Model save
Browse files- .gitignore +1 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- runs/Dec01_20-47-56_66557768fab4/1669927695.744816/events.out.tfevents.1669927695.66557768fab4.199.1 +3 -0
- runs/Dec01_20-47-56_66557768fab4/1669927730.5921853/events.out.tfevents.1669927730.66557768fab4.199.2 +3 -0
- runs/Dec01_20-47-56_66557768fab4/events.out.tfevents.1669927695.66557768fab4.199.0 +3 -0
- runs/Dec01_20-49-19_66557768fab4/1669927775.7141938/events.out.tfevents.1669927775.66557768fab4.199.4 +3 -0
- runs/Dec01_20-49-19_66557768fab4/events.out.tfevents.1669927775.66557768fab4.199.3 +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:ca94030a5cc54c3b64b5fe13502c4b030ba84857fe9327cf5afd439a269a9646
|
| 3 |
+
size 510396521
|
runs/Dec01_20-47-56_66557768fab4/1669927695.744816/events.out.tfevents.1669927695.66557768fab4.199.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc6b37b8f5177dcc286b6a0ffdd40acd2ede254cde513c33ef9d05ad0af9e09d
|
| 3 |
+
size 5465
|
runs/Dec01_20-47-56_66557768fab4/1669927730.5921853/events.out.tfevents.1669927730.66557768fab4.199.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99a5661796104585b835d8b356a9a54ed52a6df70eb677f435b9555f0b8a1cdd
|
| 3 |
+
size 5465
|
runs/Dec01_20-47-56_66557768fab4/events.out.tfevents.1669927695.66557768fab4.199.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08e08d615a65c925c28e4a97fe8def8203f10de1da6f7c39cbd63aace88fe510
|
| 3 |
+
size 7822
|
runs/Dec01_20-49-19_66557768fab4/1669927775.7141938/events.out.tfevents.1669927775.66557768fab4.199.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7076dc4ee5e5141a9066aa13227c364a712ddcaf9c921600bc27e56ac183dcd
|
| 3 |
+
size 5465
|
runs/Dec01_20-49-19_66557768fab4/events.out.tfevents.1669927775.66557768fab4.199.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbec3e5e4c6533878dd1720e6ec379baead8cb7d33ad734ae5043586f038b879
|
| 3 |
+
size 4284
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:103c9698837785259ba375fd0c967db6afcc2d05fb8a847ed7211fdb8d7f51dd
|
| 3 |
+
size 3375
|