Training in progress, step 100

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "pszemraj/mega-small-2048-C1024-simplewiki-MR50-tk_ema32",
+  "activation": "silu",
+  "add_lm_hidden_dense_layer": false,
+  "add_token_type_embeddings": true,
+  "architectures": [
+    "MegaForMaskedLM"
+  ],
+  "attention_activation": "softmax",
+  "attention_probs_dropout_prob": 0.1,
+  "bidirectional": true,
+  "bos_token_id": 0,
+  "chunk_size": 1024,
+  "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": 32,
+  "eos_token_id": 2,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_positions": 2048,
+  "model_type": "mega",
+  "nffn_activation_dropout_prob": 0.1,
+  "nffn_hidden_size": 1024,
+  "norm_affine": true,
+  "normalization_type": "scalenorm",
+  "normalize_before_ffn": true,
+  "normalize_before_mega": true,
+  "num_attention_heads": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_positional_bias": "rotary",
+  "shared_representation_size": 128,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.1",
+  "truncation": null,
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "use_chunking": true,
+  "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 sha256:33f364a9b11929d6e0485b82ddc7135d0180e3553ded9f1e159bbe9dc15d8392
+size 263983414

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 +1,16 @@
+{
+  "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": 2048,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db87039670f1bc245642ea338e75cce9fc7ddf8090ea4c24d4798fe28dba5ee7
+size 4728