Training in progress, epoch 0

config.json

@@ -1,51 +1,39 @@
 {
-  "_name_or_path": "lamaabdulaziz/AraGPT2-finetuned-fnd",
-  "activation_function": "gelu_new",
+  "_name_or_path": "aubmindlab/aragpt2-mega-detector-long",
   "architectures": [
-    "GPT2ForSequenceClassification"
+    "ElectraForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
+  "classifier_dropout": null,
   "embedding_size": 768,
-  "eos_token_id": 50256,
   "generator_hidden_size": 0.33333,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
-    "0": "Fake",
-    "1": "Real"
+    "0": "machine-generated",
+    "1": "human-written"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "0": "fake",
-    "1": "real"
+    "human-written": 1,
+    "machine-generated": 0
   },
   "layer_norm_eps": 1e-12,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 512,
-  "pad_token_id": 50256,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
+  "problem_type": "single_label_classification",
   "summary_activation": "gelu",
-  "summary_first_dropout": 0.1,
   "summary_last_dropout": 0.1,
-  "summary_proj_to_labels": true,
   "summary_type": "first",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.12.2",
+  "transformers_version": "4.20.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 64000

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d23efbef2c4413bf63127f47dd796d55fe022c866b7c8cea421c9514a913d374
-size 541618599
+oid sha256:6f45e83cc556686a7683a8ad2ea89281b5aaa7d33f522dd68f73bf1fa9644d4c
+size 540851117

runs/May05_05-25-10_2063b2ec8c4e/1683264532.0990443/events.out.tfevents.1683264532.2063b2ec8c4e.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c625d45627a1fe3cea37dad045b5798b0b7ecc2c15fd215af23deb93f120a9ca
+size 5348

runs/May05_05-25-10_2063b2ec8c4e/events.out.tfevents.1683264532.2063b2ec8c4e.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592ac76ac0ed43966e5341f1287424bb28829c185555358ef305c97cc121242b
+size 4593

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d97874927acbd836db09ec7cba2f38a12dde0121b1da4c145e57c7403797120e
-size 2863
+oid sha256:fd7892f93091088c14dba655577a2e89f6533e3e6b3dd5a1a7ebca555a376ef1
+size 3311