tanatapanun
commited on
Commit
•
5d3c997
1
Parent(s):
adab71b
Training in progress, step 500
Browse files- config.json +10 -9
- model.safetensors +2 -2
- runs/Dec21_22-38-37_william-gpu-3090-10-rxldr/events.out.tfevents.1703198324.william-gpu-3090-10-rxldr.4824.0 +2 -2
- runs/Dec21_22-39-05_william-gpu-3090-10-rxldr/events.out.tfevents.1703198346.william-gpu-3090-10-rxldr.4824.1 +2 -2
- runs/Dec21_22-42-12_william-gpu-3090-10-rxldr/events.out.tfevents.1703198533.william-gpu-3090-10-rxldr.120708.0 +3 -0
- runs/Dec21_22-42-28_william-gpu-3090-10-rxldr/events.out.tfevents.1703198548.william-gpu-3090-10-rxldr.120708.1 +3 -0
- runs/Dec21_22-43-01_william-gpu-3090-10-rxldr/events.out.tfevents.1703198582.william-gpu-3090-10-rxldr.120708.2 +3 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "facebook/bart-
|
3 |
"activation_dropout": 0.1,
|
4 |
"activation_function": "gelu",
|
5 |
"add_bias_logits": false,
|
@@ -11,18 +11,18 @@
|
|
11 |
"bos_token_id": 0,
|
12 |
"classif_dropout": 0.1,
|
13 |
"classifier_dropout": 0.0,
|
14 |
-
"d_model":
|
15 |
-
"decoder_attention_heads":
|
16 |
-
"decoder_ffn_dim":
|
17 |
"decoder_layerdrop": 0.0,
|
18 |
-
"decoder_layers":
|
19 |
"decoder_start_token_id": 2,
|
20 |
"dropout": 0.1,
|
21 |
"early_stopping": true,
|
22 |
-
"encoder_attention_heads":
|
23 |
-
"encoder_ffn_dim":
|
24 |
"encoder_layerdrop": 0.0,
|
25 |
-
"encoder_layers":
|
26 |
"eos_token_id": 2,
|
27 |
"forced_bos_token_id": 0,
|
28 |
"forced_eos_token_id": 2,
|
@@ -43,8 +43,9 @@
|
|
43 |
"model_type": "bart",
|
44 |
"no_repeat_ngram_size": 3,
|
45 |
"normalize_before": false,
|
|
|
46 |
"num_beams": 4,
|
47 |
-
"num_hidden_layers":
|
48 |
"pad_token_id": 1,
|
49 |
"scale_embedding": false,
|
50 |
"task_specific_params": {
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/bart-base",
|
3 |
"activation_dropout": 0.1,
|
4 |
"activation_function": "gelu",
|
5 |
"add_bias_logits": false,
|
|
|
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,
|
|
|
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": {
|
model.safetensors
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:bd93677e2c1427cb2571f2384851fe93dfaea649f76771c844950616c68efe71
|
3 |
+
size 557912620
|
runs/Dec21_22-38-37_william-gpu-3090-10-rxldr/events.out.tfevents.1703198324.william-gpu-3090-10-rxldr.4824.0
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:c20f83e84dd9946e550d373922adf71c49d4bd41ef89f325703bbe8cdcf9957e
|
3 |
+
size 5593
|
runs/Dec21_22-39-05_william-gpu-3090-10-rxldr/events.out.tfevents.1703198346.william-gpu-3090-10-rxldr.4824.1
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 sha256:183c7781b7f32e6d37ad87649df33575f5050acaa773b749eb6081cce1ccbb39
|
3 |
+
size 5593
|
runs/Dec21_22-42-12_william-gpu-3090-10-rxldr/events.out.tfevents.1703198533.william-gpu-3090-10-rxldr.120708.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27ed412472abc94816cb4281ca16021adf2a80da337598a81219bebb8f70208f
|
3 |
+
size 5649
|
runs/Dec21_22-42-28_william-gpu-3090-10-rxldr/events.out.tfevents.1703198548.william-gpu-3090-10-rxldr.120708.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:175fff02e5662f62da461c4c304c6b42d817bdff496725f60beb206dfab60efb
|
3 |
+
size 5647
|
runs/Dec21_22-43-01_william-gpu-3090-10-rxldr/events.out.tfevents.1703198582.william-gpu-3090-10-rxldr.120708.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec8acbf64e5b9f872b702850cde28bca01bf0d5ccb37fc02d68781124a8cdab5
|
3 |
+
size 6329
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4463
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:632bafc2350caab2af35a73a641c395b0556349027509af78de7455a9a440f1c
|
3 |
size 4463
|