Upload folder using huggingface_hub

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+base_model: EleutherAI/polyglot-ko-12.8b
+tags:
+- generated_from_trainer
+model-index:
+- name: gollm-12.8b-koalpaca-v1.1c-a100
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# gollm-12.8b-koalpaca-v1.1c-a100
+
+This model is a fine-tuned version of [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.32.0.dev0
+- Pytorch 2.0.0+cu117
+- Datasets 2.11.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "EleutherAI/polyglot-ko-12.8b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_steps": "global_step301000",
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.5,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 30080
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.32.0.dev0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3b3e03e9efedd33b709400b35d5b56510996f24a98621ff1b77c56fc44364e
+size 24400263

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4703b440b92d4d0288c86ded543b257cceb5ff4c5105c8a576a9e03441a00d79
+size 9845571882

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15933797548214b9b484fb2e73b72f8674029a271273fe90a124d7837cea1f83
+size 9963619141

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6798a8003c1562ccd87db77177166e7d8bf79911f2cb94565ebfc6e35187d77
+size 9753862981

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431cbc840010487949594bb69360151957f659a59cba4b8662d0624f01878984
+size 9648962453

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b485d2399e157850c53be846a3a6f9d6975ad2c5d687ec2038ecdd3874984673
+size 9648984817

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67411ba523ab7d4596aacb737503f2ef49676c5ef67232fd0cd26779b8087484
+size 2713607223

pytorch_model.bin.index.json

@@ -0,0 +1,531 @@
+{
+  "metadata": {
+    "total_size": 51574420480
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.38.attention.dense.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.38.attention.dense.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.38.attention.query_key_value.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.38.attention.query_key_value.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.38.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.38.input_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.38.post_attention_layernorm.bias": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "gpt_neox.layers.39.attention.dense.bias": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.39.attention.dense.weight": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.39.attention.query_key_value.bias": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.39.attention.query_key_value.weight": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.39.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.39.input_layernorm.bias": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.39.post_attention_layernorm.bias": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00006.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36fc71bd44bd7f04f2599c5dface64c517de1a7ab7bac3600f3f6470c6c72673
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c8d7ec3f6782cb179ea301ca7cd0c2f331654a2f387fc22852b2461b338be9
+size 627

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.042253521126761,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.995598591549296e-05,
+      "loss": 2.3044,
+      "step": 1
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 2.7992957746478874e-05,
+      "loss": 0.9153,
+      "step": 500
+    },
+    {
+      "epoch": 7.04,
+      "learning_rate": 6.0299295774647895e-06,
+      "loss": 0.0323,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1136,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 2.503610335399772e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2453adc6b4d1e31885a9bf772c36b7198f070d41839ab54ca7c05f9a1b3a893d
+size 4091