Training in progress, step 500

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": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "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 sha256:5609ac6f01101d2bcb425aa64610463292a0fe69c5001c2522d8c213dfd822b8
-size 497774208
+oid sha256:04832d090896cb5272c3d91e178a83d4a301826fb74b6f10cbcd85270e4e7f45
+size 327657928

runs/Dec26_14-30-20_4f87fa13cf4f/events.out.tfevents.1735223422.4f87fa13cf4f.48986.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d808b3160144279fcf5c5662f60584f2ae9498334eb011d259bca1a6b6f6a78
+size 5329

runs/Dec26_15-17-35_4f87fa13cf4f/events.out.tfevents.1735226257.4f87fa13cf4f.52160.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b681d61fe327edf63094efd3caaed004a06267047b8f8aadfed62cf39b500f6a
+size 5329

runs/Dec26_15-18-47_4f87fa13cf4f/events.out.tfevents.1735226328.4f87fa13cf4f.52529.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f0fcde8d6c9a22ea5ef5b24cce47f57eec38e5d4df36e54a8074664bf1e7b8
+size 6025

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f301c938db1cb6977900c5e27614e30ccd7fd4df22c121c98fedc0e91b2cf20
+oid sha256:44da7eabc06c79a1f80607609567e44ae9ae320d05d9c4883a152a08f36e8f4f
 size 5240