samyak24jain
commited on
Training in progress, epoch 1
Browse files
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 50256,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"model_type": "gpt2",
|
13 |
+
"n_embd": 768,
|
14 |
+
"n_head": 8,
|
15 |
+
"n_inner": null,
|
16 |
+
"n_layer": 6,
|
17 |
+
"n_positions": 128,
|
18 |
+
"reorder_and_upcast_attn": false,
|
19 |
+
"resid_pdrop": 0.1,
|
20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
21 |
+
"scale_attn_weights": true,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.37.2",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 50257
|
31 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5d2a8e5326622bec8f0ae742cff761b312f466046b39cd79d73628a9efb579f
|
3 |
+
size 324905416
|
runs/Feb18_21-24-52_nlp-gpu-02.be.ucsc.edu/events.out.tfevents.1708320293.nlp-gpu-02.be.ucsc.edu.29444.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:693714bfdb0bcad6817e9ec767f2bba5345179c6f8ce265f0a16453b130c799c
|
3 |
+
size 6856
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4927e364b3fe02e0ab04555c2b443d90c2512771e2794b8229e9fcced91a4558
|
3 |
+
size 4728
|