End of training
Browse files
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
-
base_model:
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# codeparrot-ds
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: distilgpt2
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
|
|
|
| 13 |
|
| 14 |
# codeparrot-ds
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
config.json
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
|
|
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -8,14 +9,20 @@
|
|
| 8 |
"bos_token_id": 0,
|
| 9 |
"embd_pdrop": 0.1,
|
| 10 |
"eos_token_id": 0,
|
|
|
|
|
|
|
|
|
|
| 11 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
|
|
|
| 12 |
"layer_norm_epsilon": 1e-05,
|
| 13 |
"model_type": "gpt2",
|
| 14 |
"n_ctx": 128,
|
| 15 |
"n_embd": 768,
|
| 16 |
"n_head": 12,
|
| 17 |
"n_inner": null,
|
| 18 |
-
"n_layer":
|
| 19 |
"n_positions": 1024,
|
| 20 |
"reorder_and_upcast_attn": false,
|
| 21 |
"resid_pdrop": 0.1,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "distilgpt2",
|
| 3 |
+
"_num_labels": 1,
|
| 4 |
"activation_function": "gelu_new",
|
| 5 |
"architectures": [
|
| 6 |
"GPT2LMHeadModel"
|
|
|
|
| 9 |
"bos_token_id": 0,
|
| 10 |
"embd_pdrop": 0.1,
|
| 11 |
"eos_token_id": 0,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0"
|
| 14 |
+
},
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
"layer_norm_epsilon": 1e-05,
|
| 20 |
"model_type": "gpt2",
|
| 21 |
"n_ctx": 128,
|
| 22 |
"n_embd": 768,
|
| 23 |
"n_head": 12,
|
| 24 |
"n_inner": null,
|
| 25 |
+
"n_layer": 6,
|
| 26 |
"n_positions": 1024,
|
| 27 |
"reorder_and_upcast_attn": false,
|
| 28 |
"resid_pdrop": 0.1,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6ba373b99dd86c7da278072bd0522f503e0b355851b9951dd91fe531dd8b1f7
|
| 3 |
+
size 326868424
|
runs/Apr25_16-52-06_arg4/events.out.tfevents.1714035130.arg4.968669.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b3bad5abc9b1ce74a7f3626241f69dcd40a862f689f2a44534c563cbf46756f
|
| 3 |
+
size 4545
|
runs/Apr25_16-54-01_arg4/events.out.tfevents.1714035242.arg4.1047042.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81604db1b59ec96fe3b36bf435b5855e45ffb32faa7a3099e8cc95f21fa2548b
|
| 3 |
+
size 4974
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4219
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5f6ad7a95f21e6c6c5f4fc081b6007041412ef60c882bcbf4e64779a92f39ec
|
| 3 |
size 4219
|