Add files using upload-large-folder tool

neo_base/100e1/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9d44a6295d0cd75f94510d6146c6751b4f411e465491ef207249cbf31c2961f
+size 4993794184

neo_base/100e1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7882000eb1f7dee3fc2191cf584a87ded2a70d5abfe0c5d2d9f055ff0e1dfc8e
+size 10524880634

neo_base/100e2/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d1748f315d9a67fbed2100a173e524fecb96a818eebec04e52b6d9742e8cd2
+size 4993794184

neo_base/100e3/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d4e8a9c6ea0b0f1db8f6d5ca5707cf9b86c72bac0bbc85587472c090b4b792
+size 4993794184

neo_base/100e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec0e4f84ec20a2fe70650bc957d2ab80a9f4cc71ff7382b3f8b3d08ecf6b643
+size 10524880634

neo_base/10e1/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94bc09b2cb2e3fa19668365c2f08290a59ebdd5adbe1155dc3db898eaf8cdfa1
+size 4993794184

neo_base/10e2/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2469b07c40cad5ccffb51f8190990f4739a73ab92fe415907881f300dc7cdba
+size 4993794184

neo_base/10e3/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7526ebc6e4f2f8017b4c67d37f9c3fa456316fb6a27725fa69d2a7ae8ce258a
+size 4993794184

neo_base/110e3/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155c5b56b85fb916e19f8f23ea2bd6e554223574fb11577fc15f6932e2018e5d
+size 4993794184

neo_base/20e1/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04ba97e9da669999d0b564dc0e739a3c5bdea3dd4bc65501a256726f5888492
+size 4993794184

neo_base/20e2/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4b7663569430cedb83dbf18babb4b1796dd3ceafe9b3d223af1b300c55f470
+size 4993794184

neo_base/20e3/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d57f837f870b9edc0b760d4113b2e3909bd7b92a1381ccf1bc38f077f7cb3b
+size 4993794184

neo_base/30e1/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c21b0250546db8b04331dec64adf58c1b4ca609b5f9c4b012654b6de8d1e96
+size 4993794184

neo_base/30e2/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c61d76f165a59c334752e5ad1397f00089857290bf67110d3a7f37f3f4ffeb1
+size 4993794184

neo_base/30e2/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92dac1afced5bb47c4a658b29fe4aa71f97635239b3cec410253d71aa304d414
+size 268543784

neo_base/30e2/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "return_tensors": "pt",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

neo_base/30e2/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2857142857142856,
+  "eval_steps": 500,
+  "global_step": 1170,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5494505494505495,
+      "grad_norm": 1.1440719366073608,
+      "learning_rate": 2e-05,
+      "loss": 1.759,
+      "step": 500
+    },
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 0.9083975553512573,
+      "learning_rate": 1.5515695067264575e-05,
+      "loss": 1.5431,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 90,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.68231533821952e+16,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}

neo_base/30e2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a5bb96c5a443f7368103cd40402a9a2e5fe9e3679b82d0c94667c2b51b4f72
+size 5240

neo_base/30e3/config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-1.3B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      12
+    ]
+  ],
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 16,
+  "num_layers": 24,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 0.9
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

neo_base/30e3/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

neo_base/30e3/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa98daef5cf2ce72a7f54d781450e5c41a93730c3bf33b1cd9443c1e18163dd
+size 4993794184

neo_base/30e3/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359b084de709ae3d01a4afef91c5f3913d2dfba357c5451748bb0c025afd0e43
+size 268543784

neo_base/30e3/model.safetensors.index.json

@@ -0,0 +1,323 @@
+{
+  "metadata": {
+    "total_size": 5262303232
+  },
+  "weight_map": {
+    "transformer.h.0.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.out_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.3.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00002.safetensors",
+    "transformer.wte.weight": "model-00001-of-00002.safetensors"
+  }
+}

neo_base/30e3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

neo_base/30e3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dfa4d04d26f5a45d526bec8b70828de2f99e276685de402475332c9e78d58c5
+size 1064

neo_base/30e3/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

neo_base/30e3/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "return_tensors": "pt",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

neo_base/30e3/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2747252747252746,
+  "eval_steps": 500,
+  "global_step": 2070,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5494505494505495,
+      "grad_norm": 1.1440719366073608,
+      "learning_rate": 2e-05,
+      "loss": 1.759,
+      "step": 500
+    },
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 0.9083975553512573,
+      "learning_rate": 1.5515695067264575e-05,
+      "loss": 1.5431,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6483516483516483,
+      "grad_norm": 0.9180422425270081,
+      "learning_rate": 1.1031390134529149e-05,
+      "loss": 1.3968,
+      "step": 1500
+    },
+    {
+      "epoch": 2.197802197802198,
+      "grad_norm": 1.0042611360549927,
+      "learning_rate": 6.547085201793723e-06,
+      "loss": 1.3497,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 90,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.53599485673472e+17,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}

neo_base/30e3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a5bb96c5a443f7368103cd40402a9a2e5fe9e3679b82d0c94667c2b51b4f72
+size 5240

neo_base/40e1/config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-1.3B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      12
+    ]
+  ],
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 16,
+  "num_layers": 24,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 0.9
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

neo_base/40e1/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

neo_base/40e1/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf2da2d1ca429b4daa0b7acb4ab73e42316a7ff87f68c5be13352a6d04a9ca9
+size 268543784

neo_base/40e1/model.safetensors.index.json

@@ -0,0 +1,323 @@
+{
+  "metadata": {
+    "total_size": 5262303232
+  },
+  "weight_map": {
+    "transformer.h.0.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.out_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.3.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00002.safetensors",
+    "transformer.wte.weight": "model-00001-of-00002.safetensors"
+  }
+}

neo_base/40e1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

neo_base/40e1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0086f1da157e9b30752b9c77fad98f76e07915b90505270de17f66330f93eb30
+size 1064

neo_base/40e1/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

neo_base/40e1/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": null,
+  "return_tensors": "pt",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

neo_base/40e1/trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3956043956043956,
+  "eval_steps": 500,
+  "global_step": 360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 500,
+  "max_steps": 2730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 90,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.67290947878912e+16,
+  "train_batch_size": 80,
+  "trial_name": null,
+  "trial_params": null
+}

neo_base/40e1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a5bb96c5a443f7368103cd40402a9a2e5fe9e3679b82d0c94667c2b51b4f72
+size 5240

neo_base/40e2/config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-1.3B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      12
+    ]
+  ],
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 16,
+  "num_layers": 24,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 0.9
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

neo_base/40e2/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}