Upload folder using huggingface_hub

checkpoint-1024/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/home/vault/c106fa/c106fa11/minipile_marcus/regular/pythia1.4b_dedup_untrained",
+  "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": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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": "4.47.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

checkpoint-1024/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.47.1"
+}

checkpoint-1024/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4831f2865cac402dbbf5d0cb1043c06f45dddf4b4dc5b9607866f458fb5f686
+size 4977966760

checkpoint-1024/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8bd81362c3715a9fa27fb35b320fc0061032b7ec51e441df30a17e7606f4815
+size 680658856

checkpoint-1024/model.safetensors.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_size": 5658591232
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors"
+  }
+}

checkpoint-1024/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff907a7b81887585d69839615ef952ca1038c8f0e722f0672adebad773928bdc
+size 11317433298

checkpoint-1024/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee31c34fa1004b0e8d3e73f2c24d25dc2bd16a545fb0f5eba40502426686703e
+size 15984

checkpoint-1024/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5afa94de38aab896e6b809e82ac1f7be77ec803161b05f7897e959d56250deba
+size 15984

checkpoint-1024/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5004fab2ff664143e70ef16a0556e48c83fdad5c8c7cbea017b8a1a7e43496a0
+size 15984

checkpoint-1024/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b302d0abf96b5fd918db631fb30db7e78a16e2763cc51bdad8cac5e6e5695c
+size 15984

checkpoint-1024/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3021f42768f056ae4c06a24a27f0dd34528360a3d6a473027eb0bd052fdea1
+size 15984

checkpoint-1024/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5911d37d531a36b3b7d9b95b56b5038ca2bbf3493ee8178e2330790edfdc02c1
+size 15984

checkpoint-1024/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a43190c9afb367a5134733a294d4f31a56cedacb61492d97fd97bb2087ece22
+size 15984

checkpoint-1024/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b12c90cb0f68fb4d5c5a30dad19b050bee259ad88ca59573636d9b477fc828
+size 15984

checkpoint-1024/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a580f0f1f55f914888f4d2b939067dfc5732198cab8e074ca0bbd27cb611eda
+size 16976119594

checkpoint-1024/trainer_state.json

@@ -0,0 +1,827 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.048128,
+  "eval_steps": 100,
+  "global_step": 1024,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01024,
+      "grad_norm": 269.9034729003906,
+      "learning_rate": 0.0001999995200527669,
+      "loss": 624.6766,
+      "step": 10
+    },
+    {
+      "epoch": 0.02048,
+      "grad_norm": 73.23262786865234,
+      "learning_rate": 0.000199941931959037,
+      "loss": 544.9223,
+      "step": 20
+    },
+    {
+      "epoch": 0.03072,
+      "grad_norm": 95.47492218017578,
+      "learning_rate": 0.00019978841775475367,
+      "loss": 511.6501,
+      "step": 30
+    },
+    {
+      "epoch": 0.04096,
+      "grad_norm": 145.1549530029297,
+      "learning_rate": 0.00019953912478568305,
+      "loss": 497.5438,
+      "step": 40
+    },
+    {
+      "epoch": 0.0512,
+      "grad_norm": 150.53515625,
+      "learning_rate": 0.00019919429232781712,
+      "loss": 497.208,
+      "step": 50
+    },
+    {
+      "epoch": 0.06144,
+      "grad_norm": 151.51736450195312,
+      "learning_rate": 0.0001987542513577122,
+      "loss": 496.9036,
+      "step": 60
+    },
+    {
+      "epoch": 0.07168,
+      "grad_norm": 159.39337158203125,
+      "learning_rate": 0.0001982771584048096,
+      "loss": 489.2719,
+      "step": 70
+    },
+    {
+      "epoch": 0.08192,
+      "grad_norm": 148.92176818847656,
+      "learning_rate": 0.00019765746006440455,
+      "loss": 482.9451,
+      "step": 80
+    },
+    {
+      "epoch": 0.09216,
+      "grad_norm": 139.00486755371094,
+      "learning_rate": 0.0001970195706599109,
+      "loss": 476.9848,
+      "step": 90
+    },
+    {
+      "epoch": 0.1024,
+      "grad_norm": 157.25439453125,
+      "learning_rate": 0.00019622236172137374,
+      "loss": 471.4595,
+      "step": 100
+    },
+    {
+      "epoch": 0.1024,
+      "eval_loss": 7.320011615753174,
+      "eval_runtime": 3.4958,
+      "eval_samples_per_second": 143.029,
+      "eval_steps_per_second": 9.154,
+      "step": 100
+    },
+    {
+      "epoch": 0.11264,
+      "grad_norm": 141.9667510986328,
+      "learning_rate": 0.0001953327967844356,
+      "loss": 468.9138,
+      "step": 110
+    },
+    {
+      "epoch": 0.12288,
+      "grad_norm": 99.36428833007812,
+      "learning_rate": 0.0001943517296699384,
+      "loss": 468.5555,
+      "step": 120
+    },
+    {
+      "epoch": 0.13312,
+      "grad_norm": 98.90169525146484,
+      "learning_rate": 0.00019328010202420258,
+      "loss": 463.3139,
+      "step": 130
+    },
+    {
+      "epoch": 0.14336,
+      "grad_norm": 77.31971740722656,
+      "learning_rate": 0.00019211894241521758,
+      "loss": 458.0901,
+      "step": 140
+    },
+    {
+      "epoch": 0.1536,
+      "grad_norm": 134.48403930664062,
+      "learning_rate": 0.0001908693653454033,
+      "loss": 454.8131,
+      "step": 150
+    },
+    {
+      "epoch": 0.16384,
+      "grad_norm": 95.27815246582031,
+      "learning_rate": 0.00018953257018189024,
+      "loss": 454.0167,
+      "step": 160
+    },
+    {
+      "epoch": 0.17408,
+      "grad_norm": 87.9055404663086,
+      "learning_rate": 0.00018810984000534458,
+      "loss": 449.3531,
+      "step": 170
+    },
+    {
+      "epoch": 0.18432,
+      "grad_norm": 116.1905288696289,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 447.6146,
+      "step": 180
+    },
+    {
+      "epoch": 0.19456,
+      "grad_norm": 81.48722076416016,
+      "learning_rate": 0.00018501211803518468,
+      "loss": 450.6066,
+      "step": 190
+    },
+    {
+      "epoch": 0.2048,
+      "grad_norm": 75.57894897460938,
+      "learning_rate": 0.00018334009949228061,
+      "loss": 448.9498,
+      "step": 200
+    },
+    {
+      "epoch": 0.2048,
+      "eval_loss": 6.992556571960449,
+      "eval_runtime": 3.4911,
+      "eval_samples_per_second": 143.219,
+      "eval_steps_per_second": 9.166,
+      "step": 200
+    },
+    {
+      "epoch": 0.21504,
+      "grad_norm": 160.8426513671875,
+      "learning_rate": 0.00018158808958398338,
+      "loss": 449.3857,
+      "step": 210
+    },
+    {
+      "epoch": 0.22528,
+      "grad_norm": 86.6707992553711,
+      "learning_rate": 0.00017975776992173344,
+      "loss": 449.0133,
+      "step": 220
+    },
+    {
+      "epoch": 0.23552,
+      "grad_norm": 65.60407257080078,
+      "learning_rate": 0.00017785089728011798,
+      "loss": 446.8142,
+      "step": 230
+    },
+    {
+      "epoch": 0.24576,
+      "grad_norm": 125.04796600341797,
+      "learning_rate": 0.00017586930191068655,
+      "loss": 446.0437,
+      "step": 240
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 89.98313903808594,
+      "learning_rate": 0.00017381488578524173,
+      "loss": 445.3744,
+      "step": 250
+    },
+    {
+      "epoch": 0.26624,
+      "grad_norm": 269.5317077636719,
+      "learning_rate": 0.00017168962077029147,
+      "loss": 446.719,
+      "step": 260
+    },
+    {
+      "epoch": 0.27648,
+      "grad_norm": 73.03639221191406,
+      "learning_rate": 0.00016949554673441534,
+      "loss": 448.0971,
+      "step": 270
+    },
+    {
+      "epoch": 0.28672,
+      "grad_norm": 122.57962799072266,
+      "learning_rate": 0.00016723476959036083,
+      "loss": 448.991,
+      "step": 280
+    },
+    {
+      "epoch": 0.29696,
+      "grad_norm": 81.79669189453125,
+      "learning_rate": 0.0001649094592737497,
+      "loss": 444.1866,
+      "step": 290
+    },
+    {
+      "epoch": 0.3072,
+      "grad_norm": 74.33326721191406,
+      "learning_rate": 0.00016252184766033342,
+      "loss": 436.623,
+      "step": 300
+    },
+    {
+      "epoch": 0.3072,
+      "eval_loss": 6.777511119842529,
+      "eval_runtime": 3.4227,
+      "eval_samples_per_second": 146.083,
+      "eval_steps_per_second": 9.349,
+      "step": 300
+    },
+    {
+      "epoch": 0.31744,
+      "grad_norm": 113.46410369873047,
+      "learning_rate": 0.0001600742264237979,
+      "loss": 435.7422,
+      "step": 310
+    },
+    {
+      "epoch": 0.32768,
+      "grad_norm": 99.42645263671875,
+      "learning_rate": 0.00015756894483617267,
+      "loss": 439.4858,
+      "step": 320
+    },
+    {
+      "epoch": 0.33792,
+      "grad_norm": 328.0025634765625,
+      "learning_rate": 0.0001550084075129563,
+      "loss": 447.5792,
+      "step": 330
+    },
+    {
+      "epoch": 0.34816,
+      "grad_norm": 82.54906463623047,
+      "learning_rate": 0.00015239507210512194,
+      "loss": 446.5024,
+      "step": 340
+    },
+    {
+      "epoch": 0.3584,
+      "grad_norm": 62.32942581176758,
+      "learning_rate": 0.00014973144694021876,
+      "loss": 437.9146,
+      "step": 350
+    },
+    {
+      "epoch": 0.36864,
+      "grad_norm": 64.61022186279297,
+      "learning_rate": 0.00014702008861483266,
+      "loss": 430.4142,
+      "step": 360
+    },
+    {
+      "epoch": 0.37888,
+      "grad_norm": 133.777587890625,
+      "learning_rate": 0.00014426359954071796,
+      "loss": 428.6971,
+      "step": 370
+    },
+    {
+      "epoch": 0.38912,
+      "grad_norm": 218.512939453125,
+      "learning_rate": 0.00014146462544695426,
+      "loss": 435.1475,
+      "step": 380
+    },
+    {
+      "epoch": 0.39936,
+      "grad_norm": 125.56941986083984,
+      "learning_rate": 0.00013862585284052714,
+      "loss": 445.5835,
+      "step": 390
+    },
+    {
+      "epoch": 0.4096,
+      "grad_norm": 109.06041717529297,
+      "learning_rate": 0.00013575000642776893,
+      "loss": 446.3095,
+      "step": 400
+    },
+    {
+      "epoch": 0.4096,
+      "eval_loss": 6.905622959136963,
+      "eval_runtime": 3.4269,
+      "eval_samples_per_second": 145.903,
+      "eval_steps_per_second": 9.338,
+      "step": 400
+    },
+    {
+      "epoch": 0.41984,
+      "grad_norm": 69.12989044189453,
+      "learning_rate": 0.0001328398464991355,
+      "loss": 438.9709,
+      "step": 410
+    },
+    {
+      "epoch": 0.43008,
+      "grad_norm": 68.11474609375,
+      "learning_rate": 0.00012989816627982848,
+      "loss": 432.2964,
+      "step": 420
+    },
+    {
+      "epoch": 0.44032,
+      "grad_norm": 65.17674255371094,
+      "learning_rate": 0.00012692778924880603,
+      "loss": 428.2125,
+      "step": 430
+    },
+    {
+      "epoch": 0.45056,
+      "grad_norm": 114.95523834228516,
+      "learning_rate": 0.0001239315664287558,
+      "loss": 426.8882,
+      "step": 440
+    },
+    {
+      "epoch": 0.4608,
+      "grad_norm": 185.0157470703125,
+      "learning_rate": 0.00012091237364963071,
+      "loss": 435.8043,
+      "step": 450
+    },
+    {
+      "epoch": 0.47104,
+      "grad_norm": 92.59754180908203,
+      "learning_rate": 0.00011787310878837422,
+      "loss": 440.9751,
+      "step": 460
+    },
+    {
+      "epoch": 0.48128,
+      "grad_norm": 75.24162292480469,
+      "learning_rate": 0.00011481668898748475,
+      "loss": 439.3276,
+      "step": 470
+    },
+    {
+      "epoch": 0.49152,
+      "grad_norm": 55.42325210571289,
+      "learning_rate": 0.00011174604785508813,
+      "loss": 432.4603,
+      "step": 480
+    },
+    {
+      "epoch": 0.50176,
+      "grad_norm": 62.27671813964844,
+      "learning_rate": 0.00010866413264920678,
+      "loss": 427.5299,
+      "step": 490
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 65.43367767333984,
+      "learning_rate": 0.00010557390144892684,
+      "loss": 425.4595,
+      "step": 500
+    },
+    {
+      "epoch": 0.512,
+      "eval_loss": 6.613161087036133,
+      "eval_runtime": 3.4182,
+      "eval_samples_per_second": 146.277,
+      "eval_steps_per_second": 9.362,
+      "step": 500
+    },
+    {
+      "epoch": 0.52224,
+      "grad_norm": 175.58470153808594,
+      "learning_rate": 0.0001024783203151793,
+      "loss": 425.5378,
+      "step": 510
+    },
+    {
+      "epoch": 0.53248,
+      "grad_norm": 199.92291259765625,
+      "learning_rate": 9.938036044386005e-05,
+      "loss": 431.3893,
+      "step": 520
+    },
+    {
+      "epoch": 0.54272,
+      "grad_norm": 212.65650939941406,
+      "learning_rate": 9.628299531402117e-05,
+      "loss": 443.9659,
+      "step": 530
+    },
+    {
+      "epoch": 0.55296,
+      "grad_norm": 93.11270141601562,
+      "learning_rate": 9.318919783387094e-05,
+      "loss": 443.3476,
+      "step": 540
+    },
+    {
+      "epoch": 0.5632,
+      "grad_norm": 93.02433013916016,
+      "learning_rate": 9.010193748732155e-05,
+      "loss": 438.1048,
+      "step": 550
+    },
+    {
+      "epoch": 0.57344,
+      "grad_norm": 72.0661849975586,
+      "learning_rate": 8.702417748382385e-05,
+      "loss": 431.1463,
+      "step": 560
+    },
+    {
+      "epoch": 0.58368,
+      "grad_norm": 67.0578842163086,
+      "learning_rate": 8.395887191422397e-05,
+      "loss": 427.2931,
+      "step": 570
+    },
+    {
+      "epoch": 0.59392,
+      "grad_norm": 85.532958984375,
+      "learning_rate": 8.090896291537273e-05,
+      "loss": 424.9293,
+      "step": 580
+    },
+    {
+      "epoch": 0.60416,
+      "grad_norm": 72.48572540283203,
+      "learning_rate": 7.787737784620803e-05,
+      "loss": 424.9051,
+      "step": 590
+    },
+    {
+      "epoch": 0.6144,
+      "grad_norm": 237.96592712402344,
+      "learning_rate": 7.486702647802213e-05,
+      "loss": 425.6438,
+      "step": 600
+    },
+    {
+      "epoch": 0.6144,
+      "eval_loss": 6.683709621429443,
+      "eval_runtime": 3.436,
+      "eval_samples_per_second": 145.519,
+      "eval_steps_per_second": 9.313,
+      "step": 600
+    },
+    {
+      "epoch": 0.62464,
+      "grad_norm": 178.17239379882812,
+      "learning_rate": 7.188079820160904e-05,
+      "loss": 432.3896,
+      "step": 610
+    },
+    {
+      "epoch": 0.63488,
+      "grad_norm": 84.38874053955078,
+      "learning_rate": 6.892155925397436e-05,
+      "loss": 434.9848,
+      "step": 620
+    },
+    {
+      "epoch": 0.64512,
+      "grad_norm": 66.67383575439453,
+      "learning_rate": 6.59921499672677e-05,
+      "loss": 433.8923,
+      "step": 630
+    },
+    {
+      "epoch": 0.65536,
+      "grad_norm": 74.11187744140625,
+      "learning_rate": 6.309538204257977e-05,
+      "loss": 430.2817,
+      "step": 640
+    },
+    {
+      "epoch": 0.6656,
+      "grad_norm": 95.32003784179688,
+      "learning_rate": 6.02340358512196e-05,
+      "loss": 427.1533,
+      "step": 650
+    },
+    {
+      "epoch": 0.67584,
+      "grad_norm": 71.91348266601562,
+      "learning_rate": 5.7410857766062966e-05,
+      "loss": 425.3034,
+      "step": 660
+    },
+    {
+      "epoch": 0.68608,
+      "grad_norm": 95.72642517089844,
+      "learning_rate": 5.4628557525532976e-05,
+      "loss": 425.3343,
+      "step": 670
+    },
+    {
+      "epoch": 0.69632,
+      "grad_norm": 161.08612060546875,
+      "learning_rate": 5.188980563274315e-05,
+      "loss": 426.5362,
+      "step": 680
+    },
+    {
+      "epoch": 0.70656,
+      "grad_norm": 130.4775848388672,
+      "learning_rate": 4.9197230792299195e-05,
+      "loss": 431.4921,
+      "step": 690
+    },
+    {
+      "epoch": 0.7168,
+      "grad_norm": 102.47798919677734,
+      "learning_rate": 4.6553417387219886e-05,
+      "loss": 432.9831,
+      "step": 700
+    },
+    {
+      "epoch": 0.7168,
+      "eval_loss": 6.725553512573242,
+      "eval_runtime": 3.4338,
+      "eval_samples_per_second": 145.61,
+      "eval_steps_per_second": 9.319,
+      "step": 700
+    },
+    {
+      "epoch": 0.72704,
+      "grad_norm": 73.72420501708984,
+      "learning_rate": 4.421777466693434e-05,
+      "loss": 431.4859,
+      "step": 710
+    },
+    {
+      "epoch": 0.73728,
+      "grad_norm": 83.63558197021484,
+      "learning_rate": 4.167355837898584e-05,
+      "loss": 428.698,
+      "step": 720
+    },
+    {
+      "epoch": 0.74752,
+      "grad_norm": 69.27027893066406,
+      "learning_rate": 3.918532488602094e-05,
+      "loss": 428.0623,
+      "step": 730
+    },
+    {
+      "epoch": 0.75776,
+      "grad_norm": 107.68405151367188,
+      "learning_rate": 3.675546244046228e-05,
+      "loss": 425.6424,
+      "step": 740
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 96.42312622070312,
+      "learning_rate": 3.438630326912414e-05,
+      "loss": 425.8188,
+      "step": 750
+    },
+    {
+      "epoch": 0.77824,
+      "grad_norm": 116.1615982055664,
+      "learning_rate": 3.208012133469799e-05,
+      "loss": 425.9528,
+      "step": 760
+    },
+    {
+      "epoch": 0.78848,
+      "grad_norm": 91.75414276123047,
+      "learning_rate": 2.9839130153161154e-05,
+      "loss": 426.8583,
+      "step": 770
+    },
+    {
+      "epoch": 0.79872,
+      "grad_norm": 79.31800079345703,
+      "learning_rate": 2.766548066920338e-05,
+      "loss": 425.4576,
+      "step": 780
+    },
+    {
+      "epoch": 0.80896,
+      "grad_norm": 108.06861114501953,
+      "learning_rate": 2.5561259191710407e-05,
+      "loss": 425.0249,
+      "step": 790
+    },
+    {
+      "epoch": 0.8192,
+      "grad_norm": 86.25403594970703,
+      "learning_rate": 2.3528485391286147e-05,
+      "loss": 426.0778,
+      "step": 800
+    },
+    {
+      "epoch": 0.8192,
+      "eval_loss": 6.630011558532715,
+      "eval_runtime": 3.4108,
+      "eval_samples_per_second": 146.591,
+      "eval_steps_per_second": 9.382,
+      "step": 800
+    },
+    {
+      "epoch": 0.82944,
+      "grad_norm": 80.1161117553711,
+      "learning_rate": 2.1569110361735677e-05,
+      "loss": 426.9529,
+      "step": 810
+    },
+    {
+      "epoch": 0.83968,
+      "grad_norm": 92.57079315185547,
+      "learning_rate": 2e-05,
+      "loss": 425.7674,
+      "step": 820
+    },
+    {
+      "epoch": 0.84992,
+      "grad_norm": 76.28582000732422,
+      "learning_rate": 2e-05,
+      "loss": 425.3365,
+      "step": 830
+    },
+    {
+      "epoch": 0.86016,
+      "grad_norm": 111.58943176269531,
+      "learning_rate": 2e-05,
+      "loss": 424.6131,
+      "step": 840
+    },
+    {
+      "epoch": 0.8704,
+      "grad_norm": 158.44044494628906,
+      "learning_rate": 2e-05,
+      "loss": 425.0354,
+      "step": 850
+    },
+    {
+      "epoch": 0.88064,
+      "grad_norm": 101.99372100830078,
+      "learning_rate": 2e-05,
+      "loss": 424.9413,
+      "step": 860
+    },
+    {
+      "epoch": 0.89088,
+      "grad_norm": 140.2552490234375,
+      "learning_rate": 2e-05,
+      "loss": 426.5773,
+      "step": 870
+    },
+    {
+      "epoch": 0.90112,
+      "grad_norm": 117.06301879882812,
+      "learning_rate": 2e-05,
+      "loss": 427.2063,
+      "step": 880
+    },
+    {
+      "epoch": 0.91136,
+      "grad_norm": 147.27670288085938,
+      "learning_rate": 2e-05,
+      "loss": 427.2577,
+      "step": 890
+    },
+    {
+      "epoch": 0.9216,
+      "grad_norm": 109.34888458251953,
+      "learning_rate": 2e-05,
+      "loss": 428.4192,
+      "step": 900
+    },
+    {
+      "epoch": 0.9216,
+      "eval_loss": 6.663826942443848,
+      "eval_runtime": 3.429,
+      "eval_samples_per_second": 145.817,
+      "eval_steps_per_second": 9.332,
+      "step": 900
+    },
+    {
+      "epoch": 0.93184,
+      "grad_norm": 145.62522888183594,
+      "learning_rate": 2e-05,
+      "loss": 428.9891,
+      "step": 910
+    },
+    {
+      "epoch": 0.94208,
+      "grad_norm": 90.70750427246094,
+      "learning_rate": 2e-05,
+      "loss": 429.0984,
+      "step": 920
+    },
+    {
+      "epoch": 0.95232,
+      "grad_norm": 92.83578491210938,
+      "learning_rate": 2e-05,
+      "loss": 429.0002,
+      "step": 930
+    },
+    {
+      "epoch": 0.96256,
+      "grad_norm": 125.1180648803711,
+      "learning_rate": 2e-05,
+      "loss": 428.4883,
+      "step": 940
+    },
+    {
+      "epoch": 0.9728,
+      "grad_norm": 132.3828125,
+      "learning_rate": 2e-05,
+      "loss": 428.6993,
+      "step": 950
+    },
+    {
+      "epoch": 0.98304,
+      "grad_norm": 100.2248306274414,
+      "learning_rate": 2e-05,
+      "loss": 429.164,
+      "step": 960
+    },
+    {
+      "epoch": 0.99328,
+      "grad_norm": 112.38407897949219,
+      "learning_rate": 2e-05,
+      "loss": 430.1383,
+      "step": 970
+    },
+    {
+      "epoch": 1.003072,
+      "grad_norm": 104.0753173828125,
+      "learning_rate": 2e-05,
+      "loss": 410.847,
+      "step": 980
+    },
+    {
+      "epoch": 1.013312,
+      "grad_norm": 137.40553283691406,
+      "learning_rate": 2e-05,
+      "loss": 431.1839,
+      "step": 990
+    },
+    {
+      "epoch": 1.023552,
+      "grad_norm": 191.53709411621094,
+      "learning_rate": 2e-05,
+      "loss": 431.9959,
+      "step": 1000
+    },
+    {
+      "epoch": 1.023552,
+      "eval_loss": 6.718299865722656,
+      "eval_runtime": 3.4132,
+      "eval_samples_per_second": 146.49,
+      "eval_steps_per_second": 9.375,
+      "step": 1000
+    },
+    {
+      "epoch": 1.033792,
+      "grad_norm": 188.12156677246094,
+      "learning_rate": 2e-05,
+      "loss": 432.0317,
+      "step": 1010
+    },
+    {
+      "epoch": 1.044032,
+      "grad_norm": 119.64492797851562,
+      "learning_rate": 2e-05,
+      "loss": 432.8214,
+      "step": 1020
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1024,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1024,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.134583528711782e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1024/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05808bb06f5a381500cd04f06a922b537630b6f18d2cfd53d4617345e2fb08c
+size 5368

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/home/vault/c106fa/c106fa11/minipile_marcus/regular/pythia1.4b_dedup_untrained",
+  "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": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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": "4.47.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.47.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4831f2865cac402dbbf5d0cb1043c06f45dddf4b4dc5b9607866f458fb5f686
+size 4977966760

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8bd81362c3715a9fa27fb35b320fc0061032b7ec51e441df30a17e7606f4815
+size 680658856

model.safetensors.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_size": 5658591232
+  },
+  "weight_map": {
+    "embed_out.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.embed_in.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors"
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05808bb06f5a381500cd04f06a922b537630b6f18d2cfd53d4617345e2fb08c
+size 5368