Training in progress, step 500

.gitignore

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

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": [
+    "MegaForMaskedLM"
+  ],
+  "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": "4.32.0.dev0",
+  "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 sha256:108e4433ac9a81d96d715af8b5fb5b76c10455f391bc2ef625f9d7900fcc3d4c
+size 29535231

runs/Jul25_16-14-18_8be44650b3d0/events.out.tfevents.1690301668.8be44650b3d0.584.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542060bbbc0af28ea0605ad97afd5dab68ae3b342832d387a3073180875c0efd
+size 4840

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5447d6484e6ac035718cd550e845a4674819de8c474a4ffbfe13b05a78847f83
+size 3963