Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c55ff448bbf4d8ec8b6b24b3a99275d65b1bdc21391c509585099d31c1a334f
+oid sha256:6623ceeae0ee74f44cd373cccc2622e8db69d890745f553c465e2c593aa0e458
 size 1181192

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilbert/distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "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": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f83aa1150a0f4cd2e2e1f8ddfae131c59f626f4ddf43e845470f1caeca056a
+size 328839160

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a9ab15e6998ba41a70506e738d4ab289685d57b7c9c92a5e8e3c4d473dedf2f
+oid sha256:a89d154b9e63c6b3cde644c9ec63296ebb9ab3de7e9f2540bdd6b4d65e96e68c
 size 5304