Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "EleutherAI/pythia-410m-deduped",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dcf83ad115c78cb967e0de0fc3baf39dac2a96248e1195b5731ea16c1f5d526
+size 1722117245

runs/Jun09_23-55-53_a0e27b829703/events.out.tfevents.1686354966.a0e27b829703.6532.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8be26bc03292d0df4e7cee492d047fbb892aceb933eb680965142ba1b280cafa
+size 4505

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027f5e09ae41c4a214db527beb0446d7ca08cc1aa15c8dedfe51e33a700c50e3
+size 3963