Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,173 @@
+{
+  "_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": [
+    "BertModelWithHeads"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "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": {
+    "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,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "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": "4.26.1",
+  "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 sha256:5ec6a0986467fb1c45386a3eb815a4b31fd27567b128e7c80f168e6fb3930e20
+size 444053117

runs/Jun14_03-05-36_f4bc99bdcb92/1718334375.9021647/events.out.tfevents.1718334375.f4bc99bdcb92.259.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1273e00e921bdae25c61ff05afdd2f06332345b3257acf84ce02b3445fade3af
+size 5757

runs/Jun14_03-05-36_f4bc99bdcb92/events.out.tfevents.1718334375.f4bc99bdcb92.259.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a6dc7b005e3055208b6fdf1c8736b6a454f1977ea7bb110b3310f80795cb38c
+size 4184

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "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",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56868fc71429cf82510c02405541c99ca448c7c5be43a8c84c3bb591b80a3bf9
+size 3515