Training in progress, epoch 1

config.json

@@ -1,35 +1,47 @@
 {
-  "_name_or_path": "AraGPT2-finetuned-crossVal-fnd",
+  "_name_or_path": "aubmindlab/aragpt2-mega-detector-long",
+  "activation_function": "gelu_new",
   "architectures": [
-    "ElectraForSequenceClassification"
+    "GPT2ForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
   "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,
-  "max_position_embeddings": 512,
-  "model_type": "electra",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 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_positions": 512,
+  "pad_token_id": 50256,
   "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
   "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",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7359df239ecd5a13c24957f1727a148b7131f6f957c18ef496e05a065e9e972
-size 540864877
+oid sha256:d07d896be1053fecfbdd497c755c2934cf0628d99861b1bb76c704d315af51f0
+size 541618599

runs/Apr17_11-40-59_fdfa6d275866/1681731871.7973266/events.out.tfevents.1681731871.fdfa6d275866.17.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c673b4e57bf58cbf45b86f2aeacc6708090cf6129b7cbe8dc760f260b341f908
+size 4538

runs/Apr17_11-40-59_fdfa6d275866/events.out.tfevents.1681731871.fdfa6d275866.17.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b73798a4608e6c61b780065dd74bd9b2c5904b82a67aa6b3789c707c069987f
+size 3571

runs/Apr17_11-46-46_fdfa6d275866/1681732297.16172/events.out.tfevents.1681732297.fdfa6d275866.17.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf66434d3c3a05631e5f06af786f31604c991e6436dfa4522a534acb809fefd
+size 4538

runs/Apr17_11-46-46_fdfa6d275866/events.out.tfevents.1681732297.fdfa6d275866.17.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9f3d957f1b2d131ae2fb04c2f25dd2f0d3709119a84c3dd1b83405caf322b9
+size 3571

runs/Apr17_12-14-21_fdfa6d275866/1681733793.4995327/events.out.tfevents.1681733793.fdfa6d275866.17.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f686bfc7f88dbcb5137e122aee44631f9e80c88238686ae93f404acc4aefc339
+size 4538

runs/Apr17_12-14-21_fdfa6d275866/events.out.tfevents.1681733793.fdfa6d275866.17.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee1c8e32f6499e549ebd023b69e133ad25f02b038415c8ce2a5060887453fb3
+size 4779

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe1d00a444ef3878cddd2205cf3d7f5d2aac0e359f7940a36f1973e29587309e
+oid sha256:d97874927acbd836db09ec7cba2f38a12dde0121b1da4c145e57c7403797120e
 size 2863