End of training
Browse files- .gitignore +1 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- runs/Feb21_22-48-34_85a05065a09b/1645483727.0641387/events.out.tfevents.1645483727.85a05065a09b.70.1 +3 -0
- runs/Feb21_22-48-34_85a05065a09b/events.out.tfevents.1645483727.85a05065a09b.70.0 +3 -0
- runs/Feb21_22-50-48_85a05065a09b/1645483856.9268618/events.out.tfevents.1645483856.85a05065a09b.645.1 +3 -0
- runs/Feb21_22-50-48_85a05065a09b/events.out.tfevents.1645483856.85a05065a09b.645.0 +3 -0
- runs/Feb21_22-50-48_85a05065a09b/events.out.tfevents.1645484194.85a05065a09b.645.2 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
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 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.16.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a54d5b9257a7fa692bc4d10142c6977a59aa4e2beda3c4d3fdd17819b6390cf2
|
3 |
+
size 510401385
|
runs/Feb21_22-48-34_85a05065a09b/1645483727.0641387/events.out.tfevents.1645483727.85a05065a09b.70.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dc5da6d34ca26a0163e93e967397fbe8bd9a342514c3db7970eb08dd425ed00
|
3 |
+
size 4742
|
runs/Feb21_22-48-34_85a05065a09b/events.out.tfevents.1645483727.85a05065a09b.70.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fb99150bbc1b4283ce7e1ef685dcbdc9c8f447ca1563966a1af1b90ae9f71a6
|
3 |
+
size 40
|
runs/Feb21_22-50-48_85a05065a09b/1645483856.9268618/events.out.tfevents.1645483856.85a05065a09b.645.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d6884f4352a77e3d2b0562857e61ab805285c246f525165dbb4774de497e546
|
3 |
+
size 4742
|
runs/Feb21_22-50-48_85a05065a09b/events.out.tfevents.1645483856.85a05065a09b.645.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:607a6f6583c76022ac790e827521b9bbe31bff99b365b6a6553ac5a30e874706
|
3 |
+
size 4665
|
runs/Feb21_22-50-48_85a05065a09b/events.out.tfevents.1645484194.85a05065a09b.645.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e3d1f693c2dadffcf7fcb3266a229390cc28ca19365a9b9c098cde1eb8687a1
|
3 |
+
size 306
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69280f0e565dd4813b979df08aaab97c9131b580eead6af2123f30baf7ea424e
|
3 |
+
size 2991
|