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": "4.38.2",
+  "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 sha256:4b711fc151bb5876a824bd95e4e26724369da1e17c2ff5a7ec9f7bdf5f518349
+size 496816360

runs/Apr08_01-45-38_bd20f88671d2/events.out.tfevents.1712540740.bd20f88671d2.1979.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e807ef0d5fda896547d0589ae04c346edf06271ce6c199d2727a396a9dbd5af
+size 4805

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5434fa2abb6ab1be1cd80da5d169d2a0f718d44d9cf48b9d7129c588ca43ecd
+size 4920