Training in progress, step 50

config.json

@@ -2,13 +2,28 @@
   "_name_or_path": "openai-community/gpt2-medium",
   "activation_function": "gelu_new",
   "architectures": [
-    "GPT2LMHeadModel"
+    "GPT2ForSequenceClassification"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
+  "finetuning_task": "text-classification",
+  "id2label": {
+    "0": "a",
+    "1": "b",
+    "2": "c",
+    "3": "d",
+    "4": "e"
+  },
   "initializer_range": 0.02,
+  "label2id": {
+    "a": 0,
+    "b": 1,
+    "c": 2,
+    "d": 3,
+    "e": 4
+  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
@@ -18,7 +33,9 @@
   "n_layer": 24,
   "n_positions": 1024,
   "n_special": 0,
+  "pad_token_id": 50256,
   "predict_special_tokens": true,
+  "problem_type": "single_label_classification",
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:301194d21d1b357dd4c5a37bc702d6b52324c9017c88c7fb3bc66fa3a35c3980
-size 1419322880
+oid sha256:2e3f7a523f562d6c337e03bb33a210b54ea076f951b53311f51e720b96dca1da
+size 1419343440

special_tokens_map.json

@@ -1,5 +1,6 @@
 {
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
   "unk_token": "<|endoftext|>"
 }

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 1024
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 50256,
+    "pad_type_id": 0,
+    "pad_token": "<|endoftext|>"
+  },
   "added_tokens": [
     {
       "id": 50256,

tokenizer_config.json

@@ -14,6 +14,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0908b84cd3056ca9e653c923e5b2c99a4fcc96cc0f6e92a667606e48fc0dcc93
+size 5176