,
|
32 |
+
"min_length": 30,
|
33 |
+
"no_repeat_ngram_size": 3,
|
34 |
+
"num_beams": 4,
|
35 |
+
"prefix": "summarize: "
|
36 |
+
},
|
37 |
+
"translation_en_to_de": {
|
38 |
+
"early_stopping": true,
|
39 |
+
"max_length": 300,
|
40 |
+
"num_beams": 4,
|
41 |
+
"prefix": "translate English to German: "
|
42 |
+
},
|
43 |
+
"translation_en_to_fr": {
|
44 |
+
"early_stopping": true,
|
45 |
+
"max_length": 300,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "translate English to French: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to Romanian: "
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.31.0",
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 32128
|
60 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b522df67bc6823ecafb75a5474cacec2cd07edfc22a2eabe9b635261a6e0e00e
|
3 |
+
size 242071641
|
runs/Aug01_06-06-14_923fe6008f1d/events.out.tfevents.1690869980.923fe6008f1d.22508.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da960dd0f5d8dc4e3564d2f59360240206bb2fb7161bb7375421fb2d097b5d3d
|
3 |
+
size 5055
|
runs/Aug01_06-19-38_923fe6008f1d/events.out.tfevents.1690870781.923fe6008f1d.22508.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d64ecc65fd17c9d8a4775bd62cc2e9df56fd1b3272506242babaf1de7882c932
|
3 |
+
size 5055
|
runs/Aug01_06-20-56_923fe6008f1d/events.out.tfevents.1690870859.923fe6008f1d.22508.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e136ccde037bafc77a68fd3edcfa854130aee147cc76bf8a2ca360c543ea3d3
|
3 |
+
size 5056
|
runs/Aug01_06-21-16_923fe6008f1d/events.out.tfevents.1690870879.923fe6008f1d.22508.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77a8065220b163d294f52e87508702bda6be70e0e0a68225b7a295b018fa1787
|
3 |
+
size 5056
|
runs/Aug01_06-24-35_923fe6008f1d/events.out.tfevents.1690871078.923fe6008f1d.22508.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ca89fb0a6a0a8c6828f82dc25fe927bc82eadd7bd086a1f86fe48701f8e7471
|
3 |
+
size 5055
|
runs/Aug01_06-26-08_923fe6008f1d/events.out.tfevents.1690871171.923fe6008f1d.22508.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:493beeeb4778f6ed27baa52d6a0ae849b83b343c092bb8794cf8b309b61909c5
|
3 |
+
size 5055
|
runs/Aug01_06-27-56_923fe6008f1d/events.out.tfevents.1690871279.923fe6008f1d.22508.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:705991ad5f43d3b44cf0d58b4a0ed379e66cc5dde58707475edfacca8544409f
|
3 |
+
size 6425
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c01a69c24244c96256cff931c551505f1170ab4ca75c85721deaa698d9ecdd8
|
3 |
+
size 4155
|