Model save
Browse files- .gitignore +1 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- runs/Dec01_21-09-11_b35f5ffe1493/1669928963.4713547/events.out.tfevents.1669928963.b35f5ffe1493.77.1 +3 -0
- runs/Dec01_21-09-11_b35f5ffe1493/events.out.tfevents.1669928963.b35f5ffe1493.77.0 +3 -0
- runs/Dec01_21-10-08_b35f5ffe1493/1669929012.3414333/events.out.tfevents.1669929012.b35f5ffe1493.77.3 +3 -0
- runs/Dec01_21-10-08_b35f5ffe1493/events.out.tfevents.1669929012.b35f5ffe1493.77.2 +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": "4.24.0",
|
| 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 sha256:4a905022b5b182920c4941c9a3dbc6011d71e752066a22162377603bb205d3b3
|
| 3 |
+
size 510396521
|
runs/Dec01_21-09-11_b35f5ffe1493/1669928963.4713547/events.out.tfevents.1669928963.b35f5ffe1493.77.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c93c859fdfeac5c4fe7bcfcb60b77db48fe3c61e477a5bc715a66f7df7eb217b
|
| 3 |
+
size 5462
|
runs/Dec01_21-09-11_b35f5ffe1493/events.out.tfevents.1669928963.b35f5ffe1493.77.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b169ddf361edf0fd8c367952f6fed99c18a6a565039e9908d34cccb1698d9a24
|
| 3 |
+
size 3928
|
runs/Dec01_21-10-08_b35f5ffe1493/1669929012.3414333/events.out.tfevents.1669929012.b35f5ffe1493.77.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f647f102e8dfc5d40111e9841118edfe78777920917853de6abf36062be8860
|
| 3 |
+
size 5462
|
runs/Dec01_21-10-08_b35f5ffe1493/events.out.tfevents.1669929012.b35f5ffe1493.77.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc62021fe6ff3f0bf580c47e861abbfac0a8f682e50049f40959e79db4c6a29c
|
| 3 |
+
size 4281
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccb3176298cf0930c26a982deb73f7a1d925b28685678411376ae99be1cd8737
|
| 3 |
+
size 3375
|