Training in progress, step 2500

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "austindavis/gpt2-lichess-uci-201601",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 512,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 8,
+  "n_positions": 512,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 72
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745dc3f0b377b5964a13a25068588edf0982bb108f77da9f6fca789b893d3af0
+size 102086376

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc1ae221efdc5b79752791f4901487cd4654abf4eb6dd2700df4ee44eae6578
+size 4984