Step 3238, loss 3.460

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LeanAlbertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_act_gated": true,
+  "hidden_dropout_prob": 0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-12,
+  "layers_to_keep": [],
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 16,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 24,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "rotary",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0",
+  "type_vocab_size": 2,
+  "vocab_size": 32000
+}

optimizer_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078dc2467881dc4d5b58e31eb6b1cd746acbe2f2f7179cabd6374f2cb7f999cc
+size 608100493

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa53ea0ee9f2049f37446bbae0dff170c35e5a80bf9753eb1ba42a31d247dbe
+size 304042184