Training in progress, step 500

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "junnyu/roformer_chinese_base",
+  "architectures": [
+    "RoFormerForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1536,
+  "model_type": "roformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "rotary_value": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19f3725b0308152241636468ce4079ae99c17178837afffdd76c992e7a03b6c0
+size 496816360

runs/Apr08_21-57-51_223587958e7a/events.out.tfevents.1712613473.223587958e7a.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44444d94c7a786cedaaded46e5ac44d334e59b1b4b8d095547f4b5b9f1a2bb27
+size 4802

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e5ac440da7bc36a7c5aee10a05d2e2a877dbda6db332d2118204302d831bfb
+size 4984