Training in progress, step 500

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "smallcloudai/Refact-1_6B-fim",
+  "architectures": [
+    "GPTRefactForCausalLM"
+  ],
+  "attention_bias_in_fp32": true,
+  "attention_softmax_in_fp32": true,
+  "auto_map": {
+    "AutoConfig": "smallcloudai/Refact-1_6B-fim--configuration_gpt_refact.GPTRefactConfig",
+    "AutoModelForCausalLM": "smallcloudai/Refact-1_6B-fim--modeling_gpt_refact.GPTRefactForCausalLM"
+  },
+  "do_sample": true,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt_refact",
+  "multi_query": true,
+  "n_embd": 2048,
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 32,
+  "n_positions": 4096,
+  "scale_attention_softmax_in_fp32": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 49216
+}

runs/Jan20_22-17-14_3d4e1e4c3bd8/events.out.tfevents.1705789037.3d4e1e4c3bd8.15857.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3993212b288651cc080d606aa11c76223eca9648fd23a6a418bba9fd17ff9e
+size 4586

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6472cd4cdceb49f2a4a26bfa9a6773478bab6543f1c2b8382c6411fe047dbb39
+size 4664