Training in progress, epoch 1

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "mnaylor/mega-base-wikitext",
+  "activation": "silu",
+  "add_lm_hidden_dense_layer": false,
+  "add_token_type_embeddings": false,
+  "architectures": [
+    "MegaForMultipleChoice"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "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": 1,
+  "relative_positional_bias": "rotary",
+  "shared_representation_size": 64,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "truncation": null,
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "use_chunking": false,
+  "use_feature_dropout": false,
+  "use_normalized_ffn": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93208de46ce991451d4d16e5c162beb3b528756519cc805820a72efdd1cbaeee
+size 29381028

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 +1,61 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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 sha256:0e0b6ce39e3ab674645d815986d9ccb3cabb478e36e15d05135e54c1bb2c96ac
+size 4600