Training in progress, step 500

config.json

@@ -0,0 +1,21 @@
+{
+  "_name_or_path": "RWKV/rwkv-4-169m-pile",
+  "architectures": [
+    "RwkvForCausalLM"
+  ],
+  "attention_hidden_size": 768,
+  "bos_token_id": 0,
+  "context_length": 1024,
+  "eos_token_id": 0,
+  "hidden_size": 768,
+  "intermediate_size": 3072,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "rwkv",
+  "num_hidden_layers": 12,
+  "rescale_every": 6,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50277
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07aabd5f119c19d369da7adda682480c1789f6f5c382804318fe03fe0ed934eb
+size 677393760

runs/Mar27_22-07-25_cheng-ubuntu/events.out.tfevents.1711591647.cheng-ubuntu.10235.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d54a2d6a11e2947e840241d26856b52f9c50c581ee9f1229fa74d3b96a66ae
+size 4698

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06fd8028d73f657410440d332524f37c69f93c7a6d49285110934be9cf8b7e83
+size 4920