jorge-henao
commited on
Commit
•
a950cd6
1
Parent(s):
f4abd35
Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +40 -0
- pytorch_model.bin +3 -0
- runs/Mar29_03-31-10_b5733b3c3d47/1648524686.4958806/events.out.tfevents.1648524686.b5733b3c3d47.73.1 +3 -0
- runs/Mar29_03-31-10_b5733b3c3d47/events.out.tfevents.1648524686.b5733b3c3d47.73.0 +3 -0
- runs/Mar29_03-35-39_b5733b3c3d47/1648524949.425263/events.out.tfevents.1648524949.b5733b3c3d47.73.3 +3 -0
- runs/Mar29_03-35-39_b5733b3c3d47/events.out.tfevents.1648524949.b5733b3c3d47.73.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "datificate/gpt2-small-spanish",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"summary_activation": null,
|
26 |
+
"summary_first_dropout": 0.1,
|
27 |
+
"summary_proj_to_labels": true,
|
28 |
+
"summary_type": "cls_index",
|
29 |
+
"summary_use_proj": true,
|
30 |
+
"task_specific_params": {
|
31 |
+
"text-generation": {
|
32 |
+
"do_sample": true,
|
33 |
+
"max_length": 50
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.17.0",
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 50257
|
40 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:261c2bb2d99536c6512c2c475b48c63e318e7cffbf1002ddc101c4950f9a6c69
|
3 |
+
size 510404393
|
runs/Mar29_03-31-10_b5733b3c3d47/1648524686.4958806/events.out.tfevents.1648524686.b5733b3c3d47.73.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1409cbb2efdf9e804b2263aa3af48226e16c8bf0cf2edf812c74b404760157e3
|
3 |
+
size 4841
|
runs/Mar29_03-31-10_b5733b3c3d47/events.out.tfevents.1648524686.b5733b3c3d47.73.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d003ecaca72ce3353416b15f21b728580e91ce67aee04df9bc82a0a8c650a4fc
|
3 |
+
size 3671
|
runs/Mar29_03-35-39_b5733b3c3d47/1648524949.425263/events.out.tfevents.1648524949.b5733b3c3d47.73.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bad6f83ac0f85cb083c1f518fa2c9151e77f849fe3d7898b1af8fcaad4d40d37
|
3 |
+
size 4841
|
runs/Mar29_03-35-39_b5733b3c3d47/events.out.tfevents.1648524949.b5733b3c3d47.73.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91225af598295f0021d89a3f2bd320daba1493db1a66b8a6c0a34b80201a1f0d
|
3 |
+
size 3828
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9db64c9b3a17957b94c69227d8fdfd5377bbc2e2d3946887cd78ecec32236d21
|
3 |
+
size 3055
|