Training in progress, step 1

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b262ac0ba86d3a3ef9bc0c31362c8569f66cf2c1ac0b9b1030d844b0e655b0
+size 649308728

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1a96382c254dd3b1401dded6ee8dbf29d5e61a4d5b20b6064f43cbd1b96c76e
-size 6200
+oid sha256:d9c01b79c918572bc6bd707aa83504882309975a467b640980038b79497740ae
+size 6136