Ayus077BCT014Bhandari
commited on
Commit
•
46e9a22
1
Parent(s):
47d3f5e
Training in progress, epoch 1
Browse files- config.json +32 -0
- logs/events.out.tfevents.1709031001.8c1bce108dd1.34.0 +3 -0
- logs/events.out.tfevents.1709039324.9be0f1da2c2a.34.0 +3 -0
- logs/events.out.tfevents.1709049687.9be0f1da2c2a.34.1 +3 -0
- logs/events.out.tfevents.1709050144.facfc0273a4e.34.0 +3 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Ayus077BCT014Bhandari/vartat5-using-100K-plus-25",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 1024,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 512,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"num_decoder_layers": 8,
|
21 |
+
"num_heads": 6,
|
22 |
+
"num_layers": 8,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.37.0",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 128128
|
32 |
+
}
|
logs/events.out.tfevents.1709031001.8c1bce108dd1.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:569edc9e0fe3b52e1455fa58c0d1bc9ffd4322e8423d22b432f646104aa8e9c8
|
3 |
+
size 25070
|
logs/events.out.tfevents.1709039324.9be0f1da2c2a.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5126d6f789077a3bca189ccd609f5987da9295e8c87baca9eea6775cf7de80e
|
3 |
+
size 25070
|
logs/events.out.tfevents.1709049687.9be0f1da2c2a.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b68de32f7987bd56449698895b089084c398a9b35076de05b806b6cca0f695be
|
3 |
+
size 4184
|
logs/events.out.tfevents.1709050144.facfc0273a4e.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dfa9cb9f08071932b0004f23c7398ce40a2b3b323f0f5596890af8f6be68230
|
3 |
+
size 25070
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cedc4d5b7f48016979dc6a7d85c0407c445b44b2872e9103c7ac15c6dc99f729
|
3 |
+
size 701083048
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f93189e8d1dfdf078e418a15d228c428246ddae7baca055c92351f078287634
|
3 |
+
size 4920
|