End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: gpt2
+license: apache-2.0
+base_model: distilgpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # codeparrot-ds
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 
 ## Model description
 

config.json

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,14 +9,20 @@
   "bos_token_id": 0,
   "embd_pdrop": 0.1,
   "eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 128,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 6,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e161f44d7334acf4ffe61f689a6315c1015fd2eedfd8cc442efc0dd929bf44f2
-size 496984704
+oid sha256:b40db9ef87ba7b01e30b7d73c364523952841809d8f1d40c3e7dfe6671d2c321
+size 326868424

runs/Apr25_10-59-52_d75501603109/events.out.tfevents.1714042798.d75501603109.355.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd7430fc3ad03455c8a8e7d9e3b28c24002284719863c82f13f7a10464e0143
+size 5349

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d7bee64f2c71ba6d4ad5ea2af792d8a6e332c1160f79dd0fe83f15503ceb3ef
+oid sha256:2802724822e9da08b6a380a00d735eebee16a8f1d44718c22842366941a8a5a4
 size 4984