Step 1, loss 11.031

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "AlbertForPreTraining"
+  ],
+  "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_dropout_prob": 0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "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": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

optimizer_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39cdcfc71ea139cd0096c7a76a41f92a73d5dabf024587fb3db696e5424a361a
+size 141764093

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab06c979183ae142e23395ca15804ab710188207423af96092314694e3d255d9
+size 71406466