Training in progress, step 500

config.json

@@ -1,46 +1,46 @@
 {
-  "_name_or_path": "distilbert/distilgpt2",
-  "_num_labels": 1,
-  "activation_function": "gelu_new",
+  "_name_or_path": "/hpc2hdd/home/ymen989/2541/model/model2",
   "architectures": [
-    "GPT2LMHeadModel"
+    "BertForSequenceClassification"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
-    "0": "LABEL_0"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "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
-    }
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
   },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.42.0.dev0",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09022e134cdf5fc177e1ee79f2ffebb079f58c2aa396886ca64193535415f2e7
-size 327657928
+oid sha256:b61ca65f22522fd2a92a650b33ba42495b5ba741b61132442a50c555a1c73c7b
+size 711452684

runs/Jun05_14-22-17_ad33647f7b16/events.out.tfevents.1717568539.ad33647f7b16.164.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ca645c57d905bf2ff01c99670f9f33a1e7420dacfd8a2c0aaab28c63eeb027
-size 25211
+oid sha256:340a7023be7e7f8f7a6e24d79a330c683de3d4ec060041af34de02d3efb06e87
+size 25836

runs/Jun05_14-22-17_ad33647f7b16/events.out.tfevents.1717573311.ad33647f7b16.164.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ca02a8581d0a7468405349c4e595f2ce0a146a1caf45436d8d4e5f564f31d4
+size 5180

runs/Jun05_18-08-58_4e2beb3c5ae6/events.out.tfevents.1717582235.4e2beb3c5ae6.161.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf26b861ffa5a8b922d5c73270db2cfaa60284886325a9509fbec6baae9bd41c
+size 5505

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f82a00da21b9061be9c98b8ac6138bd4c678f2819af13cce507925b347406832
+oid sha256:431a09e799508296eed1786e16f26694515b11c1b7ba586003ff900b1c52437f
 size 5112