Training in progress, epoch 4

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "EleutherAI/pythia-410m-deduped",
+  "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": 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,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

logs/events.out.tfevents.1714434430.sphinx2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab02efd002bef48ce68ce58a05c1af610c940f119071becffa2c7a5dedfd9d7
+size 96287

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccfd328ae449537e0c5d331999f5cad0d265e80c665cca8217a0c23622192d2e
+size 1621370224

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3841e0685fc16f7f59d5f1d2f53621385338428e8a3039330bf3f010da6b5b
+size 4920