Training in progress, epoch 1

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "mnaylor/mega-base-wikitext",
+  "activation": "silu",
+  "add_lm_hidden_dense_layer": false,
+  "add_token_type_embeddings": false,
+  "architectures": [
+    "MegaForSequenceClassification"
+  ],
+  "attention_activation": "softmax",
+  "attention_probs_dropout_prob": 0.1,
+  "bidirectional": true,
+  "bos_token_id": 0,
+  "chunk_size": -1,
+  "classifier_dropout": null,
+  "dropout_prob": 0.1,
+  "ema_beta_range": 0.02,
+  "ema_delta_alpha_range": 0.2,
+  "ema_gamma_omega_range": 1.0,
+  "ema_projection_size": 16,
+  "eos_token_id": 2,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
+  "max_positions": 10000,
+  "model_type": "mega",
+  "nffn_activation_dropout_prob": 0.0,
+  "nffn_hidden_size": 256,
+  "norm_affine": true,
+  "normalization_type": "scalenorm",
+  "normalize_before_ffn": true,
+  "normalize_before_mega": true,
+  "num_attention_heads": 1,
+  "num_hidden_layers": 4,
+  "pad_token_id": 2,
+  "problem_type": "single_label_classification",
+  "relative_positional_bias": "rotary",
+  "shared_representation_size": 64,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0",
+  "truncation": null,
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "use_chunking": false,
+  "use_feature_dropout": false,
+  "use_normalized_ffn": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d37a7ec16d4f6e7fb850869007700b174f4aa9568ee7d84be6df168e1fe3253c
+size 29403912

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_length": 256,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e65d59dfe6191a5f1785f27e5a3c62dfd48e0ad7d84e4ffe68910b9d6c99ee
+size 4091