Training in progress, epoch 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -1,7 +1,48 @@
 {
-  "_name_or_path": "jam15/bert-finetuned-combine-p5",
+  "_name_or_path": "bert-base-uncased",
+  "adapters": {
+    "adapters": {
+      "classification_adapter": "9076f36a74755ac4"
+    },
+    "config_map": {
+      "9076f36a74755ac4": {
+        "adapter_residual_before_ln": false,
+        "cross_adapter": false,
+        "factorized_phm_W": true,
+        "factorized_phm_rule": false,
+        "hypercomplex_nonlinearity": "glorot-uniform",
+        "init_weights": "bert",
+        "inv_adapter": null,
+        "inv_adapter_reduction_factor": null,
+        "is_parallel": false,
+        "learn_phm": true,
+        "leave_out": [],
+        "ln_after": false,
+        "ln_before": false,
+        "mh_adapter": false,
+        "non_linearity": "relu",
+        "original_ln_after": true,
+        "original_ln_before": true,
+        "output_adapter": true,
+        "phm_bias": true,
+        "phm_c_init": "normal",
+        "phm_dim": 4,
+        "phm_init_range": 0.0001,
+        "phm_layer": false,
+        "phm_rank": 1,
+        "reduction_factor": 16,
+        "residual_before_ln": true,
+        "scaling": 1.0,
+        "shared_W_phm": false,
+        "shared_phm_rule": true,
+        "use_gating": false
+      }
+    },
+    "fusion_config_map": {},
+    "fusions": {}
+  },
   "architectures": [
-    "BertForSequenceClassification"
+    "BertModelWithHeads"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
@@ -10,70 +51,70 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "loc1lay1",
-    "1": "loc1lay2",
-    "10": "loc3lay3",
-    "11": "loc3lay4",
-    "12": "loc4lay1",
-    "13": "loc4lay2",
-    "14": "loc4lay3",
-    "15": "loc4lay4",
-    "16": "loc5+",
-    "17": "loc1",
-    "18": "loc2",
-    "19": "loc3",
-    "2": "loc1lay3",
-    "20": "loc4",
-    "21": "nfw",
-    "22": "tfw",
-    "23": "tfwc",
-    "24": "tfwp",
-    "25": "fwb",
-    "26": "lay1",
-    "27": "lay2",
-    "28": "lay3",
-    "29": "lay4",
-    "3": "loc1lay4",
-    "4": "loc2lay1",
-    "5": "loc2lay2",
-    "6": "loc2lay3",
-    "7": "loc2lay4",
-    "8": "loc3lay1",
-    "9": "loc3lay2"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "fwb": 25,
-    "lay1": 26,
-    "lay2": 27,
-    "lay3": 28,
-    "lay4": 29,
-    "loc1": 17,
-    "loc1lay1": 0,
-    "loc1lay2": 1,
-    "loc1lay3": 2,
-    "loc1lay4": 3,
-    "loc2": 18,
-    "loc2lay1": 4,
-    "loc2lay2": 5,
-    "loc2lay3": 6,
-    "loc2lay4": 7,
-    "loc3": 19,
-    "loc3lay1": 8,
-    "loc3lay2": 9,
-    "loc3lay3": 10,
-    "loc3lay4": 11,
-    "loc4": 20,
-    "loc4lay1": 12,
-    "loc4lay2": 13,
-    "loc4lay3": 14,
-    "loc4lay4": 15,
-    "loc5+": 16,
-    "nfw": 21,
-    "tfw": 22,
-    "tfwc": 23,
-    "tfwp": 24
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
@@ -82,9 +123,50 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
+  "prediction_heads": {
+    "classification_adapter": {
+      "activation_function": "tanh",
+      "bias": true,
+      "head_type": "classification",
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1,
+        "LABEL_10": 10,
+        "LABEL_11": 11,
+        "LABEL_12": 12,
+        "LABEL_13": 13,
+        "LABEL_14": 14,
+        "LABEL_15": 15,
+        "LABEL_16": 16,
+        "LABEL_17": 17,
+        "LABEL_18": 18,
+        "LABEL_19": 19,
+        "LABEL_2": 2,
+        "LABEL_20": 20,
+        "LABEL_21": 21,
+        "LABEL_22": 22,
+        "LABEL_23": 23,
+        "LABEL_24": 24,
+        "LABEL_25": 25,
+        "LABEL_26": 26,
+        "LABEL_27": 27,
+        "LABEL_28": 28,
+        "LABEL_29": 29,
+        "LABEL_3": 3,
+        "LABEL_4": 4,
+        "LABEL_5": 5,
+        "LABEL_6": 6,
+        "LABEL_7": 7,
+        "LABEL_8": 8,
+        "LABEL_9": 9
+      },
+      "layers": 2,
+      "num_labels": 30,
+      "use_pooler": false
+    }
+  },
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.26.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c25370fd42d906de19ef0beb560a998209e55a48abfd11653d200d3214589ce1
+size 444053117

runs/Jun14_02-55-58_f4bc99bdcb92/1718333937.7644422/events.out.tfevents.1718333937.f4bc99bdcb92.259.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067331db3676fcce576732c1ae2d2cc64efe4bdd50845f3bbfae0dacb6600e55
+size 5733

runs/Jun14_02-55-58_f4bc99bdcb92/events.out.tfevents.1718333937.f4bc99bdcb92.259.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b9a0c08502311a07b40c0a6db8405a4d2ad7949d63e1f48d899fd7632681fa
+size 4184

tokenizer_config.json

@@ -1,53 +1,12 @@
 {
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44f833c84a329a78f1af09d2950af6f38cb0cb6320145fdff1e63119db22225
-size 4920
+oid sha256:61d94b549959646f2d4187ff2e7ccf91e258379ff93281159953a7790bdd087b
+size 3515